{"schema":"record/v1","id":"src_01M569GD9DRW911XJ6GRTM87HM","type":"source","revision":2,"etag":"\"r2.s0\"","title":"Data Provenance Initiative: Data Provenance Collection","summary":null,"status":"active","body":{"text":"","archived":false,"revision":{"ref":"main","pinned":false},"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Audit of 44 data collections (1,800+ text finetuning datasets) documenting sources, licenses and creators, with scripts to filter by self-reported license constraints. Method and data for license-aware dataset selection; text-focused, but the audit approach transfers to media datasets.","source_type":"dataset","availability":"available","dependencies":[],"source_owner":"Data Provenance Initiative","canonical_url":"https://github.com/data-provenance-initiative/data-provenance-collection","next_check_at":"2026-10-31T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":["Text datasets only; licenses are self-reported."],"upstream_updated_at":"2025-03-26T02:46:12.000Z"},"categories":["T20","T16"],"tags":["dataset-licenses","audit","provenance","text","level:advanced","code:python"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://github.com/Data-Provenance-Initiative/Data-Provenance-Collection","claim":"README: volunteer effort for transparency in training datasets; audit of 44 collections spanning 1800+ finetuning text-to-text datasets documenting web and machine sources, licenses, creators and metadata; scripts filter by license constraints.","locator":"README intro","classification":"upstream_claim"},{"url":"https://api.github.com/repos/Data-Provenance-Initiative/Data-Provenance-Collection","claim":"Repo metadata: Apache-2.0, not archived, last push 2025-03-26.","locator":"GitHub API fields","classification":"sourced_fact"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"Apache-2.0 for the scripts.","hosting":"permitted","component":"code","license_id":"Apache-2.0","modification":"permitted","evidence_urls":["https://github.com/Data-Provenance-Initiative/Data-Provenance-Collection/blob/main/LICENSE"],"model_training":"unknown","redistribution":"permitted"},{"notes":"License terms of the compiled metadata and the legal-notice section were not read.","hosting":"unknown","component":"dataset","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/Data-Provenance-Initiative/Data-Provenance-Collection"],"model_training":"unknown","redistribution":"unknown"}],"attribution":{"origin":"research_agent","upstream_owner":"Data Provenance Initiative","upstream_url":"https://github.com/data-provenance-initiative/data-provenance-collection","imported_from":"content/seeds/research/curated/resources.jsonl#data-provenance-initiative--collection","import_batch_id":"l07-curated-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-curated-2026-10-17","original":{"id":"data-provenance-initiative--collection","name":"Data Provenance Initiative: Data Provenance Collection","tags":["dataset-licenses","audit","provenance","text","level:advanced"],"rights":[{"notes":"Apache-2.0 for the scripts.","hosting":"permitted","component":"code","license_id":"Apache-2.0","modification":"permitted","evidence_urls":["https://github.com/Data-Provenance-Initiative/Data-Provenance-Collection/blob/main/LICENSE"],"model_training":"unknown","redistribution":"permitted"},{"notes":"License terms of the compiled metadata and the legal-notice section were not read.","hosting":"unknown","component":"dataset","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/Data-Provenance-Initiative/Data-Provenance-Collection"],"model_training":"unknown","redistribution":"unknown"}],"archived":false,"evidence":[{"url":"https://github.com/Data-Provenance-Initiative/Data-Provenance-Collection","claim":"README: volunteer effort for transparency in training datasets; audit of 44 collections spanning 1800+ finetuning text-to-text datasets documenting web and machine sources, licenses, creators and metadata; scripts filter by license constraints.","locator":"README intro","classification":"upstream_claim"},{"url":"https://api.github.com/repos/Data-Provenance-Initiative/Data-Provenance-Collection","claim":"Repo metadata: Apache-2.0, not archived, last push 2025-03-26.","locator":"GitHub API fields","classification":"sourced_fact"}],"language":"Python","revision":{"ref":"main","pinned":false},"checked_on":"2026-10-17","usefulness":"Audit of 44 data collections (1,800+ text finetuning datasets) documenting sources, licenses and creators, with scripts to filter by self-reported license constraints. Method and data for license-aware dataset selection; text-focused, but the audit approach transfers to media datasets.","source_type":"dataset","category_ids":["T20","T16"],"source_owner":"Data Provenance Initiative","canonical_url":"https://github.com/Data-Provenance-Initiative/Data-Provenance-Collection","review_status":"reviewed","schema_version":"0.1","execution_status":"not_run","inspection_status":"metadata_checked","known_limitations":["Text datasets only; licenses are self-reported."],"upstream_updated_at":"2025-03-26T02:46:12Z","proposed_next_action":"inspect"},"collector":{"file":"research-results/_inbox/lane-d/T20.json","lane":"lane-d","branch":"worktree-agent-ad9adef6dabe5c9be","commit":"b0288e1","collector":"Claude Sonnet 5.5 (high), combined lane D (T15,T16,T17,T19,T20), founder-run","file_sha256":"5db4dd1f40b0a1c55905b427f043de7eb360dbf3184c022d67d89c1cf2216c04","merged_from":[],"original_id":"data-provenance-initiative--collection","review_reason":"L07 review 2026-10-17: lane lane-d accepted after automated metadata re-check and sample verification; see review-log.jsonl.","review_status":"reviewed","automated_flags":[]},"observed_on":"2026-10-17","original_id":"data-provenance-initiative--collection","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"Python","execution_status":"not_run","inspection_status":"metadata_checked","proposed_next_action":"inspect"},"source_schema":"resource-candidate/0.1","original_sha256":"6da71a44b0a69cd026b0892f85df3042d00ffc95f8a024057b22be44ca9e13de","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569GD9DRW911XJ6GRTM87HM","api_url":"https://veyrul.com/v1/records/src_01M569GD9DRW911XJ6GRTM87HM","created_at":"2026-10-18T01:20:05.923Z","updated_at":"2026-10-18T01:24:06.756Z","last_activity_at":"2026-10-18T01:24:06.756Z"}