{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AUT7TMCQHUHPTD2PSRQX35QCD7","short_pith_number":"pith:AUT7TMCQ","schema_version":"1.0","canonical_sha256":"0527f9b0503d0ef98f4f94617df6021fd62cbe862113978c3f242d60f7434480","source":{"kind":"arxiv","id":"1803.09010","version":8},"attestation_state":"computed","paper":{"title":"Datasheets for Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Briana Vecchione, Hal Daum\\'e III, Hanna Wallach, Jamie Morgenstern, Jennifer Wortman Vaughan, Kate Crawford, Timnit Gebru","submitted_at":"2018-03-23T23:22:18Z","abstract_excerpt":"The machine learning community currently has no standardized process for documenting datasets, which can lead to severe consequences in high-stakes domains. To address this gap, we propose datasheets for datasets. In the electronics industry, every component, no matter how simple or complex, is accompanied with a datasheet that describes its operating characteristics, test results, recommended uses, and other information. By analogy, we propose that every dataset be accompanied with a datasheet that documents its motivation, composition, collection process, recommended uses, and so on. Datashe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1803.09010","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-03-23T23:22:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c70165eb2dc7031fdfab269b24a7f31cd22cda947800b526e9989ccdc99ccce4","abstract_canon_sha256":"0a6c5c5f4ee77749811e0f6220c7d5cbc234e6cad58bef1f4727d01b40075239"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:50.435405Z","signature_b64":"8/PpIFjDb6orRimMoB/ctHLMKiGD+JVk63GgqJ28XlN5JHYLuLoPtf6lrMaNbFEYQ23Gr7p/aloQI1PH35vMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0527f9b0503d0ef98f4f94617df6021fd62cbe862113978c3f242d60f7434480","last_reissued_at":"2026-07-05T03:36:50.434976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:50.434976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Datasheets for Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Briana Vecchione, Hal Daum\\'e III, Hanna Wallach, Jamie Morgenstern, Jennifer Wortman Vaughan, Kate Crawford, Timnit Gebru","submitted_at":"2018-03-23T23:22:18Z","abstract_excerpt":"The machine learning community currently has no standardized process for documenting datasets, which can lead to severe consequences in high-stakes domains. To address this gap, we propose datasheets for datasets. In the electronics industry, every component, no matter how simple or complex, is accompanied with a datasheet that describes its operating characteristics, test results, recommended uses, and other information. By analogy, we propose that every dataset be accompanied with a datasheet that documents its motivation, composition, collection process, recommended uses, and so on. Datashe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09010","kind":"arxiv","version":8},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1803.09010/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1803.09010","created_at":"2026-07-05T03:36:50.435044+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.09010v8","created_at":"2026-07-05T03:36:50.435044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09010","created_at":"2026-07-05T03:36:50.435044+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUT7TMCQHUHP","created_at":"2026-07-05T03:36:50.435044+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUT7TMCQHUHPTD2P","created_at":"2026-07-05T03:36:50.435044+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUT7TMCQ","created_at":"2026-07-05T03:36:50.435044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":31,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07676","citing_title":"SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11562","citing_title":"GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31272","citing_title":"The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25038","citing_title":"TRACE: A taxonomy-grounded synthetic dataset for teaching-program generation and session interpretation in Applied Behavior Analysis","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26734","citing_title":"CIRCLED: A Multi-turn CIR Dataset with Consistent Dialogues across Domains","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00871","citing_title":"Benchmarks for Vision-Language Models in Urban Perception Should Be Reliability-Aware and Negotiated","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07628","citing_title":"Frankenstein in the Pipeline: Computational Epistemicide in Facial Recognition","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09881","citing_title":"Toward Calibrated, Fair, and accurate Deepfake Detection","ref_index":247,"is_internal_anchor":false},{"citing_arxiv_id":"1907.01463","citing_title":"Reproducibility in Machine Learning for Health","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23170","citing_title":"Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2103.11474","citing_title":"#PraCegoVer: A Large Dataset for Image Captioning in Portuguese","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2107.06499","citing_title":"Deduplicating Training Data Makes Language Models Better","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2008.02275","citing_title":"Aligning AI With Shared Human Values","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12824","citing_title":"Mechanism Plausibility in Generative Agent-Based Modeling","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16538","citing_title":"LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15956","citing_title":"TeraGram: A Structured Longitudinal Dataset of the Telegram Messenger","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00033","citing_title":"Mapping the Stochastic Penal Colony","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10995","citing_title":"A Human-Centric Framework for Data Attribution in Large Language Models","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12824","citing_title":"Mechanism Plausibility in Generative Agent-Based Modeling","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11345","citing_title":"Evaluating Structured Documentation as a Tool for Reflexivity in Dataset Development","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28053","citing_title":"To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2205.11487","citing_title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09636","citing_title":"PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06856","citing_title":"Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility","ref_index":265,"is_internal_anchor":false},{"citing_arxiv_id":"2209.07858","citing_title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AUT7TMCQHUHPTD2PSRQX35QCD7","json":"https://pith.science/pith/AUT7TMCQHUHPTD2PSRQX35QCD7.json","graph_json":"https://pith.science/api/pith-number/AUT7TMCQHUHPTD2PSRQX35QCD7/graph.json","events_json":"https://pith.science/api/pith-number/AUT7TMCQHUHPTD2PSRQX35QCD7/events.json","paper":"https://pith.science/paper/AUT7TMCQ"},"agent_actions":{"view_html":"https://pith.science/pith/AUT7TMCQHUHPTD2PSRQX35QCD7","download_json":"https://pith.science/pith/AUT7TMCQHUHPTD2PSRQX35QCD7.json","view_paper":"https://pith.science/paper/AUT7TMCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.09010&json=true","fetch_graph":"https://pith.science/api/pith-number/AUT7TMCQHUHPTD2PSRQX35QCD7/graph.json","fetch_events":"https://pith.science/api/pith-number/AUT7TMCQHUHPTD2PSRQX35QCD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUT7TMCQHUHPTD2PSRQX35QCD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUT7TMCQHUHPTD2PSRQX35QCD7/action/storage_attestation","attest_author":"https://pith.science/pith/AUT7TMCQHUHPTD2PSRQX35QCD7/action/author_attestation","sign_citation":"https://pith.science/pith/AUT7TMCQHUHPTD2PSRQX35QCD7/action/citation_signature","submit_replication":"https://pith.science/pith/AUT7TMCQHUHPTD2PSRQX35QCD7/action/replication_record"}},"created_at":"2026-07-05T03:36:50.435044+00:00","updated_at":"2026-07-05T03:36:50.435044+00:00"}