{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RG2SMUV366CTML6VS3S37F7YQT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ad3d408009a438f39a685323849638490fe447914211acc5d06964029fe16746","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-07T03:59:22Z","title_canon_sha256":"280ee1a76bd09cc698572df702c8308668c457688c64e114b4091a2191b615ab"},"schema_version":"1.0","source":{"id":"2109.02846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02846","created_at":"2026-07-05T03:12:20Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02846v1","created_at":"2026-07-05T03:12:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02846","created_at":"2026-07-05T03:12:20Z"},{"alias_kind":"pith_short_12","alias_value":"RG2SMUV366CT","created_at":"2026-07-05T03:12:20Z"},{"alias_kind":"pith_short_16","alias_value":"RG2SMUV366CTML6V","created_at":"2026-07-05T03:12:20Z"},{"alias_kind":"pith_short_8","alias_value":"RG2SMUV3","created_at":"2026-07-05T03:12:20Z"}],"graph_snapshots":[{"event_id":"sha256:1b7ba4248a1afd1b723fa0ec880000c91acfccfd94d96f744230d135f4624a62","target":"graph","created_at":"2026-07-05T03:12:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.02846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The scale, variety, and quantity of publicly-available NLP datasets has grown rapidly as researchers propose new tasks, larger models, and novel benchmarks. Datasets is a community library for contemporary NLP designed to support this ecosystem. Datasets aims to standardize end-user interfaces, versioning, and documentation, while providing a lightweight front-end that behaves similarly for small datasets as for internet-scale corpora. The design of the library incorporates a distributed, community-driven approach to adding datasets and documenting usage. After a year of development, the libra","authors_text":"Abhishek Thakur, Albert Villanova del Moral, Alexander M. Rush, Angelina McMillan-Major, Bhavitvya Malik, Canwen Xu, Cl\\'ement Delangue, Fran\\c{c}ois Lagunas, Gunjan Chhablani, Joe Davison, Julien Chaumond, Julien Plu, Lewis Tunstall, Lysandre Debut, Mariama Drame, Mario \\v{S}a\\v{s}ko, Nicolas Patry, Patrick von Platen, Philipp Schmid, Pierric Cistac, Quentin Lhoest, Simon Brandeis, Stas Bekman, Suraj Patil, Sylvain Gugger, Teven Le Scao, Th\\'eo Matussi\\`ere, Thibault Goehringer, Thomas Wolf, Victor Mustar, Victor Sanh, Yacine Jernite","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-07T03:59:22Z","title":"Datasets: A Community Library for Natural Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02846","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9c17543ddbf26bbf9d089c3aef5ce16b390631340a1481def8f522f0468a9731","target":"record","created_at":"2026-07-05T03:12:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ad3d408009a438f39a685323849638490fe447914211acc5d06964029fe16746","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-07T03:59:22Z","title_canon_sha256":"280ee1a76bd09cc698572df702c8308668c457688c64e114b4091a2191b615ab"},"schema_version":"1.0","source":{"id":"2109.02846","kind":"arxiv","version":1}},"canonical_sha256":"89b52652bbf785362fd596e5bf97f884e9f3de492ea172487a16fdf154041c81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89b52652bbf785362fd596e5bf97f884e9f3de492ea172487a16fdf154041c81","first_computed_at":"2026-07-05T03:12:20.263368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:20.263368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AEpmu86oIX729fnnU456LYlnaMhC8uQ1u+IxwN9oRAqW6tYVsBI7YwAZ6HoMw9IA7clGaoibphO684JibiciDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:20.263866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.02846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c17543ddbf26bbf9d089c3aef5ce16b390631340a1481def8f522f0468a9731","sha256:1b7ba4248a1afd1b723fa0ec880000c91acfccfd94d96f744230d135f4624a62"],"state_sha256":"e44cba7d28b511e1c5fd5e9f99154648be29966673799a848bfab2bac68ce5e3"}