{ "status": "PRELIMINARY", "release_date": "2026-10-22", "datasets": [ { "id": "forestry-features", "category": "forestry", "title": "Maine FIA forest measurements", "description": "Maine forest inventory measurements for exploratory models of tree dimensions, biomass, carbon and forest condition. The two tree source parts are combined before deduplication. All available years are retained.", "stat": "903,254 unique feature rows", "type": "PUBLIC FOREST INVENTORY", "format": "CSV feature tables + species codebook", "license": "USDA public-use data - CC0 identified in USDA\u2019s dataset record", "caveat": "Represents 1,095,255 tree and condition observations, with repeated feature rows stored as record_count. Download both parts. Multi-year sample; precise locations and record linkages removed. Not a current tree census or a basis for statewide estimates.", "downloads": [ { "url": "/downloads/preliminary-2026-10-22/forestry/krummholz-forestry-preliminary-2026-10-22-part-01.zip", "label": "Download part 1", "size": "17.0 MB", "requires_purchase": true }, { "url": "/downloads/preliminary-2026-10-22/forestry/krummholz-forestry-preliminary-2026-10-22-part-02.zip", "label": "Download part 2", "size": "8.4 MB", "requires_purchase": true } ], "docs": [ { "url": "/downloads/preliminary-2026-10-22/forestry/README.md", "label": "Read documentation", "size": "6 KB" }, { "url": "/downloads/preliminary-2026-10-22/forestry/schema.json", "label": "Field dictionary", "size": "63 KB" }, { "url": "/downloads/preliminary-2026-10-22/forestry/audit.json", "label": "Cleaning audit", "size": "21 KB" } ], "sources": [ { "label": "USDA Forest Service FIA", "url": "https://research.fs.usda.gov/programs/fia" } ], "purchase": { "required": true, "price_usd": "14.99", "tax": "Applicable sales tax calculated at checkout", "url": "https://krummholz.ai/datasets/purchase/?sku=forestry-2026-10-22" } }, { "id": "fishing-features", "category": "fishing", "title": "NOAA MRIP 2024 fishing observations", "description": "NOAA Marine Recreational Information Program 2024 recreational fishing observations across all six available waves. Catch, trip activity and measured fish size support exploratory tabular ML. These are recreational survey data, not commercial fishing or vessel-control training data.", "stat": "295,104 unique feature rows", "type": "RECREATIONAL FISHING SURVEY", "format": "CSV feature tables + species codebook", "license": "NOAA U.S. government public-use data", "caveat": "Represents 392,082 retained catch, trip and size observations. Repeated feature rows use record_count. Broad state/area fields remain; fine locations and survey linkage keys are removed. Does not reproduce NOAA population estimates.", "downloads": [ { "url": "/downloads/preliminary-2026-10-22/fishing/krummholz-fishing-preliminary-2026-10-22.zip", "label": "Download ZIP", "size": "2.7 MB", "requires_purchase": true } ], "docs": [ { "url": "/downloads/preliminary-2026-10-22/fishing/README.md", "label": "Read documentation", "size": "5 KB" }, { "url": "/downloads/preliminary-2026-10-22/fishing/schema.json", "label": "Field dictionary", "size": "29 KB" }, { "url": "/downloads/preliminary-2026-10-22/fishing/audit.json", "label": "Cleaning audit", "size": "10 KB" } ], "sources": [ { "label": "NOAA MRIP", "url": "https://www.fisheries.noaa.gov/recreational-fishing-data/recreational-fishing-data-downloads" } ], "purchase": { "required": true, "price_usd": "14.99", "tax": "Applicable sales tax calculated at checkout", "url": "https://krummholz.ai/datasets/purchase/?sku=fishing-2026-10-22" } }, { "id": "banking77", "category": "customer-service", "title": "BANKING77 banking customer-service intents", "description": "Banking customer queries across all 77 intents, including card support, payments, transfers, cash withdrawals, fees, identity verification and refunds.", "stat": "13,006 queries \u00b7 77 intents", "type": "LABELED INTENT QUERIES", "format": "CSV or JSONL (same records)", "license": "CC-BY-4.0", "caveat": "Privacy screening changes some wording; five additional fine-location spans were generalized in the 2026-10-23 review. Queries and original intent/split labels only. No guarantee of complete anonymization or removal of semantic paraphrases.", "downloads": [ { "url": "/downloads/preliminary-2026-10-22/customer-service/banking77-preliminary-2026-10-22.zip", "label": "Download ZIP", "size": "848 KB" } ], "docs": [ { "url": "/downloads/preliminary-2026-10-22/customer-service/banking77/README.md", "label": "Read documentation", "size": "6 KB" }, { "url": "/downloads/preliminary-2026-10-22/customer-service/banking77/audit.json", "label": "Cleaning audit", "size": "3 KB" } ], "sources": [ { "label": "Publisher dataset", "url": "https://github.com/PolyAI-LDN/task-specific-datasets" }, { "label": "License terms", "url": "https://creativecommons.org/licenses/by/4.0/" } ], "privacy_revision_date": "2026-10-23" }, { "id": "clinc150", "category": "customer-service", "title": "CLINC150 shopping and payment intents", "description": "Crowdsourced requests for order placement, order status and declined cards. The other intents and out-of-scope examples are excluded.", "stat": "447 queries \u00b7 3 intents", "type": "LABELED INTENT QUERIES", "format": "CSV or JSONL (same records)", "license": "CC-BY-3.0", "caveat": "Automated privacy screening changes some wording. Queries and intent labels only; source evaluation splits are retained but modified. No guarantee of complete anonymization or removal of semantic paraphrases.", "downloads": [ { "url": "/downloads/preliminary-2026-10-22/customer-service/clinc150-preliminary-2026-10-22.zip", "label": "Download ZIP", "size": "38 KB" } ], "docs": [ { "url": "/downloads/preliminary-2026-10-22/customer-service/clinc150/README.md", "label": "Read documentation", "size": "6 KB" }, { "url": "/downloads/preliminary-2026-10-22/customer-service/clinc150/audit.json", "label": "Cleaning audit", "size": "2 KB" } ], "sources": [ { "label": "Publisher dataset", "url": "https://github.com/clinc/oos-eval" }, { "label": "License terms", "url": "https://creativecommons.org/licenses/by/3.0/" } ] }, { "id": "jaco-play-numeric", "category": "robotics", "title": "Jaco Play - numeric trajectories", "description": "1,085 complete tabletop-robot episodes with 77,965 ordered numeric frames and 89 task instructions, extracted from the pinned LeRobot conversion. Images and video excluded.", "stat": "1,085 episodes \u00b7 77,965 frames", "type": "NUMERIC ROBOT DEMONSTRATIONS", "format": "CSV frames, episodes and task instructions", "license": "CC BY 4.0", "caveat": "Full numeric inventory of the pinned LeRobot Jaco conversion. Images and video excluded. Coordinate units are not independently verified; no independent evaluation split. Offline research data, not validated real-robot control commands.", "downloads": [ { "url": "/downloads/preliminary-2026-10-22/robotics/krummholz-jaco-numeric-preliminary-2026-10-22.zip", "label": "Download ZIP", "size": "5.9 MB", "requires_purchase": true } ], "docs": [ { "url": "/downloads/preliminary-2026-10-22/robotics/README.md", "label": "Read documentation", "size": "5 KB" }, { "url": "/downloads/preliminary-2026-10-22/robotics/SCHEMA.json", "label": "Field dictionary", "size": "2 KB" }, { "url": "/downloads/preliminary-2026-10-22/robotics/AUDIT.json", "label": "Cleaning audit", "size": "2 KB" } ], "sources": [ { "label": "CLVR Jaco Play", "url": "https://github.com/clvrai/clvr_jaco_play_dataset" }, { "label": "LeRobot conversion", "url": "https://huggingface.co/datasets/lerobot/jaco_play" } ], "purchase": { "required": true, "price_usd": "14.99", "tax": "Applicable sales tax calculated at checkout", "url": "https://krummholz.ai/datasets/purchase/?sku=robotics-2026-10-22" } } ], "packages": [ { "category": "forestry", "name": "krummholz-forestry-preliminary-2026-10-22-part-01.zip", "relative_path": "forestry/krummholz-forestry-preliminary-2026-10-22-part-01.zip", "bytes": 17022450, "sha256": "840f44033e3e6db7eaccb946ba7543c6410de7dd32ef1437c33303b512b2a722", "url": "https://krummholz.ai/downloads/preliminary-2026-10-22/forestry/krummholz-forestry-preliminary-2026-10-22-part-01.zip" }, { "category": "forestry", "name": "krummholz-forestry-preliminary-2026-10-22-part-02.zip", "relative_path": "forestry/krummholz-forestry-preliminary-2026-10-22-part-02.zip", "bytes": 8393335, "sha256": "8a2beda406a38ad75029d92edb07e080887cf4c0abd250e7e94cc6bae8b44165", "url": "https://krummholz.ai/downloads/preliminary-2026-10-22/forestry/krummholz-forestry-preliminary-2026-10-22-part-02.zip" }, { "category": "fishing", "name": "krummholz-fishing-preliminary-2026-10-22.zip", "relative_path": "fishing/krummholz-fishing-preliminary-2026-10-22.zip", "bytes": 2735852, "sha256": "f39aadaa7a0cf3e9c6a8f11f8912011449b984a97f957a4593774b444d663e05", "url": "https://krummholz.ai/downloads/preliminary-2026-10-22/fishing/krummholz-fishing-preliminary-2026-10-22.zip" }, { "category": "customer-service", "name": "banking77-preliminary-2026-10-22.zip", "relative_path": "customer-service/banking77-preliminary-2026-10-22.zip", "bytes": 848326, "sha256": "f02996ae3e2b35dd5a6c5ff02fb0598e3baaa7cd6aa9751474263f39cd13dd6d", "url": "https://krummholz.ai/downloads/preliminary-2026-10-22/customer-service/banking77-preliminary-2026-10-22.zip", "privacy_revision_date": "2026-10-23" }, { "category": "customer-service", "name": "clinc150-preliminary-2026-10-22.zip", "relative_path": "customer-service/clinc150-preliminary-2026-10-22.zip", "bytes": 37705, "sha256": "78fd8887e09625277623b278935548c04c5622ef2f4a26b0a98a96e26e8bc99f", "url": "https://krummholz.ai/downloads/preliminary-2026-10-22/customer-service/clinc150-preliminary-2026-10-22.zip" }, { "category": "robotics", "name": "krummholz-jaco-numeric-preliminary-2026-10-22.zip", "relative_path": "robotics/krummholz-jaco-numeric-preliminary-2026-10-22.zip", "bytes": 5947639, "sha256": "877a01d2512d63f95733dc6c09f8770f704f179e513fa14fbceff95068a846c3", "url": "https://krummholz.ai/downloads/preliminary-2026-10-22/robotics/krummholz-jaco-numeric-preliminary-2026-10-22.zip" } ], "privacy_revision": { "date": "2026-10-23", "scope": "BANKING77 targeted residual-location privacy revision", "changed_records": 5, "rows_removed": 0, "unchanged_record_count": 13006, "notes": "Five fine-location spans were replaced with LOCATION placeholders; changed content-derived record identifiers and all alternate/review copies were updated. No raw-to-clean crosswalk is published. All other preliminary package bytes are unchanged." }, "catalog_updated": "2026-10-26" }