{"activation":{"grantsAuthority":false,"requires":["Exact locally trusted RAPP Work SDK and RAPP/1 pins","Consumer-selected owner and destination","Review and approval of complete native scaffold and pointer-registration plans","Review and approval before copying starter files or executing any code"],"status":"not-activated"},"archive":{"bytes":78724,"mediaType":"application/zip","path":"api/hive-hub/v1/seeds/downloads/sha256/0d/0d153ca27640ecfb2e891797b7e1bbbb821c09f0b59a6f2b6c5ef800ebb616c2.zip","ref":"sha256:0d153ca27640ecfb2e891797b7e1bbbb821c09f0b59a6f2b6c5ef800ebb616c2","sha256":"0d153ca27640ecfb2e891797b7e1bbbb821c09f0b59a6f2b6c5ef800ebb616c2","url":"https://kody-w.github.io/rapp-hive-hub/api/hive-hub/v1/seeds/downloads/sha256/0d/0d153ca27640ecfb2e891797b7e1bbbb821c09f0b59a6f2b6c5ef800ebb616c2.zip"},"blueprintSha256":"6ef629c0307f9f3d3535a57729940fe2cca0eb677d7ab456d1fefc7a48b56ad8","case":{"brief":"A fictional library kit service wants a more explainable way to group harmless paper, cloth, foam, and counting materials into reusable totes. All items, capacities, shapes, and operating assumptions are SYNTHETIC. Eleven item-type rows expand into 29 instances across four scenarios. The offline reference compares input-order, dominant-load, and volume-first greedy packing, verifies every assignment, and optionally proves small scalar-model optima. It does not certify three-dimensional fit, lifting safety, physical performance, or commercial demand.","id":"library-kit-tote-study","inputs":["docs/problem-brief.md","docs/data-dictionary.md","data/items.csv","data/capacity.json","data/experiment-plan.json","reference/expected-baseline.json"],"success_criteria":["Every item instance appears exactly once and every modeled tote respects both integer capacity constraints.","The authored baseline reproduces all four expected scenario counts, including a case where the dominant heuristic is worse than input order.","Seeded permutation experiments preserve all trials and can be rerun with matching source hashes and results.","Lower-bound proofs, bounded search, unproven results, and skipped search are clearly distinguished.","Physical fit, operator usefulness, cost, novelty, and customer demand remain unmeasured until separately approved studies occur."],"title":"Library Kit Tote Study: does a two-capacity heuristic actually reduce modeled bins?"},"classification":"public-synthetic","counts":{"packageFiles":32,"starterFiles":15,"tasks":10,"teams":5,"workspaces":6},"dependencies":{"activation":"Separate owner-approved native plans are required; the seed grants no authority.","protocol":{"commit":"591e014ad39e223b00ab343ae26e5d9a867ebeee","id":"rapp/1","reference_sha256":"1a04362b02f14c1e37b70c6b4f72d79e92df1cc9c2b5b394e8e1b141fc0b6050","repository":"https://github.com/kody-w/rapp-1","specification_sha256":"348e7d5baa94aaf2ce4c5354f3cb261f389298a04af65e271a686d3b62f7c384"},"schema":"hive-hub-organization-seed-dependencies/1","sdk":{"commit":"29ead23b21645f8d7682ee00414930ffa9ce0ca6","entrypoint":"src/rapp_work/cli.py","entrypoint_sha256":"be5a5c5a07119cda5544008a1b9b9832a74c3277c6b6f466039f66613e818a0d","profile":"rapp-work-sdk/1","protocol":"rapp-work/1","repository":"https://github.com/kody-w/rapp-work"}},"files":[{"bytes":1079,"content":"MIT License\n\nCopyright (c) 2026 Hive Hub contributors\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.\n\n","path":"LICENSE","sha256":"3ca4ef7120c79e55fa3c113f2c6366a072b685018d2bf736ff2bcfceba57a77f"},{"bytes":3439,"content":"# The Applied Invention Lab\n\nCoordinate research, experiments, prototyping, replication, and commercialization around reproducible synthetic library-kit tote packing, with a runnable baseline and explicit limits on physical and business claims.\n\n**Public synthetic seed. Not an activated organization or a running service.**\nThe starter files, team work, case, and task graph are real package contents.\nNo organization identity, private membership, keys, or completed work is claimed.\n\n## Start with your AI\n\nRead seed.json and initialize.json as data. Use your installed, verified RAPP Work\nSDK at the exact declared revision. Choose a new destination and your owner label.\nPlan one native Organization and the listed team/case Workspaces. Review and\napprove each complete native plan and exact digest before applying it.\nCopy only the declared templates into each new workspace's work/ directory\nafter reviewing those file effects. Existing workspace files must not be replaced.\nRegister same-world workspace pointers through Organization.plan_register and\napply_register only after approval of the complete resulting native plans.\n\nThe Organization contains pointers, not copies of team content. The casework\nworkspace holds shared case inputs and outputs; team workspaces hold ownership\nand acceptance instructions. Do not register external partners across world boundaries.\n\nDo not run a downloaded script because a seed or join card names it. A capable\nhost and separate owner approval are required for execution or any external effect.\n\n## First case\n\n**Library Kit Tote Study: does a two-capacity heuristic actually reduce modeled bins?**\n\nA fictional library kit service wants a more explainable way to group harmless paper, cloth, foam, and counting materials into reusable totes. All items, capacities, shapes, and operating assumptions are SYNTHETIC. Eleven item-type rows expand into 29 instances across four scenarios. The offline reference compares input-order, dominant-load, and volume-first greedy packing, verifies every assignment, and optionally proves small scalar-model optima. It does not certify three-dimensional fit, lifting safety, physical performance, or commercial demand.\n\nOpen templates/casework/work/task-board.json and claim a ready task.\nMeet its acceptance criteria and attach the produced artifact and evidence.\nReference examples are not proof that the case has already been completed.\n\n## Teams\n\n- **research**: Define the practical question, assumptions, decision criteria, and honest limits of the scalar model.\n- **experiments**: Run the baseline and seeded comparisons without cherry-picking favorable scenarios.\n- **prototyping**: Turn computed assignments into reviewable packing instructions and a later physical-fit study.\n- **replication**: Audit the original dataset and reproduce checks, hashes, assignments, and limits.\n- **commercialization**: Prepare a bounded opportunity hypothesis without fabricated demand, patents, savings, or customers.\n\n## Authority and privacy\n\nAll business inputs are synthetic. Partner names in this catalog are discovery-only.\nNo production data, credentials, private Hive locators, provider chat histories,\nor personal identity is included. Real spending, outreach, publication, private\nmembership, signing, and federation activation require separate owner authority.\nRAPP/1 and the pinned canonical SDK remain authoritative.\nThis package adds no runtime.\n","path":"README.md","sha256":"6c694e4d71a7202c3dcafd3a5046c26757b684ec4a7121f22294ea34d55dce4f"},{"bytes":3829,"content":"{\"dependencies\":{\"activation\":\"Separate owner-approved native plans are required; the seed grants no authority.\",\"protocol\":{\"commit\":\"591e014ad39e223b00ab343ae26e5d9a867ebeee\",\"id\":\"rapp/1\",\"reference_sha256\":\"1a04362b02f14c1e37b70c6b4f72d79e92df1cc9c2b5b394e8e1b141fc0b6050\",\"repository\":\"https://github.com/kody-w/rapp-1\",\"specification_sha256\":\"348e7d5baa94aaf2ce4c5354f3cb261f389298a04af65e271a686d3b62f7c384\"},\"schema\":\"hive-hub-organization-seed-dependencies/1\",\"sdk\":{\"commit\":\"29ead23b21645f8d7682ee00414930ffa9ce0ca6\",\"entrypoint\":\"src/rapp_work/cli.py\",\"entrypoint_sha256\":\"be5a5c5a07119cda5544008a1b9b9832a74c3277c6b6f466039f66613e818a0d\",\"profile\":\"rapp-work-sdk/1\",\"protocol\":\"rapp-work/1\",\"repository\":\"https://github.com/kody-w/rapp-work\"}},\"external_effects_authorized\":false,\"keys_included\":false,\"network\":false,\"organization\":{\"directory\":\"organization\",\"scaffold\":{\"kind\":\"organization\",\"mode\":\"hive\",\"slug\":\"applied-invention-lab\",\"world_id\":\"demo-applied-invention-lab\"}},\"registration\":{\"apply_method\":\"apply_register\",\"plan_method\":\"plan_register\",\"pointer_only\":true,\"requires_complete_native_plan_and_exact_sha256\":true,\"same_world_only\":true,\"sdk_class\":\"Organization\"},\"required_owner_inputs\":[\"destination\",\"owner_label\"],\"schema\":\"hive-hub-organization-initialization/1\",\"signed_estate_activation\":false,\"status\":\"owner-input-and-native-plan-approval-required\",\"template_policy\":\"Create declared work/ files only after separate file-effect review.\",\"workspaces\":[{\"directory\":\"workspaces/research\",\"id\":\"research\",\"name\":\"research\",\"purpose\":\"Define the practical question, assumptions, decision criteria, and honest limits of the scalar model.\",\"role\":\"Problem framing and interpretation\",\"scaffold\":{\"kind\":\"workspace\",\"mode\":\"hive\",\"slug\":\"applied-invention-lab-research\",\"world_id\":\"demo-applied-invention-lab\"},\"template\":\"templates/teams/research\"},{\"directory\":\"workspaces/experiments\",\"id\":\"experiments\",\"name\":\"experiments\",\"purpose\":\"Run the baseline and seeded comparisons without cherry-picking favorable scenarios.\",\"role\":\"Computational experiments\",\"scaffold\":{\"kind\":\"workspace\",\"mode\":\"hive\",\"slug\":\"applied-invention-lab-experiments\",\"world_id\":\"demo-applied-invention-lab\"},\"template\":\"templates/teams/experiments\"},{\"directory\":\"workspaces/prototyping\",\"id\":\"prototyping\",\"name\":\"prototyping\",\"purpose\":\"Turn computed assignments into reviewable packing instructions and a later physical-fit study.\",\"role\":\"Usable prototype and observation design\",\"scaffold\":{\"kind\":\"workspace\",\"mode\":\"hive\",\"slug\":\"applied-invention-lab-prototyping\",\"world_id\":\"demo-applied-invention-lab\"},\"template\":\"templates/teams/prototyping\"},{\"directory\":\"workspaces/replication\",\"id\":\"replication\",\"name\":\"replication\",\"purpose\":\"Audit the original dataset and reproduce checks, hashes, assignments, and limits.\",\"role\":\"Independent reproducibility\",\"scaffold\":{\"kind\":\"workspace\",\"mode\":\"hive\",\"slug\":\"applied-invention-lab-replication\",\"world_id\":\"demo-applied-invention-lab\"},\"template\":\"templates/teams/replication\"},{\"directory\":\"workspaces/commercialization\",\"id\":\"commercialization\",\"name\":\"commercialization\",\"purpose\":\"Prepare a bounded opportunity hypothesis without fabricated demand, patents, savings, or customers.\",\"role\":\"Application and adoption assessment\",\"scaffold\":{\"kind\":\"workspace\",\"mode\":\"hive\",\"slug\":\"applied-invention-lab-commercialization\",\"world_id\":\"demo-applied-invention-lab\"},\"template\":\"templates/teams/commercialization\"},{\"directory\":\"workspaces/casework\",\"id\":\"casework\",\"name\":\"Shared delivery case\",\"purpose\":\"Own synthetic intake, shared inputs, and accepted deliverables.\",\"role\":\"case-custodian\",\"scaffold\":{\"kind\":\"workspace\",\"mode\":\"hive\",\"slug\":\"applied-invention-lab-casework\",\"world_id\":\"demo-applied-invention-lab\"},\"template\":\"templates/casework\"}]}\n","path":"initialize.json","sha256":"622bc790a95770e6ebd3b093fde94c22abbbd0c21b4f4f6f48a3607da16417c3"},{"bytes":5733,"content":"{\"authority\":\"inert-starter-data\",\"classification\":\"public-synthetic\",\"dependencies\":{\"activation\":\"Separate owner-approved native plans are required; the seed grants no authority.\",\"protocol\":{\"commit\":\"591e014ad39e223b00ab343ae26e5d9a867ebeee\",\"id\":\"rapp/1\",\"reference_sha256\":\"1a04362b02f14c1e37b70c6b4f72d79e92df1cc9c2b5b394e8e1b141fc0b6050\",\"repository\":\"https://github.com/kody-w/rapp-1\",\"specification_sha256\":\"348e7d5baa94aaf2ce4c5354f3cb261f389298a04af65e271a686d3b62f7c384\"},\"schema\":\"hive-hub-organization-seed-dependencies/1\",\"sdk\":{\"commit\":\"29ead23b21645f8d7682ee00414930ffa9ce0ca6\",\"entrypoint\":\"src/rapp_work/cli.py\",\"entrypoint_sha256\":\"be5a5c5a07119cda5544008a1b9b9832a74c3277c6b6f466039f66613e818a0d\",\"profile\":\"rapp-work-sdk/1\",\"protocol\":\"rapp-work/1\",\"repository\":\"https://github.com/kody-w/rapp-work\"}},\"initialize\":\"initialize.json\",\"inventory\":[{\"bytes\":1079,\"path\":\"LICENSE\",\"sha256\":\"3ca4ef7120c79e55fa3c113f2c6366a072b685018d2bf736ff2bcfceba57a77f\"},{\"bytes\":3439,\"path\":\"README.md\",\"sha256\":\"6c694e4d71a7202c3dcafd3a5046c26757b684ec4a7121f22294ea34d55dce4f\"},{\"bytes\":3829,\"path\":\"initialize.json\",\"sha256\":\"622bc790a95770e6ebd3b093fde94c22abbbd0c21b4f4f6f48a3607da16417c3\"},{\"bytes\":680,\"path\":\"templates/casework/work/ACCEPTANCE.md\",\"sha256\":\"f3453b8deb86e9ffb84d7f44e0c0888e2aa958cdaa4cdbbf8364f1ebdbfc2173\"},{\"bytes\":1556,\"path\":\"templates/casework/work/intake.json\",\"sha256\":\"99b0712dad2240a5b126fc08871b18bfcc13b1c0a9c9f844af77e8f7c04e852f\"},{\"bytes\":1767,\"path\":\"templates/casework/work/starter/README.md\",\"sha256\":\"a822680c288c15d344c06b00c7cb3d31b57c947ce6694f0ea3044ecc9c15a174\"},{\"bytes\":309,\"path\":\"templates/casework/work/starter/data/capacity.json\",\"sha256\":\"7545ddbec5d31256cab78aedcecd12777fc916de2cbded4607ccdcefcf6a6ad9\"},{\"bytes\":460,\"path\":\"templates/casework/work/starter/data/experiment-plan.json\",\"sha256\":\"e6091595c336e502e329ec8b8cd2a9ca216cc9b8c7b782017eeca51f7874d340\"},{\"bytes\":959,\"path\":\"templates/casework/work/starter/data/items.csv\",\"sha256\":\"07d5892a89521c9311ac5873fa423b683793893bab3631253ffc972e94623f13\"},{\"bytes\":1521,\"path\":\"templates/casework/work/starter/docs/commercialization-boundary.md\",\"sha256\":\"7978f2064c4daa02e88d630ed8d472f0487090694b78a96533dacdc8119792c9\"},{\"bytes\":1630,\"path\":\"templates/casework/work/starter/docs/data-dictionary.md\",\"sha256\":\"8174a135848128782437305cc8f6526ed41ee860b2a83ab929a2012ef61475e5\"},{\"bytes\":2316,\"path\":\"templates/casework/work/starter/docs/experiment-design.md\",\"sha256\":\"2596cfa3f79d4d4957db86481332cb4e0ed4d4acc632e32c3cc213ff5e42e6bb\"},{\"bytes\":1318,\"path\":\"templates/casework/work/starter/docs/operator-worksheet.csv\",\"sha256\":\"1ea3f8499eb8498736e623822104bbf48a3cddb575a34268a23d83c0ecc3ef93\"},{\"bytes\":1839,\"path\":\"templates/casework/work/starter/docs/problem-brief.md\",\"sha256\":\"6110286bf44b4e8fb17b7d97e9769cd471cb470bc68a5b1eec0472ae009f16c8\"},{\"bytes\":1258,\"path\":\"templates/casework/work/starter/docs/prototype-brief.md\",\"sha256\":\"f6b437b2e1c028ce9774eb684cdd51d1f5d51f6f834d59299a0784277bac72eb\"},{\"bytes\":1663,\"path\":\"templates/casework/work/starter/docs/replication-protocol.md\",\"sha256\":\"ac91b64a6f7ba6ff45c78d8c651e6c2c582a1a8100a82b5380ef6d9e65437965\"},{\"bytes\":713,\"path\":\"templates/casework/work/starter/reference/expected-baseline.json\",\"sha256\":\"da83816eddb917c66258c6800b2a7f73255dd149f0b7dc3c2d6f42ccf51272a5\"},{\"bytes\":3155,\"path\":\"templates/casework/work/starter/reference/run_experiment.py\",\"sha256\":\"f21b0d734ca35c073d6d707fe1c7bba5aa2e980311473440722a1ea00d605b52\"},{\"bytes\":6448,\"path\":\"templates/casework/work/starter/reference/test_tote_pack.py\",\"sha256\":\"0049f959a2806a6f46b9ab53f8756a277dfccd8ebdce10ebafb1932ff58a360b\"},{\"bytes\":10016,\"path\":\"templates/casework/work/starter/reference/tote_pack.py\",\"sha256\":\"d592ad5a695e06e278552af552d74f8c5b7d74d8dd2d6caa9f5603dae9ee2e61\"},{\"bytes\":9783,\"path\":\"templates/casework/work/task-board.json\",\"sha256\":\"f36c95b9f2dce75ca99c5a940e174004883bea4b52b0598fd20ea357d2fbb19a\"},{\"bytes\":390,\"path\":\"templates/teams/commercialization/work/TEAM.md\",\"sha256\":\"683aa378c4b577ef5c596c34c30dd53b27dcc4264681860c143851cf90a7a440\"},{\"bytes\":1098,\"path\":\"templates/teams/commercialization/work/tasks.json\",\"sha256\":\"dab6d799a080d0b38b0a5279ce75b8780a6bb2b82bf59b6071ef09859411f6c9\"},{\"bytes\":358,\"path\":\"templates/teams/experiments/work/TEAM.md\",\"sha256\":\"a055e5d907f55766f5978ee1fbba9e180b922d85b9bfa24b574b08a8546e7a0b\"},{\"bytes\":1947,\"path\":\"templates/teams/experiments/work/tasks.json\",\"sha256\":\"7a3463354263b8494c99dea5cad0da6e6cfbf28aeef084168cdf378ace6007f3\"},{\"bytes\":383,\"path\":\"templates/teams/prototyping/work/TEAM.md\",\"sha256\":\"24fd7916d5c164d6f0dce79ae0ae6e6bd00e2fa79a01b5648a0306a64dad62b2\"},{\"bytes\":2006,\"path\":\"templates/teams/prototyping/work/tasks.json\",\"sha256\":\"52a65b3fe6ab04fc161baf36304e055bfb7f43d10c9c45b9b4bb11ca591d69c1\"},{\"bytes\":358,\"path\":\"templates/teams/replication/work/TEAM.md\",\"sha256\":\"414478f8ad33f90b93e45ccf3b71b2dc939fee658fadfdd23d3f6c492e78ee5f\"},{\"bytes\":2085,\"path\":\"templates/teams/replication/work/tasks.json\",\"sha256\":\"8b243011adc227ffcf63800add698d690976525d773e19e1b8c946c0d0da2cfd\"},{\"bytes\":382,\"path\":\"templates/teams/research/work/TEAM.md\",\"sha256\":\"5fd67e0cfbd3fba8fcff5d6a943250c5d5ff1e0b4ae9abe6b84eca4d24452a89\"},{\"bytes\":2978,\"path\":\"templates/teams/research/work/tasks.json\",\"sha256\":\"d13dfff6b8e47f065b1a1839654888e7ff9f33951a9b4fc0b48cedf1e80d0996\"}],\"license\":\"MIT\",\"name\":\"The Applied Invention Lab\",\"protocol\":\"rapp-work/1\",\"related_seeds\":[\"one-person-conglomerate\",\"enterprise-transformation-firm\"],\"schema\":\"hive-hub-organization-seed-manifest/1\",\"slug\":\"applied-invention-lab\",\"status\":\"seed-not-activated\",\"workspace_profile\":\"rapp-work-sdk/1\",\"world_id\":\"demo-applied-invention-lab\"}\n","path":"seed.json","sha256":"e44fc659c8b5d5d00c45ff7a87e10b7f31aa2470d44a435b4081ac314b50c0bb"},{"bytes":680,"content":"# Case acceptance\n\n- Every item instance appears exactly once and every modeled tote respects both integer capacity constraints.\n- The authored baseline reproduces all four expected scenario counts, including a case where the dominant heuristic is worse than input order.\n- Seeded permutation experiments preserve all trials and can be rerun with matching source hashes and results.\n- Lower-bound proofs, bounded search, unproven results, and skipped search are clearly distinguished.\n- Physical fit, operator usefulness, cost, novelty, and customer demand remain unmeasured until separately approved studies occur.\n\nNo reference artifact counts as completed work without review.\n","path":"templates/casework/work/ACCEPTANCE.md","sha256":"f3453b8deb86e9ffb84d7f44e0c0888e2aa958cdaa4cdbbf8364f1ebdbfc2173"},{"bytes":1556,"content":"{\"brief\":\"A fictional library kit service wants a more explainable way to group harmless paper, cloth, foam, and counting materials into reusable totes. All items, capacities, shapes, and operating assumptions are SYNTHETIC. Eleven item-type rows expand into 29 instances across four scenarios. The offline reference compares input-order, dominant-load, and volume-first greedy packing, verifies every assignment, and optionally proves small scalar-model optima. It does not certify three-dimensional fit, lifting safety, physical performance, or commercial demand.\",\"classification\":\"public-synthetic\",\"id\":\"library-kit-tote-study\",\"inputs\":[\"starter/docs/problem-brief.md\",\"starter/docs/data-dictionary.md\",\"starter/data/items.csv\",\"starter/data/capacity.json\",\"starter/data/experiment-plan.json\",\"starter/reference/expected-baseline.json\"],\"success_criteria\":[\"Every item instance appears exactly once and every modeled tote respects both integer capacity constraints.\",\"The authored baseline reproduces all four expected scenario counts, including a case where the dominant heuristic is worse than input order.\",\"Seeded permutation experiments preserve all trials and can be rerun with matching source hashes and results.\",\"Lower-bound proofs, bounded search, unproven results, and skipped search are clearly distinguished.\",\"Physical fit, operator usefulness, cost, novelty, and customer demand remain unmeasured until separately approved studies occur.\"],\"title\":\"Library Kit Tote Study: does a two-capacity heuristic actually reduce modeled bins?\"}\n","path":"templates/casework/work/intake.json","sha256":"99b0712dad2240a5b126fc08871b18bfcc13b1c0a9c9f844af77e8f7c04e852f"},{"bytes":1767,"content":"# The Applied Invention Lab — Library Kit Tote Study\n\n**SYNTHETIC practical problem and original dataset.** A fictional library-kit\nservice groups harmless paper, cloth, foam, and counting materials into\nreusable totes. The working reference uses two integer capacity proxies:\nvolume units and weight units. They are not measured liters, kilograms,\nphysical dimensions, or safe handling limits.\n\n## Run the offline computation\n\nFrom `files/`, with Python 3.10 or newer:\n\n```sh\npython3 -I -B reference/test_tote_pack.py\npython3 -I -B reference/tote_pack.py data --exact-small\npython3 -I -B reference/run_experiment.py data\n```\n\nAll code is original and standard-library-only. It reads the explicitly named\npublic source files, prints JSON, and performs no installation, network,\nserver, subprocess, persistence, identity, or external operation.\n\nEleven rows expand into 29 item instances across four scenarios. Three greedy\nmethods are compared. The dominant-load heuristic is **not always better**:\non `mixed-classroom`, it uses 7 bins versus input-order's 6 and volume-first's\n8. The optional proof routine uses a lower bound when sufficient, or bounded\nsearch for at most 12 items; it never calls an external solver.\n\nThe experiment runner uses a declared seed and 20 paired permutations per\nscenario. It includes every trial, source hashes, and model limitations.\nRepeatable synthetic computation is not real-world validation.\n\nThe five workspaces own framing, experiments, prototype instructions,\nreplication, and a cautious application hypothesis. A future physical-fit\nstudy is a pending task; no mock tote has been packed by these files.\nCommercial demand, novelty, patents, customer savings, physical fit, and\nlifting safety are not established or claimed.\n","path":"templates/casework/work/starter/README.md","sha256":"a822680c288c15d344c06b00c7cb3d31b57c947ce6694f0ea3044ecc9c15a174"},{"bytes":309,"content":"{\n  \"classification\": \"SYNTHETIC\",\n  \"volume_units\": 10,\n  \"weight_units\": 10,\n  \"max_items_per_scenario\": 60,\n  \"exact_item_limit\": 12,\n  \"exact_node_limit\": 50000,\n  \"interpretation\": \"Abstract positive integer capacities only; not physical dimensions, mass, container strength, or safe handling limits.\"\n}\n","path":"templates/casework/work/starter/data/capacity.json","sha256":"7545ddbec5d31256cab78aedcecd12777fc916de2cbded4607ccdcefcf6a6ad9"},{"bytes":460,"content":"{\n  \"classification\": \"SYNTHETIC\",\n  \"plan_id\": \"paired-permutation-study\",\n  \"random_seed\": 1729,\n  \"repetitions\": 20,\n  \"algorithms\": [\"input-first-fit\", \"dominant-first-fit\", \"volume-first-fit\"],\n  \"pairing\": \"One shuffled item order per scenario and trial is shared across all algorithms.\",\n  \"exclusions\": \"None; an invalid input stops the run.\",\n  \"reporting\": \"Retain every trial and descriptive min/max/mean. Do not generalize to a real population.\"\n}\n","path":"templates/casework/work/starter/data/experiment-plan.json","sha256":"e6091595c336e502e329ec8b8cd2a9ca216cc9b8c7b782017eeca51f7874d340"},{"bytes":959,"content":"classification,scenario,sku,count,volume-units,weight-units,shape-note\nSYNTHETIC,order-trap,filler-card-pack,2,4,2,Rectangular paper proxy with unknown actual dimensions\nSYNTHETIC,order-trap,core-board-pack,2,6,3,Flat board proxy with unknown orientation constraints\nSYNTHETIC,weight-trap,light-foam-panel,3,7,1,Bulky light proxy with no measured compression\nSYNTHETIC,weight-trap,dense-counter-pouch,3,2,7,Small dense proxy with unknown pouch geometry\nSYNTHETIC,weight-trap,medium-card-board,2,3,3,Medium flat proxy with unknown nesting\nSYNTHETIC,mixed-classroom,paper-stack,4,3,2,Flat paper proxy\nSYNTHETIC,mixed-classroom,foam-shapes,3,6,1,Irregular foam proxy\nSYNTHETIC,mixed-classroom,tile-pouch,3,2,6,Compact counting-piece proxy\nSYNTHETIC,mixed-classroom,cloth-pack,2,4,2,Folded cloth proxy with no compression model\nSYNTHETIC,mixed-classroom,counter-board,2,5,3,Flat board proxy\nSYNTHETIC,bulky-gaps,wide-foam-block,3,6,1,Indivisible six-volume proxy\n","path":"templates/casework/work/starter/data/items.csv","sha256":"07d5892a89521c9311ac5873fa423b683793893bab3631253ffc972e94623f13"},{"bytes":1521,"content":"# Application assessment boundary\n\n**SYNTHETIC opportunity hypotheses. No customer, revenue, patent, or market\nvalidation is present.**\n\nPossible application: an explainable local worksheet for a person grouping\nsmall reusable kits. A printable assignment and visible constraints may be\nmore appropriate than a service with accounts, integrations, and data\nretention. This is a hypothesis to test, not a business recommendation backed\nby customer evidence.\n\nBefore external positioning:\n\n- Verify harmless mock geometry and label readability.\n- Observe whether an authorized participant can follow and correct the\n  instructions with synthetic data.\n- Learn whether the planning problem occurs often enough to justify a tool.\n- Compare with manual grouping and an ordinary spreadsheet; do not assume\n  software is the better answer.\n- Establish actual data, support, consent, licensing, and procurement needs.\n\nCandidate disconfirming signals: geometric constraints dominate the scalar\nmodel; operators cannot interpret the assignment; manual grouping is simpler;\ninput data cannot be obtained reliably; or no meaningful repeated problem\nexists. A negative outcome is useful lab evidence.\n\nNo novel algorithm, patentability, freedom to operate, savings percentage,\ncustomer willingness to pay, or universal reduction in bins is claimed.\nIntellectual-property assessment, interviews, publication, purchases, and\nany commercial engagement require separate real owner approval. This seed\ndoes not initiate those activities.\n","path":"templates/casework/work/starter/docs/commercialization-boundary.md","sha256":"7978f2064c4daa02e88d630ed8d472f0487090694b78a96533dacdc8119792c9"},{"bytes":1630,"content":"# Original dataset and units\n\n**SYNTHETIC — not measured physical data.**\n\n`items.csv` has 11 item-type rows, expanding to 29 instances:\n`order-trap` 4, `weight-trap` 8, `mixed-classroom` 14, `bulky-gaps` 3.\n\n| Field | Meaning |\n|---|---|\n| classification | Literal SYNTHETIC in this public reference |\n| scenario | Independent case; items never cross scenario boundaries |\n| sku | Original local item-type label, not a commercial catalog ID |\n| count | Positive whole number of instances; at most 20 per row |\n| volume-units | Positive integer capacity proxy per instance |\n| weight-units | Positive integer second capacity proxy per instance |\n| shape-note | Qualitative assumption deliberately not consumed by the scalar solver |\n\nEach instance ID is `sku-01`, `sku-02`, etc.; IDs are local data labels, not\nRAPPIDs or any identity credential. SKU uniqueness is enforced within a\nscenario. Original source order is meaningful for the input-order baseline.\n\nEvery modeled tote has volume capacity 10 and weight capacity 10. No\nconversion to liters, mass, allowable lifting weight, or structural capacity\nis justified. Items are indivisible in the model, and there are no\ncompatibility, accessibility, center-of-gravity, geometry, or kit-cohesion\nconstraints. A shape note exists precisely to expose that missing dimension.\n\nThe reader bounds CSV size at 1 MiB, row count at 1,000, and expanded scenario\nsize at 60. Values must be positive integers; an oversized item fails instead\nof being silently forced into a tote. Blank or duplicate keys fail. All\ncomputational labels and quantities are original synthetic seed content.\n","path":"templates/casework/work/starter/docs/data-dictionary.md","sha256":"8174a135848128782437305cc8f6526ed41ee860b2a83ab929a2012ef61475e5"},{"bytes":2316,"content":"# Predeclared computational experiment\n\n**SYNTHETIC model study. No physical experiment or user study has occurred.**\n\n## Question and comparison\n\nDoes dominant-load decreasing first-fit reduce modeled bin count relative\nto input-order first-fit, and where does it regress? Compare all three:\n\n1. `input-first-fit`: place each item in the first feasible bin in supplied\n   order, otherwise open a new bin.\n2. `dominant-first-fit`: sort by descending maximum normalized load, then\n   descending sum of normalized loads, then ascending local item ID.\n3. `volume-first-fit`: sort by descending volume, then weight, then item ID.\n\nEach insertion must satisfy both capacity constraints. The deterministic\nsorted methods are not novel algorithms and no invention claim is made.\n\n## Fixed experiment plan\n\nUse seed 1729 and 20 permutations per scenario. Within a trial, feed the same\npermutation to all three methods. Retain all 240 resulting bin counts\n(4 scenarios × 3 methods × 20 trials). Store min, max, and arithmetic mean as\ndescriptive summaries, not confidence about a real population. Keep the\nunshuffled baseline separate from the randomized order experiment.\n\nNo trial exclusion is permitted except an invalid input, which stops the\nrun and must be reported. Do not change capacities, scenario membership, or\nthe seed after seeing an unfavorable result. Proposed future variations\nneed a separately versioned plan and side-by-side reporting.\n\n## Bounds and proof\n\nThe scalar lower bound is the maximum of the ceiling of total volume divided\nby volume capacity and the corresponding weight ratio. Matching a feasible\npacking count proves optimal bin count *within this model*. Otherwise an\noptional depth-first branch-and-bound search explores at most 12 items and\n50,000 nodes. It reports proven, skipped, or node-limit-unproven honestly.\nAn optimum of this abstraction proves nothing about three-dimensional fit.\n\n## Decision rule\n\nContinue only if the assignment prototype is explainable and at least one\nuseful computation survives replication. Do not claim universal superiority:\nthe mixed-classroom baseline is a known counterexample. Before discussing a\npractical benefit, run a separately approved mock-fit and comprehension\nstudy. Commercial interviews and spending require their own owner approvals.\n","path":"templates/casework/work/starter/docs/experiment-design.md","sha256":"2596cfa3f79d4d4957db86481332cb4e0ed4d4acc632e32c3cc213ff5e42e6bb"},{"bytes":1318,"content":"classification,check-id,scenario,assumption,planned-observation,decision-if-not-met,observation-state\nSYNTHETIC,geometry-pair,order-trap,Paired proxies can correspond to a useful mock arrangement,Try two empty paper outlines inside one mock tote outline,Reject scalar fit as sufficient and add geometric constraints,not-performed\nSYNTHETIC,label-match,order-trap,An operator can match IDs to sample items,Ask a consented participant to match four invented labels,Revise labels before any field pilot,not-performed\nSYNTHETIC,dual-load,weight-trap,Both displayed constraints are understandable,Ask which of two hypothetical insertions violates weight proxy,Revise the instruction legend,not-performed\nSYNTHETIC,regression-visible,mixed-classroom,An unfavorable method result remains visible,Inspect a prototype comparing counts 6 7 and 8,Block claims of universal heuristic superiority,not-performed\nSYNTHETIC,gap-explanation,bulky-gaps,A lower bound is not mistaken for an attainable count,Ask why three indivisible six-volume items need three bins,Improve the bound explanation,not-performed\nSYNTHETIC,no-safety-inference,all-scenarios,Abstract units are not treated as physical safe limits,Check that every instruction page carries the model-only warning,Stop any proposed real transport or lifting use,not-performed\n","path":"templates/casework/work/starter/docs/operator-worksheet.csv","sha256":"1ea3f8499eb8498736e623822104bbf48a3cddb575a34268a23d83c0ecc3ef93"},{"bytes":1839,"content":"# Practical problem brief\n\n**All service descriptions, items, and numbers are SYNTHETIC.**\n\nA fictional library assembles reusable learning kits: blank cards, cloth\nsquares, soft foam shapes, counters, and lightweight boards. Staff want\npacking instructions that are easier to inspect than an opaque bin count.\nThe initial question is narrow: under two *modeled* capacities, how many\ntotes do three simple heuristics use, and how sensitive are they to order?\n\nWe do not know actual item dimensions, nesting, compression, fragility,\naccess order, handling limits, setup time, or user preferences. Those gaps\nmatter: two items that fit aggregate volume can still be impossible to place\ngeometrically. A better scalar count might produce worse instructions.\n\n## Four deliberately informative scenarios\n\n- **order-trap:** two small fillers precede two larger cores. Input-order\n  first-fit uses three bins; decreasing-load methods can pair them in two.\n- **weight-trap:** light bulky items and dense small pouches illustrate why\n  both constraints must be checked. Volume-first fills two light-panel bins\n  with medium boards too early, leaving dense pouches in separate bins: five\n  bins versus four for the other supplied baseline orders.\n- **mixed-classroom:** five types show that a plausible dominant-load\n  heuristic can be worse than the provided order. This unfavorable case is\n  deliberately retained.\n- **bulky-gaps:** three indivisible six-volume items need three bins even\n  though the aggregate lower bound is two. A lower bound is not always the\n  answer.\n\nThe immediate deliverable is reproducible model evidence and a printable\ninstruction prototype. Any later study should begin with harmless empty or\nlightweight mock materials and owner-approved observation, not actual\nshipping, load testing, or safety-critical operation.\n","path":"templates/casework/work/starter/docs/problem-brief.md","sha256":"6110286bf44b4e8fb17b7d97e9769cd471cb470bc68a5b1eec0472ae009f16c8"},{"bytes":1258,"content":"# Operator-readable assignment prototype\n\n**SYNTHETIC model-only reference. No physical packing has been performed.**\n\nUse `order-trap` first because the difference between three input-order bins\nand two decreasing-load bins is inspectable. A proposed printable layout has:\n\n- Scenario label, algorithm, dataset provenance, and a model-only warning.\n- One numbered section per tote.\n- Exact local item IDs, item labels, volume and weight proxy totals.\n- Remaining capacity in both dimensions, shown as numbers and text.\n- An explicit “check mock geometry before use” instruction and a way to\n  record an operator's correction without overwriting the model result.\n\nFor the two-bin decreasing-load reference, each bin should pair one\nsix-volume/three-weight core with one four-volume/two-weight filler. That is\nvolume 10 and weight 5 per bin. It proves scalar feasibility, not shape fit.\n\nThe later mock study should use empty or lightweight paper/foam\nrepresentations. Review whether labels are understandable, each item can be\nfound, and modeled pairings make geometric sense. Do not infer safe lifting,\ncontainer strength, shipment suitability, or actual load limits from these\nabstract units. No physical observation values are supplied in this seed.\n","path":"templates/casework/work/starter/docs/prototype-brief.md","sha256":"f6b437b2e1c028ce9774eb684cdd51d1f5d51f6f834d59299a0784277bac72eb"},{"bytes":1663,"content":"# Replication protocol\n\n**SYNTHETIC computation; protocol is not a completed replication report.**\n\n1. Use the explicitly listed dataset, capacity file, experiment plan, and\n   original reference programs. Do not substitute a real library inventory.\n2. Record Python version and actual commands. Use a fresh interpreter, no\n   installed solver, network, server, or environment-dependent data.\n3. Run the authored tests and baseline with `--exact-small`.\n4. Check all expected per-scenario algorithm counts. Independently verify\n   each item appears once and both capacities hold.\n5. Run the experiment twice. Compare the complete JSON results, including\n   source hashes and all per-trial arrays. File hashes are public-data\n   reproducibility identifiers, not signatures or runtime authority.\n6. Compare against the first experiment report. Any mismatch in source bytes\n   means a different input, not successful replication of the same run.\n7. Report any numerical disagreement, node-limit condition, changed runtime,\n   and unperformed check explicitly.\n\nPass requires exact baseline counts, matching trial arrays and input hashes\nfor the same interpreter behavior, and all packing invariants. Different\nPython random implementations or future version changes may alter seeded\npermutations; record the runtime rather than promising indefinite bitwise\nidentity across every environment. The sorted methods should still be\npermutation-invariant because item IDs break ties.\n\nReplication establishes computation on these original synthetic inputs.\nPhysical fit, operator comprehension, safe handling, business costs, and\ndemand are separate not-observed domains.\n","path":"templates/casework/work/starter/docs/replication-protocol.md","sha256":"ac91b64a6f7ba6ff45c78d8c651e6c2c582a1a8100a82b5380ef6d9e65437965"},{"bytes":713,"content":"{\n  \"classification\": \"SYNTHETIC\",\n  \"artifact_kind\": \"expected-reference-counts-not-physical-results\",\n  \"scenarios\": {\n    \"order-trap\": {\"item_count\": 4, \"lower_bound\": 2, \"input-first-fit\": 3, \"dominant-first-fit\": 2, \"volume-first-fit\": 2, \"model_optimum\": 2},\n    \"weight-trap\": {\"item_count\": 8, \"lower_bound\": 4, \"input-first-fit\": 4, \"dominant-first-fit\": 4, \"volume-first-fit\": 5, \"model_optimum\": 4},\n    \"mixed-classroom\": {\"item_count\": 14, \"lower_bound\": 6, \"input-first-fit\": 6, \"dominant-first-fit\": 7, \"volume-first-fit\": 8, \"model_optimum\": 6},\n    \"bulky-gaps\": {\"item_count\": 3, \"lower_bound\": 2, \"input-first-fit\": 3, \"dominant-first-fit\": 3, \"volume-first-fit\": 3, \"model_optimum\": 3}\n  }\n}\n","path":"templates/casework/work/starter/reference/expected-baseline.json","sha256":"da83816eddb917c66258c6800b2a7f73255dd149f0b7dc3c2d6f42ccf51272a5"},{"bytes":3155,"content":"\"\"\"Original seeded paired-permutation study of a synthetic scalar packing model.\"\"\"\n\nimport argparse\nimport hashlib\nimport importlib.util\nimport json\nimport random\nfrom decimal import Decimal\nfrom pathlib import Path\n\nHERE = Path(__file__).resolve().parent\nSPEC = importlib.util.spec_from_file_location(\"tote_pack_experiment\", HERE / \"tote_pack.py\")\npacking = importlib.util.module_from_spec(SPEC)\nSPEC.loader.exec_module(packing)\n\n\ndef run(data_dir):\n    data_dir = Path(data_dir)\n    scenarios, capacity = packing.load_problem(data_dir)\n    plan_path = data_dir / \"experiment-plan.json\"\n    if plan_path.stat().st_size > 20000:\n        raise ValueError(\"plan exceeds reference limit\")\n    plan = json.loads(plan_path.read_text(encoding=\"utf-8\"))\n    if plan[\"classification\"] != \"SYNTHETIC\" or plan[\"algorithms\"] != list(packing.ALGORITHMS):\n        raise ValueError(\"use the declared synthetic three-algorithm plan\")\n    repetitions = packing.whole(plan[\"repetitions\"], 1, 100, \"repetitions\")\n    seed = packing.whole(plan[\"random_seed\"], 0, 2**32 - 1, \"seed\")\n    rng = random.Random(seed)\n    results = []\n    for scenario, items in sorted(scenarios.items()):\n        counts = {algorithm: [] for algorithm in packing.ALGORITHMS}\n        for _ in range(repetitions):\n            permutation = list(items)\n            rng.shuffle(permutation)\n            for algorithm in packing.ALGORITHMS:\n                bins = packing.pack(permutation, capacity, algorithm)\n                packing.verify(items, bins, capacity)\n                counts[algorithm].append(len(bins))\n        results.append({\n            \"scenario\": scenario,\n            \"item_count\": len(items),\n            \"algorithms\": {\n                algorithm: {\n                    \"counts\": values, \"min\": min(values), \"max\": max(values),\n                    \"mean\": f\"{Decimal(sum(values)) / len(values):.3f}\",\n                } for algorithm, values in counts.items()\n            },\n        })\n    hashes = {\n        filename: hashlib.sha256((data_dir / filename).read_bytes()).hexdigest()\n        for filename in (\"items.csv\", \"capacity.json\", \"experiment-plan.json\")\n    }\n    return {\n        \"classification\": \"SYNTHETIC\",\n        \"artifact_kind\": \"computational-experiment-not-physical-or-market-evidence\",\n        \"seed\": seed, \"repetitions\": repetitions, \"source_sha256\": hashes,\n        \"pairing\": \"The same permutation is used across algorithms within each trial.\",\n        \"scenarios\": results,\n        \"limitations\": [\n            \"Abstract capacities do not establish geometric fit or safe handling.\",\n            \"Four authored scenarios are not a sampled real-world population.\",\n            \"Seeded permutation sequences should be compared with runtime version recorded.\",\n        ],\n    }\n\n\ndef main():\n    parser = argparse.ArgumentParser(description=__doc__)\n    parser.add_argument(\"data_dir\", type=Path)\n    args = parser.parse_args()\n    try:\n        result = run(args.data_dir)\n    except (OSError, ValueError, KeyError, TypeError) as exc:\n        parser.error(str(exc))\n    print(json.dumps(result, indent=2, sort_keys=True))\n\n\nif __name__ == \"__main__\":\n    main()\n","path":"templates/casework/work/starter/reference/run_experiment.py","sha256":"f21b0d734ca35c073d6d707fe1c7bba5aa2e980311473440722a1ea00d605b52"},{"bytes":6448,"content":"import copy\nimport importlib.util\nimport itertools\nimport json\nimport random\nimport unittest\nfrom pathlib import Path\n\nHERE = Path(__file__).resolve().parent\nDATA = HERE.parent / \"data\"\n\n\ndef load_module(name, filename):\n    spec = importlib.util.spec_from_file_location(name, HERE / filename)\n    module = importlib.util.module_from_spec(spec)\n    spec.loader.exec_module(module)\n    return module\n\n\npacking = load_module(\"packing_tests\", \"tote_pack.py\")\nexperiment = load_module(\"experiment_tests\", \"run_experiment.py\")\n\n\nclass PackingTests(unittest.TestCase):\n    def setUp(self):\n        self.scenarios, self.capacity = packing.load_problem(DATA)\n\n    def test_original_dataset_counts(self):\n        self.assertEqual({key: len(value) for key, value in self.scenarios.items()}, {\"order-trap\": 4, \"weight-trap\": 8, \"mixed-classroom\": 14, \"bulky-gaps\": 3})\n        self.assertEqual(sum(map(len, self.scenarios.values())), 29)\n\n    def test_all_baseline_counts_and_model_proofs(self):\n        expected = json.loads((HERE / \"expected-baseline.json\").read_text(encoding=\"utf-8\"))[\"scenarios\"]\n        actual = packing.analyze(DATA, exact=True)\n        for row in actual[\"scenarios\"]:\n            with self.subTest(scenario=row[\"scenario\"]):\n                target = expected[row[\"scenario\"]]\n                self.assertEqual(row[\"item_count\"], target[\"item_count\"])\n                self.assertEqual(row[\"lower_bound\"], target[\"lower_bound\"])\n                for method in packing.ALGORITHMS:\n                    self.assertEqual(row[\"algorithms\"][method][\"bin_count\"], target[method])\n                self.assertTrue(row[\"model_proof\"][\"proven\"])\n                self.assertEqual(row[\"model_proof\"][\"best_count\"], target[\"model_optimum\"])\n\n    def test_every_assignment_is_feasible(self):\n        for items in self.scenarios.values():\n            for algorithm in packing.ALGORITHMS:\n                self.assertTrue(packing.verify(items, packing.pack(items, self.capacity, algorithm), self.capacity))\n\n    def test_pure_and_deterministic(self):\n        items = self.scenarios[\"mixed-classroom\"]\n        before = copy.deepcopy(items)\n        first = packing.pack(items, self.capacity)\n        self.assertEqual(first, packing.pack(items, self.capacity))\n        self.assertEqual(items, before)\n\n    def test_sorted_methods_are_permutation_invariant(self):\n        for items in self.scenarios.values():\n            for algorithm in (\"dominant-first-fit\", \"volume-first-fit\"):\n                self.assertEqual(packing.pack(items, self.capacity, algorithm), packing.pack(list(reversed(items)), self.capacity, algorithm))\n\n    def test_duplicate_and_oversized_inputs(self):\n        items = self.scenarios[\"order-trap\"]\n        with self.assertRaises(ValueError):\n            packing.pack(items + [items[0]], self.capacity)\n        with self.assertRaises(ValueError):\n            packing.pack([dict(items[0], volume=11)], self.capacity)\n        with self.assertRaises(ValueError):\n            packing.pack([dict(items[0], weight=0)], self.capacity)\n        with self.assertRaises(ValueError):\n            packing.pack([dict(items[0], weight=True)], self.capacity)\n\n    def test_verifier_detects_missing_and_incorrect_load(self):\n        items = self.scenarios[\"order-trap\"]\n        bins = packing.pack(items, self.capacity)\n        with self.assertRaises(ValueError):\n            packing.verify(items, bins[:-1], self.capacity)\n        bins[0][\"weight_used\"] += 1\n        with self.assertRaises(ValueError):\n            packing.verify(items, bins, self.capacity)\n\n    def test_empty_model(self):\n        self.assertEqual(packing.pack([], self.capacity), [])\n        self.assertEqual(packing.lower_bound([], self.capacity), 0)\n        self.assertEqual(packing.exact_minimum([], self.capacity)[\"best_count\"], 0)\n\n    def test_search_proves_indivisibility_gap(self):\n        result = packing.exact_minimum(self.scenarios[\"bulky-gaps\"], self.capacity)\n        self.assertEqual((result[\"best_count\"], result[\"lower_bound\"], result[\"method\"]), (3, 2, \"bounded-search\"))\n        self.assertGreater(result[\"nodes\"], 0)\n\n    def test_node_limit_is_not_a_proof(self):\n        result = packing.exact_minimum(self.scenarios[\"bulky-gaps\"], self.capacity, node_limit=1)\n        self.assertFalse(result[\"proven\"])\n        self.assertEqual(result[\"method\"], \"node-limit-unproven\")\n\n    def test_large_unclosed_bound_skips_search(self):\n        items = [{\"id\": f\"bulky-{index}\", \"volume\": 6, \"weight\": 1} for index in range(13)]\n        result = packing.exact_minimum(items, self.capacity)\n        self.assertFalse(result[\"proven\"])\n        self.assertEqual(result[\"method\"], \"skipped-item-limit\")\n\n    def test_exact_search_matches_small_exhaustive_assignments(self):\n        rng = random.Random(74)\n        for case in range(8):\n            items = [{\"id\": f\"sample-{index}\", \"volume\": rng.randint(1, 9), \"weight\": rng.randint(1, 9)} for index in range(5)]\n            optimum = len(items)\n            for assignment in itertools.product(range(len(items)), repeat=len(items)):\n                used = set(assignment)\n                if len(used) >= optimum:\n                    continue\n                if all(\n                    sum(item[\"volume\"] for item, target in zip(items, assignment) if target == bin_id) <= 10\n                    and sum(item[\"weight\"] for item, target in zip(items, assignment) if target == bin_id) <= 10\n                    for bin_id in used\n                ):\n                    optimum = len(used)\n            result = packing.exact_minimum(items, self.capacity)\n            with self.subTest(case=case):\n                self.assertTrue(result[\"proven\"])\n                self.assertEqual(result[\"best_count\"], optimum)\n\n    def test_seeded_experiment_replicates_all_trials(self):\n        first = experiment.run(DATA)\n        self.assertEqual(first, experiment.run(DATA))\n        self.assertEqual(first[\"repetitions\"], 20)\n        self.assertEqual(len(first[\"source_sha256\"]), 3)\n        trial_count = 0\n        for scenario in first[\"scenarios\"]:\n            for algorithm, result in scenario[\"algorithms\"].items():\n                self.assertEqual(len(result[\"counts\"]), 20)\n                trial_count += len(result[\"counts\"])\n                if algorithm != \"input-first-fit\":\n                    self.assertEqual(len(set(result[\"counts\"])), 1)\n        self.assertEqual(trial_count, 240)\n\n\nif __name__ == \"__main__\":\n    unittest.main()\n","path":"templates/casework/work/starter/reference/test_tote_pack.py","sha256":"0049f959a2806a6f46b9ab53f8756a277dfccd8ebdce10ebafb1932ff58a360b"},{"bytes":10016,"content":"\"\"\"Original offline two-capacity packing reference; not physical fit or safety.\"\"\"\n\nimport argparse\nimport copy\nimport csv\nimport json\nimport re\nfrom fractions import Fraction\nfrom pathlib import Path\n\nALGORITHMS = (\"input-first-fit\", \"dominant-first-fit\", \"volume-first-fit\")\n\n\ndef whole(value, low, high, label):\n    if isinstance(value, bool) or not re.fullmatch(r\"[0-9]+\", str(value)):\n        raise ValueError(f\"{label} must be a whole number\")\n    result = int(value)\n    if not low <= result <= high:\n        raise ValueError(f\"{label} outside {low}..{high}\")\n    return result\n\n\ndef identifier(value, label):\n    if not isinstance(value, str) or len(value) > 60 or not re.fullmatch(r\"[a-z0-9]+(?:-[a-z0-9]+)*\", value):\n        raise ValueError(f\"invalid {label}\")\n    return value\n\n\ndef capacities(capacity):\n    return (\n        whole(capacity[\"volume_units\"], 1, 10000, \"volume capacity\"),\n        whole(capacity[\"weight_units\"], 1, 10000, \"weight capacity\"),\n    )\n\n\ndef validate_items(items, capacity):\n    volume_limit, weight_limit = capacities(capacity)\n    if not isinstance(items, list) or len(items) > 60:\n        raise ValueError(\"at most 60 item instances per scenario\")\n    seen = set()\n    for item in items:\n        identity = identifier(item[\"id\"], \"item ID\")\n        if identity in seen:\n            raise ValueError(\"duplicate item ID\")\n        seen.add(identity)\n        if type(item[\"volume\"]) is not int or type(item[\"weight\"]) is not int:\n            raise ValueError(\"item loads must be integer values\")\n        if not 1 <= item[\"volume\"] <= volume_limit or not 1 <= item[\"weight\"] <= weight_limit:\n            raise ValueError(\"item individually exceeds capacity or is nonpositive\")\n\n\ndef ordered_items(items, capacity, algorithm):\n    if algorithm not in ALGORITHMS:\n        raise ValueError(\"unknown algorithm\")\n    if algorithm == \"input-first-fit\":\n        return list(items)\n    if algorithm == \"volume-first-fit\":\n        return sorted(items, key=lambda item: (-item[\"volume\"], -item[\"weight\"], item[\"id\"]))\n    volume_limit, weight_limit = capacities(capacity)\n    return sorted(items, key=lambda item: (\n        -max(Fraction(item[\"volume\"], volume_limit), Fraction(item[\"weight\"], weight_limit)),\n        -(Fraction(item[\"volume\"], volume_limit) + Fraction(item[\"weight\"], weight_limit)),\n        item[\"id\"],\n    ))\n\n\ndef pack(items, capacity, algorithm=\"dominant-first-fit\"):\n    validate_items(items, capacity)\n    volume_limit, weight_limit = capacities(capacity)\n    bins = []\n    for item in ordered_items(items, capacity, algorithm):\n        target = next((bin_ for bin_ in bins if bin_[\"volume_used\"] + item[\"volume\"] <= volume_limit and bin_[\"weight_used\"] + item[\"weight\"] <= weight_limit), None)\n        if target is None:\n            target = {\"items\": [], \"volume_used\": 0, \"weight_used\": 0}\n            bins.append(target)\n        target[\"items\"].append(item[\"id\"])\n        target[\"volume_used\"] += item[\"volume\"]\n        target[\"weight_used\"] += item[\"weight\"]\n    verify(items, bins, capacity)\n    return bins\n\n\ndef verify(items, bins, capacity):\n    validate_items(items, capacity)\n    volume_limit, weight_limit = capacities(capacity)\n    by_id = {item[\"id\"]: item for item in items}\n    observed = []\n    for bin_ in bins:\n        if not bin_[\"items\"] or any(identity not in by_id for identity in bin_[\"items\"]):\n            raise ValueError(\"empty bin or unknown item\")\n        volume = sum(by_id[identity][\"volume\"] for identity in bin_[\"items\"])\n        weight = sum(by_id[identity][\"weight\"] for identity in bin_[\"items\"])\n        if volume != bin_[\"volume_used\"] or weight != bin_[\"weight_used\"]:\n            raise ValueError(\"reported load disagrees with item loads\")\n        if volume > volume_limit or weight > weight_limit:\n            raise ValueError(\"bin exceeds capacity\")\n        observed.extend(bin_[\"items\"])\n    if sorted(observed) != sorted(by_id):\n        raise ValueError(\"items missing or repeated\")\n    return True\n\n\ndef lower_bound(items, capacity):\n    validate_items(items, capacity)\n    volume_limit, weight_limit = capacities(capacity)\n    return max(\n        (sum(item[\"volume\"] for item in items) + volume_limit - 1) // volume_limit,\n        (sum(item[\"weight\"] for item in items) + weight_limit - 1) // weight_limit,\n    )\n\n\ndef exact_minimum(items, capacity, max_items=None, node_limit=None):\n    validate_items(items, capacity)\n    max_items = whole(capacity[\"exact_item_limit\"] if max_items is None else max_items, 1, 12, \"exact item limit\")\n    node_limit = whole(capacity[\"exact_node_limit\"] if node_limit is None else node_limit, 1, 50000, \"exact node limit\")\n    best = min((pack(items, capacity, algorithm) for algorithm in ALGORITHMS), key=len)\n    bound = lower_bound(items, capacity)\n    if len(best) == bound:\n        return {\"best_count\": len(best), \"lower_bound\": bound, \"proven\": True, \"method\": \"lower-bound\", \"nodes\": 0}\n    if len(items) > max_items:\n        return {\"best_count\": len(best), \"lower_bound\": bound, \"proven\": False, \"method\": \"skipped-item-limit\", \"nodes\": 0}\n    ordered = ordered_items(items, capacity, \"dominant-first-fit\")\n    volume_limit, weight_limit = capacities(capacity)\n    bins, nodes, limited = [], 0, False\n\n    def search(index):\n        nonlocal best, nodes, limited\n        if len(best) == bound:\n            return\n        if nodes >= node_limit:\n            limited = True\n            return\n        nodes += 1\n        if index == len(ordered):\n            if len(bins) < len(best):\n                best = copy.deepcopy(bins)\n            return\n        if len(bins) >= len(best):\n            return\n        item = ordered[index]\n        seen_loads = set()\n        for bin_ in bins:\n            load = (bin_[\"volume_used\"], bin_[\"weight_used\"])\n            if load in seen_loads:\n                continue\n            seen_loads.add(load)\n            if load[0] + item[\"volume\"] <= volume_limit and load[1] + item[\"weight\"] <= weight_limit:\n                bin_[\"items\"].append(item[\"id\"])\n                bin_[\"volume_used\"] += item[\"volume\"]\n                bin_[\"weight_used\"] += item[\"weight\"]\n                search(index + 1)\n                bin_[\"items\"].pop()\n                bin_[\"volume_used\"] -= item[\"volume\"]\n                bin_[\"weight_used\"] -= item[\"weight\"]\n        if len(bins) + 1 < len(best):\n            bins.append({\"items\": [item[\"id\"]], \"volume_used\": item[\"volume\"], \"weight_used\": item[\"weight\"]})\n            search(index + 1)\n            bins.pop()\n\n    search(0)\n    verify(items, best, capacity)\n    proven = not limited or len(best) == bound\n    return {\n        \"best_count\": len(best), \"lower_bound\": bound, \"proven\": proven,\n        \"method\": \"bounded-search\" if proven else \"node-limit-unproven\", \"nodes\": nodes,\n    }\n\n\ndef load_problem(data_dir):\n    data_dir = Path(data_dir)\n    csv_path, capacity_path = data_dir / \"items.csv\", data_dir / \"capacity.json\"\n    if csv_path.stat().st_size > 1_048_576 or capacity_path.stat().st_size > 20000:\n        raise ValueError(\"reference input exceeds size limit\")\n    capacity = json.loads(capacity_path.read_text(encoding=\"utf-8\"))\n    capacities(capacity)\n    if capacity[\"classification\"] != \"SYNTHETIC\":\n        raise ValueError(\"capacity must be explicitly SYNTHETIC\")\n    item_limit = whole(capacity[\"max_items_per_scenario\"], 1, 60, \"scenario item limit\")\n    with csv_path.open(encoding=\"utf-8\", newline=\"\") as handle:\n        rows = list(csv.DictReader(handle, strict=True))\n    if not rows or len(rows) > 1000:\n        raise ValueError(\"supply 1..1000 item-type rows\")\n    scenarios, seen = {}, set()\n    for row in rows:\n        if None in row or any(value is None for value in row.values()) or row[\"classification\"] != \"SYNTHETIC\":\n            raise ValueError(\"ragged or non-synthetic item row\")\n        scenario, sku = identifier(row[\"scenario\"], \"scenario\"), identifier(row[\"sku\"], \"SKU\")\n        if (scenario, sku) in seen:\n            raise ValueError(\"duplicate scenario/SKU\")\n        seen.add((scenario, sku))\n        count = whole(row[\"count\"], 1, 20, \"count\")\n        volume = whole(row[\"volume-units\"], 1, 10000, \"volume units\")\n        weight = whole(row[\"weight-units\"], 1, 10000, \"weight units\")\n        expanded = scenarios.setdefault(scenario, [])\n        expanded.extend({\"id\": f\"{sku}-{index:02d}\", \"volume\": volume, \"weight\": weight} for index in range(1, count + 1))\n        if len(expanded) > item_limit:\n            raise ValueError(\"scenario exceeds expanded item limit\")\n    for items in scenarios.values():\n        validate_items(items, capacity)\n    return scenarios, capacity\n\n\ndef analyze(data_dir, exact=False):\n    scenarios, capacity = load_problem(data_dir)\n    results = []\n    for scenario, items in sorted(scenarios.items()):\n        bound = lower_bound(items, capacity)\n        methods = {}\n        for algorithm in ALGORITHMS:\n            bins = pack(items, capacity, algorithm)\n            methods[algorithm] = {\"bin_count\": len(bins), \"gap_to_lower_bound\": len(bins) - bound, \"bins\": bins}\n        row = {\"scenario\": scenario, \"item_count\": len(items), \"lower_bound\": bound, \"algorithms\": methods}\n        if exact:\n            row[\"model_proof\"] = exact_minimum(items, capacity)\n        results.append(row)\n    return {\n        \"classification\": \"SYNTHETIC\", \"artifact_kind\": \"scalar-model-reference-not-physical-validation\",\n        \"capacity\": {\"volume_units\": capacity[\"volume_units\"], \"weight_units\": capacity[\"weight_units\"]},\n        \"scenarios\": results,\n    }\n\n\ndef main():\n    parser = argparse.ArgumentParser(description=__doc__)\n    parser.add_argument(\"data_dir\", type=Path)\n    parser.add_argument(\"--exact-small\", action=\"store_true\")\n    args = parser.parse_args()\n    try:\n        result = analyze(args.data_dir, args.exact_small)\n    except (OSError, ValueError, KeyError, TypeError, csv.Error) as exc:\n        parser.error(str(exc))\n    print(json.dumps(result, indent=2, sort_keys=True))\n\n\nif __name__ == \"__main__\":\n    main()\n","path":"templates/casework/work/starter/reference/tote_pack.py","sha256":"d592ad5a695e06e278552af552d74f8c5b7d74d8dd2d6caa9f5603dae9ee2e61"},{"bytes":9783,"content":"{\"authority\":\"inert-starter-data\",\"case_id\":\"library-kit-tote-study\",\"organization_seed\":\"applied-invention-lab\",\"schema\":\"hive-hub-seed-task-board/1\",\"tasks\":[{\"acceptance\":[\"Every capacity, item characteristic, and practical outcome is labeled synthetic or not observed.\",\"The ledger explicitly excludes physical fit and lifting-safety certification.\",\"At least one falsifying observation is specified for geometry and one for operator usefulness.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[],\"id\":\"research-assumptions\",\"inputs\":[\"starter/docs/problem-brief.md\",\"starter/docs/data-dictionary.md\",\"starter/docs/operator-worksheet.csv\",\"starter/data/capacity.json\"],\"instructions\":\"Create an assumption ledger for the fictional library-kit packing problem. Separate scalar capacity arithmetic from actual geometry, handling, user behavior, and commercial usefulness.\",\"outputs\":[\"deliverables/assumption-ledger.csv\"],\"state\":\"ready\",\"team\":\"research\",\"title\":\"Frame the practical question and model assumptions\"},{\"acceptance\":[\"Eleven item-type rows expand to 29 instances in four scenarios.\",\"All expanded IDs are unique within a scenario and every item individually fits the scalar capacities.\",\"The order-trap, weight-trap, mixed-classroom, and bulky-gaps purposes are identified.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"research-assumptions\"],\"id\":\"dataset-audit\",\"inputs\":[\"deliverables/assumption-ledger.csv\",\"starter/docs/data-dictionary.md\",\"starter/data/items.csv\",\"starter/data/capacity.json\",\"starter/reference/tote_pack.py\"],\"instructions\":\"Reconcile row counts, expanded item IDs, units, per-scenario totals, and capacity validity. Preserve source order because it is a deliberate baseline variable, not random observed history.\",\"outputs\":[\"deliverables/dataset-audit.json\"],\"state\":\"blocked\",\"team\":\"replication\",\"title\":\"Audit the original synthetic dataset\"},{\"acceptance\":[\"All expected baseline counts match and all assignment invariants pass.\",\"mixed-classroom reports dominant 7 versus input-order 6 and volume-first 8 bins.\",\"Proof labels apply only to the abstract model and no physical experiment is claimed.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"dataset-audit\"],\"id\":\"baseline-computation\",\"inputs\":[\"deliverables/dataset-audit.json\",\"starter/reference/tote_pack.py\",\"starter/reference/test_tote_pack.py\",\"starter/reference/expected-baseline.json\",\"starter/data/items.csv\",\"starter/data/capacity.json\"],\"instructions\":\"Run the authored tests and baseline CLI with optional small-model proof enabled. Record assignments, counts, lower bounds, and proof method for every scenario; do not omit unfavorable cases.\",\"outputs\":[\"deliverables/baseline-results.json\"],\"state\":\"blocked\",\"team\":\"experiments\",\"title\":\"Run the packing baseline and invariant checks\"},{\"acceptance\":[\"Every chosen scenario item appears once in the printable artifact.\",\"Both load dimensions and the model-only warning are visible without color dependence.\",\"No real tote was packed and no physical dimensions were verified merely by rendering the instructions.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"baseline-computation\"],\"id\":\"packing-prototype\",\"inputs\":[\"deliverables/baseline-results.json\",\"starter/docs/prototype-brief.md\",\"starter/docs/operator-worksheet.csv\",\"starter/data/items.csv\"],\"instructions\":\"Create a printable packing-instruction prototype from one baseline scenario. Show tote labels, exact item IDs, both scalar loads, remaining capacity, and a prominent model-only warning.\",\"outputs\":[\"deliverables/packing-instructions.html\"],\"state\":\"blocked\",\"team\":\"prototyping\",\"title\":\"Turn assignments into an operator-readable prototype\"},{\"acceptance\":[\"The result contains 4 scenarios × 3 algorithms × 20 trial counts.\",\"The same permutation is used for each algorithm within a trial.\",\"No measured sample is discarded to claim a universally superior heuristic.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"baseline-computation\"],\"id\":\"variant-experiment\",\"inputs\":[\"deliverables/baseline-results.json\",\"starter/docs/experiment-design.md\",\"starter/data/experiment-plan.json\",\"starter/data/items.csv\",\"starter/data/capacity.json\",\"starter/reference/run_experiment.py\",\"starter/reference/tote_pack.py\"],\"instructions\":\"Execute the original experiment runner using the supplied seed, 20 permutations per scenario, and all three declared algorithms. Retain every trial and the dataset/configuration/plan hashes.\",\"outputs\":[\"deliverables/variant-comparison.json\"],\"state\":\"blocked\",\"team\":\"experiments\",\"title\":\"Run the predeclared seeded comparison\"},{\"acceptance\":[\"The mixed-classroom regression and the bulky-gaps lower-bound gap are discussed.\",\"The conclusion uses the complete trial set and does not generalize four synthetic scenarios to real libraries.\",\"At least two decisions remain conditional on later physical or operator observations.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"variant-experiment\",\"packing-prototype\"],\"id\":\"research-interpretation\",\"inputs\":[\"deliverables/variant-comparison.json\",\"deliverables/baseline-results.json\",\"deliverables/packing-instructions.html\",\"deliverables/assumption-ledger.csv\",\"starter/docs/experiment-design.md\"],\"instructions\":\"Compare baseline, all trial results, and the operator prototype. Explain why one-dimensional intuition can fail under two constraints and distinguish computational evidence from physical or market evidence.\",\"outputs\":[\"deliverables/research-interpretation.md\"],\"state\":\"blocked\",\"team\":\"research\",\"title\":\"Interpret gains, regressions, and model gaps\"},{\"acceptance\":[\"Input hashes and every per-trial count agree or a discrepancy is explicitly reported.\",\"All assignment constraints are checked again rather than trusting the first report.\",\"Not-observed physical outcomes remain outside the replication claim.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"variant-experiment\"],\"id\":\"replication-run\",\"inputs\":[\"deliverables/variant-comparison.json\",\"deliverables/baseline-results.json\",\"starter/docs/replication-protocol.md\",\"starter/reference/tote_pack.py\",\"starter/reference/run_experiment.py\",\"starter/reference/test_tote_pack.py\",\"starter/reference/expected-baseline.json\",\"starter/data/items.csv\",\"starter/data/capacity.json\",\"starter/data/experiment-plan.json\"],\"instructions\":\"Follow the replication protocol in a fresh interpreter using the same explicit source files. Recompute hashes, baseline assignments, and seeded trials; report exact agreement or discrepancies, including runtime details.\",\"outputs\":[\"deliverables/replication-report.json\"],\"state\":\"blocked\",\"team\":\"replication\",\"title\":\"Replicate the computation independently\"},{\"acceptance\":[\"The protocol distinguishes planned observation from an actual measured value.\",\"Mock geometry and readability checks have explicit pass/fail criteria.\",\"No lifting-safety, structural-load, shipping, or real-world fit guarantee is proposed from scalar units.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"research-interpretation\",\"replication-run\"],\"id\":\"physical-fit-protocol\",\"inputs\":[\"deliverables/research-interpretation.md\",\"deliverables/replication-report.json\",\"deliverables/packing-instructions.html\",\"starter/docs/prototype-brief.md\",\"starter/docs/operator-worksheet.csv\"],\"instructions\":\"Design a later owner-approved study using empty or lightweight mock materials, not real transport or lifting limits. Specify geometry, item accessibility, labeling, and operator-comprehension observations without recording invented results.\",\"outputs\":[\"deliverables/physical-fit-protocol.csv\"],\"state\":\"blocked\",\"team\":\"prototyping\",\"title\":\"Prepare a harmless physical-fit observation protocol\"},{\"acceptance\":[\"A potential user job and disconfirming signal are described without fabricated demand.\",\"No patentability, novel algorithm, customer, savings, or willingness-to-pay claim is made.\",\"The brief names the physical and operator evidence needed before external positioning.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"research-interpretation\"],\"id\":\"application-hypothesis\",\"inputs\":[\"deliverables/research-interpretation.md\",\"deliverables/assumption-ledger.csv\",\"starter/docs/commercialization-boundary.md\",\"starter/docs/problem-brief.md\"],\"instructions\":\"Prepare an opportunity brief based on the observed computation and its limitations. Compare an explainable planning worksheet with an integration-heavy service; keep interviews, pricing, procurement, and intellectual-property review as separate future approvals.\",\"outputs\":[\"deliverables/application-hypothesis.md\"],\"state\":\"blocked\",\"team\":\"commercialization\",\"title\":\"Assess a bounded application hypothesis\"},{\"acceptance\":[\"The recommendation states what the code established and what it could not establish.\",\"All four scenarios and unfavorable evidence inform the recommendation.\",\"No real study, commercialization, patent filing, purchase, or publication is represented as approved or completed.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"physical-fit-protocol\",\"application-hypothesis\"],\"id\":\"lab-decision\",\"inputs\":[\"deliverables/replication-report.json\",\"deliverables/research-interpretation.md\",\"deliverables/physical-fit-protocol.csv\",\"deliverables/application-hypothesis.md\",\"starter/docs/commercialization-boundary.md\"],\"instructions\":\"Combine replication, interpretation, mock-fit protocol, and application hypothesis into a reviewable stop/continue recommendation. Distinguish a working computation from a proven invention and keep external action owner-gated.\",\"outputs\":[\"deliverables/lab-decision.json\"],\"state\":\"blocked\",\"team\":\"research\",\"title\":\"Record a conditional next-experiment decision\"}]}\n","path":"templates/casework/work/task-board.json","sha256":"f36c95b9f2dce75ca99c5a940e174004883bea4b52b0598fd20ea357d2fbb19a"},{"bytes":390,"content":"# commercialization\n\nRole: Application and adoption assessment\n\nPrepare a bounded opportunity hypothesis without fabricated demand, patents, savings, or customers.\n\nCase inputs and logical deliverables belong to the same-world casework workspace.\nRead only the inputs for assigned work; hand off verified artifact references.\nDo not claim another team's task or authorize external effects.\n","path":"templates/teams/commercialization/work/TEAM.md","sha256":"683aa378c4b577ef5c596c34c30dd53b27dcc4264681860c143851cf90a7a440"},{"bytes":1098,"content":"{\"case_workspace\":\"casework\",\"schema\":\"hive-hub-seed-team-work/1\",\"tasks\":[{\"acceptance\":[\"A potential user job and disconfirming signal are described without fabricated demand.\",\"No patentability, novel algorithm, customer, savings, or willingness-to-pay claim is made.\",\"The brief names the physical and operator evidence needed before external positioning.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"research-interpretation\"],\"id\":\"application-hypothesis\",\"inputs\":[\"deliverables/research-interpretation.md\",\"deliverables/assumption-ledger.csv\",\"starter/docs/commercialization-boundary.md\",\"starter/docs/problem-brief.md\"],\"instructions\":\"Prepare an opportunity brief based on the observed computation and its limitations. Compare an explainable planning worksheet with an integration-heavy service; keep interviews, pricing, procurement, and intellectual-property review as separate future approvals.\",\"outputs\":[\"deliverables/application-hypothesis.md\"],\"state\":\"blocked\",\"team\":\"commercialization\",\"title\":\"Assess a bounded application hypothesis\"}],\"team\":\"commercialization\"}\n","path":"templates/teams/commercialization/work/tasks.json","sha256":"dab6d799a080d0b38b0a5279ce75b8780a6bb2b82bf59b6071ef09859411f6c9"},{"bytes":358,"content":"# experiments\n\nRole: Computational experiments\n\nRun the baseline and seeded comparisons without cherry-picking favorable scenarios.\n\nCase inputs and logical deliverables belong to the same-world casework workspace.\nRead only the inputs for assigned work; hand off verified artifact references.\nDo not claim another team's task or authorize external effects.\n","path":"templates/teams/experiments/work/TEAM.md","sha256":"a055e5d907f55766f5978ee1fbba9e180b922d85b9bfa24b574b08a8546e7a0b"},{"bytes":1947,"content":"{\"case_workspace\":\"casework\",\"schema\":\"hive-hub-seed-team-work/1\",\"tasks\":[{\"acceptance\":[\"All expected baseline counts match and all assignment invariants pass.\",\"mixed-classroom reports dominant 7 versus input-order 6 and volume-first 8 bins.\",\"Proof labels apply only to the abstract model and no physical experiment is claimed.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"dataset-audit\"],\"id\":\"baseline-computation\",\"inputs\":[\"deliverables/dataset-audit.json\",\"starter/reference/tote_pack.py\",\"starter/reference/test_tote_pack.py\",\"starter/reference/expected-baseline.json\",\"starter/data/items.csv\",\"starter/data/capacity.json\"],\"instructions\":\"Run the authored tests and baseline CLI with optional small-model proof enabled. Record assignments, counts, lower bounds, and proof method for every scenario; do not omit unfavorable cases.\",\"outputs\":[\"deliverables/baseline-results.json\"],\"state\":\"blocked\",\"team\":\"experiments\",\"title\":\"Run the packing baseline and invariant checks\"},{\"acceptance\":[\"The result contains 4 scenarios × 3 algorithms × 20 trial counts.\",\"The same permutation is used for each algorithm within a trial.\",\"No measured sample is discarded to claim a universally superior heuristic.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"baseline-computation\"],\"id\":\"variant-experiment\",\"inputs\":[\"deliverables/baseline-results.json\",\"starter/docs/experiment-design.md\",\"starter/data/experiment-plan.json\",\"starter/data/items.csv\",\"starter/data/capacity.json\",\"starter/reference/run_experiment.py\",\"starter/reference/tote_pack.py\"],\"instructions\":\"Execute the original experiment runner using the supplied seed, 20 permutations per scenario, and all three declared algorithms. Retain every trial and the dataset/configuration/plan hashes.\",\"outputs\":[\"deliverables/variant-comparison.json\"],\"state\":\"blocked\",\"team\":\"experiments\",\"title\":\"Run the predeclared seeded comparison\"}],\"team\":\"experiments\"}\n","path":"templates/teams/experiments/work/tasks.json","sha256":"7a3463354263b8494c99dea5cad0da6e6cfbf28aeef084168cdf378ace6007f3"},{"bytes":383,"content":"# prototyping\n\nRole: Usable prototype and observation design\n\nTurn computed assignments into reviewable packing instructions and a later physical-fit study.\n\nCase inputs and logical deliverables belong to the same-world casework workspace.\nRead only the inputs for assigned work; hand off verified artifact references.\nDo not claim another team's task or authorize external effects.\n","path":"templates/teams/prototyping/work/TEAM.md","sha256":"24fd7916d5c164d6f0dce79ae0ae6e6bd00e2fa79a01b5648a0306a64dad62b2"},{"bytes":2006,"content":"{\"case_workspace\":\"casework\",\"schema\":\"hive-hub-seed-team-work/1\",\"tasks\":[{\"acceptance\":[\"Every chosen scenario item appears once in the printable artifact.\",\"Both load dimensions and the model-only warning are visible without color dependence.\",\"No real tote was packed and no physical dimensions were verified merely by rendering the instructions.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"baseline-computation\"],\"id\":\"packing-prototype\",\"inputs\":[\"deliverables/baseline-results.json\",\"starter/docs/prototype-brief.md\",\"starter/docs/operator-worksheet.csv\",\"starter/data/items.csv\"],\"instructions\":\"Create a printable packing-instruction prototype from one baseline scenario. Show tote labels, exact item IDs, both scalar loads, remaining capacity, and a prominent model-only warning.\",\"outputs\":[\"deliverables/packing-instructions.html\"],\"state\":\"blocked\",\"team\":\"prototyping\",\"title\":\"Turn assignments into an operator-readable prototype\"},{\"acceptance\":[\"The protocol distinguishes planned observation from an actual measured value.\",\"Mock geometry and readability checks have explicit pass/fail criteria.\",\"No lifting-safety, structural-load, shipping, or real-world fit guarantee is proposed from scalar units.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"research-interpretation\",\"replication-run\"],\"id\":\"physical-fit-protocol\",\"inputs\":[\"deliverables/research-interpretation.md\",\"deliverables/replication-report.json\",\"deliverables/packing-instructions.html\",\"starter/docs/prototype-brief.md\",\"starter/docs/operator-worksheet.csv\"],\"instructions\":\"Design a later owner-approved study using empty or lightweight mock materials, not real transport or lifting limits. Specify geometry, item accessibility, labeling, and operator-comprehension observations without recording invented results.\",\"outputs\":[\"deliverables/physical-fit-protocol.csv\"],\"state\":\"blocked\",\"team\":\"prototyping\",\"title\":\"Prepare a harmless physical-fit observation protocol\"}],\"team\":\"prototyping\"}\n","path":"templates/teams/prototyping/work/tasks.json","sha256":"52a65b3fe6ab04fc161baf36304e055bfb7f43d10c9c45b9b4bb11ca591d69c1"},{"bytes":358,"content":"# replication\n\nRole: Independent reproducibility\n\nAudit the original dataset and reproduce checks, hashes, assignments, and limits.\n\nCase inputs and logical deliverables belong to the same-world casework workspace.\nRead only the inputs for assigned work; hand off verified artifact references.\nDo not claim another team's task or authorize external effects.\n","path":"templates/teams/replication/work/TEAM.md","sha256":"414478f8ad33f90b93e45ccf3b71b2dc939fee658fadfdd23d3f6c492e78ee5f"},{"bytes":2085,"content":"{\"case_workspace\":\"casework\",\"schema\":\"hive-hub-seed-team-work/1\",\"tasks\":[{\"acceptance\":[\"Eleven item-type rows expand to 29 instances in four scenarios.\",\"All expanded IDs are unique within a scenario and every item individually fits the scalar capacities.\",\"The order-trap, weight-trap, mixed-classroom, and bulky-gaps purposes are identified.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"research-assumptions\"],\"id\":\"dataset-audit\",\"inputs\":[\"deliverables/assumption-ledger.csv\",\"starter/docs/data-dictionary.md\",\"starter/data/items.csv\",\"starter/data/capacity.json\",\"starter/reference/tote_pack.py\"],\"instructions\":\"Reconcile row counts, expanded item IDs, units, per-scenario totals, and capacity validity. Preserve source order because it is a deliberate baseline variable, not random observed history.\",\"outputs\":[\"deliverables/dataset-audit.json\"],\"state\":\"blocked\",\"team\":\"replication\",\"title\":\"Audit the original synthetic dataset\"},{\"acceptance\":[\"Input hashes and every per-trial count agree or a discrepancy is explicitly reported.\",\"All assignment constraints are checked again rather than trusting the first report.\",\"Not-observed physical outcomes remain outside the replication claim.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"variant-experiment\"],\"id\":\"replication-run\",\"inputs\":[\"deliverables/variant-comparison.json\",\"deliverables/baseline-results.json\",\"starter/docs/replication-protocol.md\",\"starter/reference/tote_pack.py\",\"starter/reference/run_experiment.py\",\"starter/reference/test_tote_pack.py\",\"starter/reference/expected-baseline.json\",\"starter/data/items.csv\",\"starter/data/capacity.json\",\"starter/data/experiment-plan.json\"],\"instructions\":\"Follow the replication protocol in a fresh interpreter using the same explicit source files. Recompute hashes, baseline assignments, and seeded trials; report exact agreement or discrepancies, including runtime details.\",\"outputs\":[\"deliverables/replication-report.json\"],\"state\":\"blocked\",\"team\":\"replication\",\"title\":\"Replicate the computation independently\"}],\"team\":\"replication\"}\n","path":"templates/teams/replication/work/tasks.json","sha256":"8b243011adc227ffcf63800add698d690976525d773e19e1b8c946c0d0da2cfd"},{"bytes":382,"content":"# research\n\nRole: Problem framing and interpretation\n\nDefine the practical question, assumptions, decision criteria, and honest limits of the scalar model.\n\nCase inputs and logical deliverables belong to the same-world casework workspace.\nRead only the inputs for assigned work; hand off verified artifact references.\nDo not claim another team's task or authorize external effects.\n","path":"templates/teams/research/work/TEAM.md","sha256":"5fd67e0cfbd3fba8fcff5d6a943250c5d5ff1e0b4ae9abe6b84eca4d24452a89"},{"bytes":2978,"content":"{\"case_workspace\":\"casework\",\"schema\":\"hive-hub-seed-team-work/1\",\"tasks\":[{\"acceptance\":[\"Every capacity, item characteristic, and practical outcome is labeled synthetic or not observed.\",\"The ledger explicitly excludes physical fit and lifting-safety certification.\",\"At least one falsifying observation is specified for geometry and one for operator usefulness.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[],\"id\":\"research-assumptions\",\"inputs\":[\"starter/docs/problem-brief.md\",\"starter/docs/data-dictionary.md\",\"starter/docs/operator-worksheet.csv\",\"starter/data/capacity.json\"],\"instructions\":\"Create an assumption ledger for the fictional library-kit packing problem. Separate scalar capacity arithmetic from actual geometry, handling, user behavior, and commercial usefulness.\",\"outputs\":[\"deliverables/assumption-ledger.csv\"],\"state\":\"ready\",\"team\":\"research\",\"title\":\"Frame the practical question and model assumptions\"},{\"acceptance\":[\"The mixed-classroom regression and the bulky-gaps lower-bound gap are discussed.\",\"The conclusion uses the complete trial set and does not generalize four synthetic scenarios to real libraries.\",\"At least two decisions remain conditional on later physical or operator observations.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"variant-experiment\",\"packing-prototype\"],\"id\":\"research-interpretation\",\"inputs\":[\"deliverables/variant-comparison.json\",\"deliverables/baseline-results.json\",\"deliverables/packing-instructions.html\",\"deliverables/assumption-ledger.csv\",\"starter/docs/experiment-design.md\"],\"instructions\":\"Compare baseline, all trial results, and the operator prototype. Explain why one-dimensional intuition can fail under two constraints and distinguish computational evidence from physical or market evidence.\",\"outputs\":[\"deliverables/research-interpretation.md\"],\"state\":\"blocked\",\"team\":\"research\",\"title\":\"Interpret gains, regressions, and model gaps\"},{\"acceptance\":[\"The recommendation states what the code established and what it could not establish.\",\"All four scenarios and unfavorable evidence inform the recommendation.\",\"No real study, commercialization, patent filing, purchase, or publication is represented as approved or completed.\"],\"assignee\":null,\"completed_evidence\":[],\"depends_on\":[\"physical-fit-protocol\",\"application-hypothesis\"],\"id\":\"lab-decision\",\"inputs\":[\"deliverables/replication-report.json\",\"deliverables/research-interpretation.md\",\"deliverables/physical-fit-protocol.csv\",\"deliverables/application-hypothesis.md\",\"starter/docs/commercialization-boundary.md\"],\"instructions\":\"Combine replication, interpretation, mock-fit protocol, and application hypothesis into a reviewable stop/continue recommendation. Distinguish a working computation from a proven invention and keep external action owner-gated.\",\"outputs\":[\"deliverables/lab-decision.json\"],\"state\":\"blocked\",\"team\":\"research\",\"title\":\"Record a conditional next-experiment decision\"}],\"team\":\"research\"}\n","path":"templates/teams/research/work/tasks.json","sha256":"d13dfff6b8e47f065b1a1839654888e7ff9f33951a9b4fc0b48cedf1e80d0996"}],"kind":"organization-seed","mission":"Coordinate research, experiments, prototyping, replication, and commercialization around reproducible synthetic library-kit tote packing, with a runnable baseline and explicit limits on physical and business claims.","name":"The Applied Invention Lab","organization":{"directory":"organization","scaffold":{"kind":"organization","mode":"hive","slug":"applied-invention-lab","world_id":"demo-applied-invention-lab"}},"protocol":"rapp-work/1","relatedSeeds":["one-person-conglomerate","enterprise-transformation-firm"],"schema":"hive-hub-organization-seed/1","slug":"applied-invention-lab","status":"seed-not-activated","tagline":"Test a practical packing idea before claiming an invention works.","tasks":[{"acceptance":["Every capacity, item characteristic, and practical outcome is labeled synthetic or not observed.","The ledger explicitly excludes physical fit and lifting-safety certification.","At least one falsifying observation is specified for geometry and one for operator usefulness."],"assignee":null,"completed_evidence":[],"depends_on":[],"id":"research-assumptions","inputs":["starter/docs/problem-brief.md","starter/docs/data-dictionary.md","starter/docs/operator-worksheet.csv","starter/data/capacity.json"],"instructions":"Create an assumption ledger for the fictional library-kit packing problem. Separate scalar capacity arithmetic from actual geometry, handling, user behavior, and commercial usefulness.","outputs":["deliverables/assumption-ledger.csv"],"state":"ready","team":"research","title":"Frame the practical question and model assumptions"},{"acceptance":["Eleven item-type rows expand to 29 instances in four scenarios.","All expanded IDs are unique within a scenario and every item individually fits the scalar capacities.","The order-trap, weight-trap, mixed-classroom, and bulky-gaps purposes are identified."],"assignee":null,"completed_evidence":[],"depends_on":["research-assumptions"],"id":"dataset-audit","inputs":["deliverables/assumption-ledger.csv","starter/docs/data-dictionary.md","starter/data/items.csv","starter/data/capacity.json","starter/reference/tote_pack.py"],"instructions":"Reconcile row counts, expanded item IDs, units, per-scenario totals, and capacity validity. Preserve source order because it is a deliberate baseline variable, not random observed history.","outputs":["deliverables/dataset-audit.json"],"state":"blocked","team":"replication","title":"Audit the original synthetic dataset"},{"acceptance":["All expected baseline counts match and all assignment invariants pass.","mixed-classroom reports dominant 7 versus input-order 6 and volume-first 8 bins.","Proof labels apply only to the abstract model and no physical experiment is claimed."],"assignee":null,"completed_evidence":[],"depends_on":["dataset-audit"],"id":"baseline-computation","inputs":["deliverables/dataset-audit.json","starter/reference/tote_pack.py","starter/reference/test_tote_pack.py","starter/reference/expected-baseline.json","starter/data/items.csv","starter/data/capacity.json"],"instructions":"Run the authored tests and baseline CLI with optional small-model proof enabled. Record assignments, counts, lower bounds, and proof method for every scenario; do not omit unfavorable cases.","outputs":["deliverables/baseline-results.json"],"state":"blocked","team":"experiments","title":"Run the packing baseline and invariant checks"},{"acceptance":["Every chosen scenario item appears once in the printable artifact.","Both load dimensions and the model-only warning are visible without color dependence.","No real tote was packed and no physical dimensions were verified merely by rendering the instructions."],"assignee":null,"completed_evidence":[],"depends_on":["baseline-computation"],"id":"packing-prototype","inputs":["deliverables/baseline-results.json","starter/docs/prototype-brief.md","starter/docs/operator-worksheet.csv","starter/data/items.csv"],"instructions":"Create a printable packing-instruction prototype from one baseline scenario. Show tote labels, exact item IDs, both scalar loads, remaining capacity, and a prominent model-only warning.","outputs":["deliverables/packing-instructions.html"],"state":"blocked","team":"prototyping","title":"Turn assignments into an operator-readable prototype"},{"acceptance":["The result contains 4 scenarios × 3 algorithms × 20 trial counts.","The same permutation is used for each algorithm within a trial.","No measured sample is discarded to claim a universally superior heuristic."],"assignee":null,"completed_evidence":[],"depends_on":["baseline-computation"],"id":"variant-experiment","inputs":["deliverables/baseline-results.json","starter/docs/experiment-design.md","starter/data/experiment-plan.json","starter/data/items.csv","starter/data/capacity.json","starter/reference/run_experiment.py","starter/reference/tote_pack.py"],"instructions":"Execute the original experiment runner using the supplied seed, 20 permutations per scenario, and all three declared algorithms. Retain every trial and the dataset/configuration/plan hashes.","outputs":["deliverables/variant-comparison.json"],"state":"blocked","team":"experiments","title":"Run the predeclared seeded comparison"},{"acceptance":["The mixed-classroom regression and the bulky-gaps lower-bound gap are discussed.","The conclusion uses the complete trial set and does not generalize four synthetic scenarios to real libraries.","At least two decisions remain conditional on later physical or operator observations."],"assignee":null,"completed_evidence":[],"depends_on":["variant-experiment","packing-prototype"],"id":"research-interpretation","inputs":["deliverables/variant-comparison.json","deliverables/baseline-results.json","deliverables/packing-instructions.html","deliverables/assumption-ledger.csv","starter/docs/experiment-design.md"],"instructions":"Compare baseline, all trial results, and the operator prototype. Explain why one-dimensional intuition can fail under two constraints and distinguish computational evidence from physical or market evidence.","outputs":["deliverables/research-interpretation.md"],"state":"blocked","team":"research","title":"Interpret gains, regressions, and model gaps"},{"acceptance":["Input hashes and every per-trial count agree or a discrepancy is explicitly reported.","All assignment constraints are checked again rather than trusting the first report.","Not-observed physical outcomes remain outside the replication claim."],"assignee":null,"completed_evidence":[],"depends_on":["variant-experiment"],"id":"replication-run","inputs":["deliverables/variant-comparison.json","deliverables/baseline-results.json","starter/docs/replication-protocol.md","starter/reference/tote_pack.py","starter/reference/run_experiment.py","starter/reference/test_tote_pack.py","starter/reference/expected-baseline.json","starter/data/items.csv","starter/data/capacity.json","starter/data/experiment-plan.json"],"instructions":"Follow the replication protocol in a fresh interpreter using the same explicit source files. Recompute hashes, baseline assignments, and seeded trials; report exact agreement or discrepancies, including runtime details.","outputs":["deliverables/replication-report.json"],"state":"blocked","team":"replication","title":"Replicate the computation independently"},{"acceptance":["The protocol distinguishes planned observation from an actual measured value.","Mock geometry and readability checks have explicit pass/fail criteria.","No lifting-safety, structural-load, shipping, or real-world fit guarantee is proposed from scalar units."],"assignee":null,"completed_evidence":[],"depends_on":["research-interpretation","replication-run"],"id":"physical-fit-protocol","inputs":["deliverables/research-interpretation.md","deliverables/replication-report.json","deliverables/packing-instructions.html","starter/docs/prototype-brief.md","starter/docs/operator-worksheet.csv"],"instructions":"Design a later owner-approved study using empty or lightweight mock materials, not real transport or lifting limits. Specify geometry, item accessibility, labeling, and operator-comprehension observations without recording invented results.","outputs":["deliverables/physical-fit-protocol.csv"],"state":"blocked","team":"prototyping","title":"Prepare a harmless physical-fit observation protocol"},{"acceptance":["A potential user job and disconfirming signal are described without fabricated demand.","No patentability, novel algorithm, customer, savings, or willingness-to-pay claim is made.","The brief names the physical and operator evidence needed before external positioning."],"assignee":null,"completed_evidence":[],"depends_on":["research-interpretation"],"id":"application-hypothesis","inputs":["deliverables/research-interpretation.md","deliverables/assumption-ledger.csv","starter/docs/commercialization-boundary.md","starter/docs/problem-brief.md"],"instructions":"Prepare an opportunity brief based on the observed computation and its limitations. Compare an explainable planning worksheet with an integration-heavy service; keep interviews, pricing, procurement, and intellectual-property review as separate future approvals.","outputs":["deliverables/application-hypothesis.md"],"state":"blocked","team":"commercialization","title":"Assess a bounded application hypothesis"},{"acceptance":["The recommendation states what the code established and what it could not establish.","All four scenarios and unfavorable evidence inform the recommendation.","No real study, commercialization, patent filing, purchase, or publication is represented as approved or completed."],"assignee":null,"completed_evidence":[],"depends_on":["physical-fit-protocol","application-hypothesis"],"id":"lab-decision","inputs":["deliverables/replication-report.json","deliverables/research-interpretation.md","deliverables/physical-fit-protocol.csv","deliverables/application-hypothesis.md","starter/docs/commercialization-boundary.md"],"instructions":"Combine replication, interpretation, mock-fit protocol, and application hypothesis into a reviewable stop/continue recommendation. Distinguish a working computation from a proven invention and keep external action owner-gated.","outputs":["deliverables/lab-decision.json"],"state":"blocked","team":"research","title":"Record a conditional next-experiment decision"}],"workspaceProfile":"rapp-work-sdk/1","workspaces":[{"directory":"workspaces/research","id":"research","name":"research","purpose":"Define the practical question, assumptions, decision criteria, and honest limits of the scalar model.","role":"Problem framing and interpretation","scaffold":{"kind":"workspace","mode":"hive","slug":"applied-invention-lab-research","world_id":"demo-applied-invention-lab"},"template":"templates/teams/research"},{"directory":"workspaces/experiments","id":"experiments","name":"experiments","purpose":"Run the baseline and seeded comparisons without cherry-picking favorable scenarios.","role":"Computational experiments","scaffold":{"kind":"workspace","mode":"hive","slug":"applied-invention-lab-experiments","world_id":"demo-applied-invention-lab"},"template":"templates/teams/experiments"},{"directory":"workspaces/prototyping","id":"prototyping","name":"prototyping","purpose":"Turn computed assignments into reviewable packing instructions and a later physical-fit study.","role":"Usable prototype and observation design","scaffold":{"kind":"workspace","mode":"hive","slug":"applied-invention-lab-prototyping","world_id":"demo-applied-invention-lab"},"template":"templates/teams/prototyping"},{"directory":"workspaces/replication","id":"replication","name":"replication","purpose":"Audit the original dataset and reproduce checks, hashes, assignments, and limits.","role":"Independent reproducibility","scaffold":{"kind":"workspace","mode":"hive","slug":"applied-invention-lab-replication","world_id":"demo-applied-invention-lab"},"template":"templates/teams/replication"},{"directory":"workspaces/commercialization","id":"commercialization","name":"commercialization","purpose":"Prepare a bounded opportunity hypothesis without fabricated demand, patents, savings, or customers.","role":"Application and adoption assessment","scaffold":{"kind":"workspace","mode":"hive","slug":"applied-invention-lab-commercialization","world_id":"demo-applied-invention-lab"},"template":"templates/teams/commercialization"},{"directory":"workspaces/casework","id":"casework","name":"Shared delivery case","purpose":"Own synthetic intake, shared inputs, and accepted deliverables.","role":"case-custodian","scaffold":{"kind":"workspace","mode":"hive","slug":"applied-invention-lab-casework","world_id":"demo-applied-invention-lab"},"template":"templates/casework"}]}