{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TB4RP6SMV4OODRDYRIT2234E37","short_pith_number":"pith:TB4RP6SM","canonical_record":{"source":{"id":"2104.00606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-01T16:37:01Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"7435069743660d1a99c394d8a3667adfa277692a75d65dcd3113f5c7493ac61a","abstract_canon_sha256":"c394950ba38a1237c6e4b409d74a484337c72493de7234ffd607ed47a30daaeb"},"schema_version":"1.0"},"canonical_sha256":"987917fa4caf1ce1c4788a27ad6f84dffbe3b9ae3ddbbd6fcea2d854352e53f0","source":{"kind":"arxiv","id":"2104.00606","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00606","created_at":"2026-07-05T03:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00606v2","created_at":"2026-07-05T03:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00606","created_at":"2026-07-05T03:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"TB4RP6SMV4OO","created_at":"2026-07-05T03:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"TB4RP6SMV4OODRDY","created_at":"2026-07-05T03:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"TB4RP6SM","created_at":"2026-07-05T03:12:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TB4RP6SMV4OODRDYRIT2234E37","target":"record","payload":{"canonical_record":{"source":{"id":"2104.00606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-01T16:37:01Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"7435069743660d1a99c394d8a3667adfa277692a75d65dcd3113f5c7493ac61a","abstract_canon_sha256":"c394950ba38a1237c6e4b409d74a484337c72493de7234ffd607ed47a30daaeb"},"schema_version":"1.0"},"canonical_sha256":"987917fa4caf1ce1c4788a27ad6f84dffbe3b9ae3ddbbd6fcea2d854352e53f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:27.313608Z","signature_b64":"S1B2az4QkFk65hx/3CtnU3tSkPrhAKOPKagWAcr66A68awYsp77pZqf1Nzf7toGpMp25eL1nhlXWQThPSpe0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"987917fa4caf1ce1c4788a27ad6f84dffbe3b9ae3ddbbd6fcea2d854352e53f0","last_reissued_at":"2026-07-05T03:12:27.313202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:27.313202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.00606","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":"2026-07-05T03:12:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WoFZ1F+7Ek4rO0hMtwn87IwjulAHcIVnJQ9RQLr05z8H6vx74KUtZWwxlV9xKvHdl5rpEa2Yfk2cAPALzV76AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:50:54.392668Z"},"content_sha256":"4fabc78e3914b3f376042246007dcd4fbfdd34dce4744a0e6f10542edca018e4","schema_version":"1.0","event_id":"sha256:4fabc78e3914b3f376042246007dcd4fbfdd34dce4744a0e6f10542edca018e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TB4RP6SMV4OODRDYRIT2234E37","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model Selection's Disparate Impact in Real-World Deep Learning Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"A. Feder Cooper, Chris De Sa, Jessica Zosa Forde, Kweku Kwegyir-Aggrey, Michael Littman","submitted_at":"2021-04-01T16:37:01Z","abstract_excerpt":"Algorithmic fairness has emphasized the role of biased data in automated decision outcomes. Recently, there has been a shift in attention to sources of bias that implicate fairness in other stages in the ML pipeline. We contend that one source of such bias, human preferences in model selection, remains under-explored in terms of its role in disparate impact across demographic groups. Using a deep learning model trained on real-world medical imaging data, we verify our claim empirically and argue that choice of metric for model comparison, especially those that do not take variability into acco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00606","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/2104.00606/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":"2026-07-05T03:12:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jAdgBFEIm/sNG6Depg+BRE7EvwNEhEe/zhkiAWaauOg+Cdjv7NTr8PKHuS9PlFROT+fEzEem4jGbW6RbXeBnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:50:54.395331Z"},"content_sha256":"33d913fd448460f716c2f1bb4716f7acf9a26360a23156bd16ed9504a0b172be","schema_version":"1.0","event_id":"sha256:33d913fd448460f716c2f1bb4716f7acf9a26360a23156bd16ed9504a0b172be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TB4RP6SMV4OODRDYRIT2234E37/bundle.json","state_url":"https://pith.science/pith/TB4RP6SMV4OODRDYRIT2234E37/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TB4RP6SMV4OODRDYRIT2234E37/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":"2026-08-11T21:50:54Z","links":{"resolver":"https://pith.science/pith/TB4RP6SMV4OODRDYRIT2234E37","bundle":"https://pith.science/pith/TB4RP6SMV4OODRDYRIT2234E37/bundle.json","state":"https://pith.science/pith/TB4RP6SMV4OODRDYRIT2234E37/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TB4RP6SMV4OODRDYRIT2234E37/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TB4RP6SMV4OODRDYRIT2234E37","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":"c394950ba38a1237c6e4b409d74a484337c72493de7234ffd607ed47a30daaeb","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-01T16:37:01Z","title_canon_sha256":"7435069743660d1a99c394d8a3667adfa277692a75d65dcd3113f5c7493ac61a"},"schema_version":"1.0","source":{"id":"2104.00606","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00606","created_at":"2026-07-05T03:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00606v2","created_at":"2026-07-05T03:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00606","created_at":"2026-07-05T03:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"TB4RP6SMV4OO","created_at":"2026-07-05T03:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"TB4RP6SMV4OODRDY","created_at":"2026-07-05T03:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"TB4RP6SM","created_at":"2026-07-05T03:12:27Z"}],"graph_snapshots":[{"event_id":"sha256:33d913fd448460f716c2f1bb4716f7acf9a26360a23156bd16ed9504a0b172be","target":"graph","created_at":"2026-07-05T03:12:27Z","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/2104.00606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Algorithmic fairness has emphasized the role of biased data in automated decision outcomes. Recently, there has been a shift in attention to sources of bias that implicate fairness in other stages in the ML pipeline. We contend that one source of such bias, human preferences in model selection, remains under-explored in terms of its role in disparate impact across demographic groups. Using a deep learning model trained on real-world medical imaging data, we verify our claim empirically and argue that choice of metric for model comparison, especially those that do not take variability into acco","authors_text":"A. Feder Cooper, Chris De Sa, Jessica Zosa Forde, Kweku Kwegyir-Aggrey, Michael Littman","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-01T16:37:01Z","title":"Model Selection's Disparate Impact in Real-World Deep Learning Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00606","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":"sha256:4fabc78e3914b3f376042246007dcd4fbfdd34dce4744a0e6f10542edca018e4","target":"record","created_at":"2026-07-05T03:12:27Z","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":"c394950ba38a1237c6e4b409d74a484337c72493de7234ffd607ed47a30daaeb","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-01T16:37:01Z","title_canon_sha256":"7435069743660d1a99c394d8a3667adfa277692a75d65dcd3113f5c7493ac61a"},"schema_version":"1.0","source":{"id":"2104.00606","kind":"arxiv","version":2}},"canonical_sha256":"987917fa4caf1ce1c4788a27ad6f84dffbe3b9ae3ddbbd6fcea2d854352e53f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"987917fa4caf1ce1c4788a27ad6f84dffbe3b9ae3ddbbd6fcea2d854352e53f0","first_computed_at":"2026-07-05T03:12:27.313202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:27.313202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S1B2az4QkFk65hx/3CtnU3tSkPrhAKOPKagWAcr66A68awYsp77pZqf1Nzf7toGpMp25eL1nhlXWQThPSpe0DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:27.313608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00606","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fabc78e3914b3f376042246007dcd4fbfdd34dce4744a0e6f10542edca018e4","sha256:33d913fd448460f716c2f1bb4716f7acf9a26360a23156bd16ed9504a0b172be"],"state_sha256":"773ed087a6daed59f75d7218fcc30a2bac43c48bd937ac47c22c1041a50c54da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gWcStJlaPrVRIuMQLGboWkq01y7ad3sVLna2vhELQit9dDn7tw/+LTEMHz7p7vl54b3v1ktFOSSoEO6D/qC/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:50:54.439898Z","bundle_sha256":"339e0aa60b1d7a00d4efe8c8f6ff1b6ca2f2b2be6f74181caaf935e52b6f67e5"}}