{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GPXRIQ37JXQZHIIF3X4PBOQBCQ","short_pith_number":"pith:GPXRIQ37","canonical_record":{"source":{"id":"2108.02922","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-06T02:52:36Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"f0a3f4c55de45ce314dea33b4f6e0e7c61b761497c6ae52e8d722e0b39032550","abstract_canon_sha256":"f5a64a2b36007f19f5f15c36dfbb27134c08b5be6ec90d20f0a74243ce5a4bce"},"schema_version":"1.0"},"canonical_sha256":"33ef14437f4de193a105ddf8f0ba011416df277f5b2c2b20c156bf3f8b578ebd","source":{"kind":"arxiv","id":"2108.02922","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02922","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02922v2","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02922","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"pith_short_12","alias_value":"GPXRIQ37JXQZ","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"pith_short_16","alias_value":"GPXRIQ37JXQZHIIF","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"pith_short_8","alias_value":"GPXRIQ37","created_at":"2026-07-05T03:33:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GPXRIQ37JXQZHIIF3X4PBOQBCQ","target":"record","payload":{"canonical_record":{"source":{"id":"2108.02922","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-06T02:52:36Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"f0a3f4c55de45ce314dea33b4f6e0e7c61b761497c6ae52e8d722e0b39032550","abstract_canon_sha256":"f5a64a2b36007f19f5f15c36dfbb27134c08b5be6ec90d20f0a74243ce5a4bce"},"schema_version":"1.0"},"canonical_sha256":"33ef14437f4de193a105ddf8f0ba011416df277f5b2c2b20c156bf3f8b578ebd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:46.585446Z","signature_b64":"cxg9JJcenwT8zRAkO9w18f/dQq3CsW0666uW+g7hgr9LS1eERDXoYxc+SGfIRThcfeQ6sBrLzt+d0887Y2RiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33ef14437f4de193a105ddf8f0ba011416df277f5b2c2b20c156bf3f8b578ebd","last_reissued_at":"2026-07-05T03:33:46.585087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:46.585087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.02922","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:33:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BUmuyYMaJ4lBr15t68lnjmuQvC+NmPI/bNpOjtpI8cKa99AoZI7oer4rV0xNFCCulCXODIyg9ECI/0rDE1NzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:58:46.563192Z"},"content_sha256":"98df02541f21b2dc093c3aff7f087fb62a1bf4f99d4fa79d83c28b9f5afeaa1d","schema_version":"1.0","event_id":"sha256:98df02541f21b2dc093c3aff7f087fb62a1bf4f99d4fa79d83c28b9f5afeaa1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GPXRIQ37JXQZHIIF3X4PBOQBCQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"Arunesh Mathur, Arvind Narayanan, Kenny Peng","submitted_at":"2021-08-06T02:52:36Z","abstract_excerpt":"Machine learning datasets have elicited concerns about privacy, bias, and unethical applications, leading to the retraction of prominent datasets such as DukeMTMC, MS-Celeb-1M, and Tiny Images. In response, the machine learning community has called for higher ethical standards in dataset creation. To help inform these efforts, we studied three influential but ethically problematic face and person recognition datasets -- Labeled Faces in the Wild (LFW), MS-Celeb-1M, and DukeMTM -- by analyzing nearly 1000 papers that cite them. We found that the creation of derivative datasets and models, broad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02922","kind":"arxiv","version":2},"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/2108.02922/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:33:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XfTfNpsIpnrCHBb71gc/8ChbEm/F6F6L4sZhi6FfttJAdwta1l4q9oMnS0y5/GgOcpx8fBvayNwb9PTGRqXNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:58:46.563817Z"},"content_sha256":"f2ebb779235cbd2da1f57bb21a2ddc1d1a06488ee0affd40cc580590339b213f","schema_version":"1.0","event_id":"sha256:f2ebb779235cbd2da1f57bb21a2ddc1d1a06488ee0affd40cc580590339b213f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GPXRIQ37JXQZHIIF3X4PBOQBCQ/bundle.json","state_url":"https://pith.science/pith/GPXRIQ37JXQZHIIF3X4PBOQBCQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GPXRIQ37JXQZHIIF3X4PBOQBCQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T11:58:46Z","links":{"resolver":"https://pith.science/pith/GPXRIQ37JXQZHIIF3X4PBOQBCQ","bundle":"https://pith.science/pith/GPXRIQ37JXQZHIIF3X4PBOQBCQ/bundle.json","state":"https://pith.science/pith/GPXRIQ37JXQZHIIF3X4PBOQBCQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GPXRIQ37JXQZHIIF3X4PBOQBCQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GPXRIQ37JXQZHIIF3X4PBOQBCQ","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":"f5a64a2b36007f19f5f15c36dfbb27134c08b5be6ec90d20f0a74243ce5a4bce","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-06T02:52:36Z","title_canon_sha256":"f0a3f4c55de45ce314dea33b4f6e0e7c61b761497c6ae52e8d722e0b39032550"},"schema_version":"1.0","source":{"id":"2108.02922","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02922","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02922v2","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02922","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"pith_short_12","alias_value":"GPXRIQ37JXQZ","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"pith_short_16","alias_value":"GPXRIQ37JXQZHIIF","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"pith_short_8","alias_value":"GPXRIQ37","created_at":"2026-07-05T03:33:46Z"}],"graph_snapshots":[{"event_id":"sha256:f2ebb779235cbd2da1f57bb21a2ddc1d1a06488ee0affd40cc580590339b213f","target":"graph","created_at":"2026-07-05T03:33:46Z","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/2108.02922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning datasets have elicited concerns about privacy, bias, and unethical applications, leading to the retraction of prominent datasets such as DukeMTMC, MS-Celeb-1M, and Tiny Images. In response, the machine learning community has called for higher ethical standards in dataset creation. To help inform these efforts, we studied three influential but ethically problematic face and person recognition datasets -- Labeled Faces in the Wild (LFW), MS-Celeb-1M, and DukeMTM -- by analyzing nearly 1000 papers that cite them. We found that the creation of derivative datasets and models, broad","authors_text":"Arunesh Mathur, Arvind Narayanan, Kenny Peng","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-06T02:52:36Z","title":"Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02922","kind":"arxiv","version":2},"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":"sha256:98df02541f21b2dc093c3aff7f087fb62a1bf4f99d4fa79d83c28b9f5afeaa1d","target":"record","created_at":"2026-07-05T03:33:46Z","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":"f5a64a2b36007f19f5f15c36dfbb27134c08b5be6ec90d20f0a74243ce5a4bce","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-06T02:52:36Z","title_canon_sha256":"f0a3f4c55de45ce314dea33b4f6e0e7c61b761497c6ae52e8d722e0b39032550"},"schema_version":"1.0","source":{"id":"2108.02922","kind":"arxiv","version":2}},"canonical_sha256":"33ef14437f4de193a105ddf8f0ba011416df277f5b2c2b20c156bf3f8b578ebd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33ef14437f4de193a105ddf8f0ba011416df277f5b2c2b20c156bf3f8b578ebd","first_computed_at":"2026-07-05T03:33:46.585087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:46.585087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cxg9JJcenwT8zRAkO9w18f/dQq3CsW0666uW+g7hgr9LS1eERDXoYxc+SGfIRThcfeQ6sBrLzt+d0887Y2RiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:46.585446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.02922","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98df02541f21b2dc093c3aff7f087fb62a1bf4f99d4fa79d83c28b9f5afeaa1d","sha256:f2ebb779235cbd2da1f57bb21a2ddc1d1a06488ee0affd40cc580590339b213f"],"state_sha256":"db471cb711a83f35d2e2dda4411ba3aa156d0ef317a7704b972d1a4777b0c7e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WMaI08CJjvJeM01Ty6U9puz77TnPSp+ifHZDc+TZLgp1vmpIQq/QyWEOzJF435pDocKuV0Fm62H8Ggq1a9LtDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:58:46.569086Z","bundle_sha256":"0f291cd095c18f14b56de7caed52436946a55fcfdfcd38ea61889fcbdb7a79bc"}}