{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BQCZYPAUQ5PHSVRSZWB4UHJXJF","short_pith_number":"pith:BQCZYPAU","canonical_record":{"source":{"id":"2012.05345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T22:13:13Z","cross_cats_sorted":[],"title_canon_sha256":"93b1c7636e3870436ec568fc89290e2f6b4262ecd481b649da442d44d4b6412a","abstract_canon_sha256":"9193631e57944b80de9049cfe3f9180b44b30bf6e9fff1e35164fa2f0ada1f7c"},"schema_version":"1.0"},"canonical_sha256":"0c059c3c14875e795632cd83ca1d3749773386fadd1e7b208a76ec62635c8b2c","source":{"kind":"arxiv","id":"2012.05345","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05345","created_at":"2026-07-05T03:31:23Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05345v1","created_at":"2026-07-05T03:31:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05345","created_at":"2026-07-05T03:31:23Z"},{"alias_kind":"pith_short_12","alias_value":"BQCZYPAUQ5PH","created_at":"2026-07-05T03:31:23Z"},{"alias_kind":"pith_short_16","alias_value":"BQCZYPAUQ5PHSVRS","created_at":"2026-07-05T03:31:23Z"},{"alias_kind":"pith_short_8","alias_value":"BQCZYPAU","created_at":"2026-07-05T03:31:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BQCZYPAUQ5PHSVRSZWB4UHJXJF","target":"record","payload":{"canonical_record":{"source":{"id":"2012.05345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T22:13:13Z","cross_cats_sorted":[],"title_canon_sha256":"93b1c7636e3870436ec568fc89290e2f6b4262ecd481b649da442d44d4b6412a","abstract_canon_sha256":"9193631e57944b80de9049cfe3f9180b44b30bf6e9fff1e35164fa2f0ada1f7c"},"schema_version":"1.0"},"canonical_sha256":"0c059c3c14875e795632cd83ca1d3749773386fadd1e7b208a76ec62635c8b2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:23.754283Z","signature_b64":"tvK84el7TdJYl8GAIY8/ucMdl11KX3rPyaKZs1l+JyPnR1ORsQRPO1OoMl/HSwXBHeJWQTSpDBfEKxPPSlunDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c059c3c14875e795632cd83ca1d3749773386fadd1e7b208a76ec62635c8b2c","last_reissued_at":"2026-07-05T03:31:23.753866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:23.753866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.05345","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:31:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Faqdb+8mXpv327Qm2nlbdkPSSlj3PunbMrYLEQTDLm/1W/s6Jt3FlaiJi6T829rjxNHG+Knt1SEB77qnYrciCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:57:47.975962Z"},"content_sha256":"479b52cf8fdae85f838ee82da944afd7172fdb259654fbe4eec2b1233d5d8994","schema_version":"1.0","event_id":"sha256:479b52cf8fdae85f838ee82da944afd7172fdb259654fbe4eec2b1233d5d8994"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BQCZYPAUQ5PHSVRSZWB4UHJXJF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex Hanna, Amandalynne Paullada, Emily Denton, Emily M. Bender, Inioluwa Deborah Raji","submitted_at":"2020-12-09T22:13:13Z","abstract_excerpt":"Datasets have played a foundational role in the advancement of machine learning research. They form the basis for the models we design and deploy, as well as our primary medium for benchmarking and evaluation. Furthermore, the ways in which we collect, construct and share these datasets inform the kinds of problems the field pursues and the methods explored in algorithm development. However, recent work from a breadth of perspectives has revealed the limitations of predominant practices in dataset collection and use. In this paper, we survey the many concerns raised about the way we collect an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05345","kind":"arxiv","version":1},"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/2012.05345/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":"2026-07-05T03:31:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bTUIUM/tWFk9cvy5ilHb2AuPmZihLFESKpchiDYMH3PfI6E91TxtKIqRb1y8IpSlLjrP8hIWxy+OyneAZddkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:57:47.976955Z"},"content_sha256":"f4ef5f77ad15c8aa1f428c4505a2feb3ec2766f03d9aa99b5a40b77ea1b53d14","schema_version":"1.0","event_id":"sha256:f4ef5f77ad15c8aa1f428c4505a2feb3ec2766f03d9aa99b5a40b77ea1b53d14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BQCZYPAUQ5PHSVRSZWB4UHJXJF/bundle.json","state_url":"https://pith.science/pith/BQCZYPAUQ5PHSVRSZWB4UHJXJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BQCZYPAUQ5PHSVRSZWB4UHJXJF/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":"2026-08-11T14:57:47Z","links":{"resolver":"https://pith.science/pith/BQCZYPAUQ5PHSVRSZWB4UHJXJF","bundle":"https://pith.science/pith/BQCZYPAUQ5PHSVRSZWB4UHJXJF/bundle.json","state":"https://pith.science/pith/BQCZYPAUQ5PHSVRSZWB4UHJXJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BQCZYPAUQ5PHSVRSZWB4UHJXJF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BQCZYPAUQ5PHSVRSZWB4UHJXJF","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":"9193631e57944b80de9049cfe3f9180b44b30bf6e9fff1e35164fa2f0ada1f7c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T22:13:13Z","title_canon_sha256":"93b1c7636e3870436ec568fc89290e2f6b4262ecd481b649da442d44d4b6412a"},"schema_version":"1.0","source":{"id":"2012.05345","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05345","created_at":"2026-07-05T03:31:23Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05345v1","created_at":"2026-07-05T03:31:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05345","created_at":"2026-07-05T03:31:23Z"},{"alias_kind":"pith_short_12","alias_value":"BQCZYPAUQ5PH","created_at":"2026-07-05T03:31:23Z"},{"alias_kind":"pith_short_16","alias_value":"BQCZYPAUQ5PHSVRS","created_at":"2026-07-05T03:31:23Z"},{"alias_kind":"pith_short_8","alias_value":"BQCZYPAU","created_at":"2026-07-05T03:31:23Z"}],"graph_snapshots":[{"event_id":"sha256:f4ef5f77ad15c8aa1f428c4505a2feb3ec2766f03d9aa99b5a40b77ea1b53d14","target":"graph","created_at":"2026-07-05T03:31:23Z","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/2012.05345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Datasets have played a foundational role in the advancement of machine learning research. They form the basis for the models we design and deploy, as well as our primary medium for benchmarking and evaluation. Furthermore, the ways in which we collect, construct and share these datasets inform the kinds of problems the field pursues and the methods explored in algorithm development. However, recent work from a breadth of perspectives has revealed the limitations of predominant practices in dataset collection and use. In this paper, we survey the many concerns raised about the way we collect an","authors_text":"Alex Hanna, Amandalynne Paullada, Emily Denton, Emily M. Bender, Inioluwa Deborah Raji","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T22:13:13Z","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05345","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":"sha256:479b52cf8fdae85f838ee82da944afd7172fdb259654fbe4eec2b1233d5d8994","target":"record","created_at":"2026-07-05T03:31:23Z","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":"9193631e57944b80de9049cfe3f9180b44b30bf6e9fff1e35164fa2f0ada1f7c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T22:13:13Z","title_canon_sha256":"93b1c7636e3870436ec568fc89290e2f6b4262ecd481b649da442d44d4b6412a"},"schema_version":"1.0","source":{"id":"2012.05345","kind":"arxiv","version":1}},"canonical_sha256":"0c059c3c14875e795632cd83ca1d3749773386fadd1e7b208a76ec62635c8b2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c059c3c14875e795632cd83ca1d3749773386fadd1e7b208a76ec62635c8b2c","first_computed_at":"2026-07-05T03:31:23.753866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:31:23.753866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tvK84el7TdJYl8GAIY8/ucMdl11KX3rPyaKZs1l+JyPnR1ORsQRPO1OoMl/HSwXBHeJWQTSpDBfEKxPPSlunDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:31:23.754283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.05345","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:479b52cf8fdae85f838ee82da944afd7172fdb259654fbe4eec2b1233d5d8994","sha256:f4ef5f77ad15c8aa1f428c4505a2feb3ec2766f03d9aa99b5a40b77ea1b53d14"],"state_sha256":"61a96fba6de36e50667b752a9b9781e6e8493c4352f06dd9c248ac9f1bb55b3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vmv2bHsJY4iqTfMDFVYAq5ErhElQ8p7Bf0937mEZfDC/DfTBrDdSGdQzBAbi+ng+LatnPAsglDbTExRyCtcwCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:57:47.983268Z","bundle_sha256":"b53f9ec993afdc5afef18a83942835fc2b7fa5953e324841b69c07f18efc6538"}}