{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:G2YVBYRHFGD6SE2CZPBWAWQKUU","short_pith_number":"pith:G2YVBYRH","canonical_record":{"source":{"id":"2012.10986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-20T18:09:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c7a98aaa61a1b33e7b01edf60411883d08b47bd2b4057b3dfc1275fc146b3b8","abstract_canon_sha256":"c4034175ee6619991b752b0e100e8f75b8f24c00880d12b8187736b8dfa20fea"},"schema_version":"1.0"},"canonical_sha256":"36b150e2272987e91342cbc3605a0aa50b67c717f9d84c6c9632c7ff50c339b1","source":{"kind":"arxiv","id":"2012.10986","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.10986","created_at":"2026-07-05T02:00:57Z"},{"alias_kind":"arxiv_version","alias_value":"2012.10986v1","created_at":"2026-07-05T02:00:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10986","created_at":"2026-07-05T02:00:57Z"},{"alias_kind":"pith_short_12","alias_value":"G2YVBYRHFGD6","created_at":"2026-07-05T02:00:57Z"},{"alias_kind":"pith_short_16","alias_value":"G2YVBYRHFGD6SE2C","created_at":"2026-07-05T02:00:57Z"},{"alias_kind":"pith_short_8","alias_value":"G2YVBYRH","created_at":"2026-07-05T02:00:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:G2YVBYRHFGD6SE2CZPBWAWQKUU","target":"record","payload":{"canonical_record":{"source":{"id":"2012.10986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-20T18:09:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c7a98aaa61a1b33e7b01edf60411883d08b47bd2b4057b3dfc1275fc146b3b8","abstract_canon_sha256":"c4034175ee6619991b752b0e100e8f75b8f24c00880d12b8187736b8dfa20fea"},"schema_version":"1.0"},"canonical_sha256":"36b150e2272987e91342cbc3605a0aa50b67c717f9d84c6c9632c7ff50c339b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:57.364076Z","signature_b64":"Zgrx3Qw5GPo01FHfcX198dRvGmnSOtAtIlHlcZt3ySvApcEV4cOo80LfICT/tpsPkiT2Oz0VyNsI1L8HOfy3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36b150e2272987e91342cbc3605a0aa50b67c717f9d84c6c9632c7ff50c339b1","last_reissued_at":"2026-07-05T02:00:57.363721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:57.363721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.10986","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":"2026-07-05T02:00:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Fintoidb152ZNzgqzzmQcwsR+HPAsDYcNeb/h0GxZ8MGsyPtCzQdouGVhaV/KUq1XLLnKEurCXKkEK6J8E1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:40:29.769615Z"},"content_sha256":"25e19e18d856a6aa81dae757009deca5de950abb5c545923dae3a43d7eb70606","schema_version":"1.0","event_id":"sha256:25e19e18d856a6aa81dae757009deca5de950abb5c545923dae3a43d7eb70606"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:G2YVBYRHFGD6SE2CZPBWAWQKUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Biased Models Have Biased Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Jain, Joydeep Ghosh, Manish Ravula","submitted_at":"2020-12-20T18:09:45Z","abstract_excerpt":"We study fairness in Machine Learning (FairML) through the lens of attribute-based explanations generated for machine learning models. Our hypothesis is: Biased Models have Biased Explanations. To establish that, we first translate existing statistical notions of group fairness and define these notions in terms of explanations given by the model. Then, we propose a novel way of detecting (un)fairness for any black box model. We further look at post-processing techniques for fairness and reason how explanations can be used to make a bias mitigation technique more individually fair. We also intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10986","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/2012.10986/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":"2026-07-05T02:00:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZpDF7cq9SX+d8QyVxLi8kJxM7vqwRKHdJiLD64injn+B3E64N4vriglN9dTrKfUAWMbADy1NBcs85XDo3LYNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:40:29.770215Z"},"content_sha256":"9b497e758fcd48aa5b054a6ccd190582ec239e0cd74c6d3b5da6341f1a61765f","schema_version":"1.0","event_id":"sha256:9b497e758fcd48aa5b054a6ccd190582ec239e0cd74c6d3b5da6341f1a61765f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G2YVBYRHFGD6SE2CZPBWAWQKUU/bundle.json","state_url":"https://pith.science/pith/G2YVBYRHFGD6SE2CZPBWAWQKUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G2YVBYRHFGD6SE2CZPBWAWQKUU/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":"2026-08-10T00:40:29Z","links":{"resolver":"https://pith.science/pith/G2YVBYRHFGD6SE2CZPBWAWQKUU","bundle":"https://pith.science/pith/G2YVBYRHFGD6SE2CZPBWAWQKUU/bundle.json","state":"https://pith.science/pith/G2YVBYRHFGD6SE2CZPBWAWQKUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G2YVBYRHFGD6SE2CZPBWAWQKUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G2YVBYRHFGD6SE2CZPBWAWQKUU","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":"c4034175ee6619991b752b0e100e8f75b8f24c00880d12b8187736b8dfa20fea","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-20T18:09:45Z","title_canon_sha256":"8c7a98aaa61a1b33e7b01edf60411883d08b47bd2b4057b3dfc1275fc146b3b8"},"schema_version":"1.0","source":{"id":"2012.10986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.10986","created_at":"2026-07-05T02:00:57Z"},{"alias_kind":"arxiv_version","alias_value":"2012.10986v1","created_at":"2026-07-05T02:00:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10986","created_at":"2026-07-05T02:00:57Z"},{"alias_kind":"pith_short_12","alias_value":"G2YVBYRHFGD6","created_at":"2026-07-05T02:00:57Z"},{"alias_kind":"pith_short_16","alias_value":"G2YVBYRHFGD6SE2C","created_at":"2026-07-05T02:00:57Z"},{"alias_kind":"pith_short_8","alias_value":"G2YVBYRH","created_at":"2026-07-05T02:00:57Z"}],"graph_snapshots":[{"event_id":"sha256:9b497e758fcd48aa5b054a6ccd190582ec239e0cd74c6d3b5da6341f1a61765f","target":"graph","created_at":"2026-07-05T02:00:57Z","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/2012.10986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study fairness in Machine Learning (FairML) through the lens of attribute-based explanations generated for machine learning models. Our hypothesis is: Biased Models have Biased Explanations. To establish that, we first translate existing statistical notions of group fairness and define these notions in terms of explanations given by the model. Then, we propose a novel way of detecting (un)fairness for any black box model. We further look at post-processing techniques for fairness and reason how explanations can be used to make a bias mitigation technique more individually fair. We also intr","authors_text":"Aditya Jain, Joydeep Ghosh, Manish Ravula","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-20T18:09:45Z","title":"Biased Models Have Biased Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10986","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":"sha256:25e19e18d856a6aa81dae757009deca5de950abb5c545923dae3a43d7eb70606","target":"record","created_at":"2026-07-05T02:00:57Z","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":"c4034175ee6619991b752b0e100e8f75b8f24c00880d12b8187736b8dfa20fea","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-20T18:09:45Z","title_canon_sha256":"8c7a98aaa61a1b33e7b01edf60411883d08b47bd2b4057b3dfc1275fc146b3b8"},"schema_version":"1.0","source":{"id":"2012.10986","kind":"arxiv","version":1}},"canonical_sha256":"36b150e2272987e91342cbc3605a0aa50b67c717f9d84c6c9632c7ff50c339b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36b150e2272987e91342cbc3605a0aa50b67c717f9d84c6c9632c7ff50c339b1","first_computed_at":"2026-07-05T02:00:57.363721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:57.363721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zgrx3Qw5GPo01FHfcX198dRvGmnSOtAtIlHlcZt3ySvApcEV4cOo80LfICT/tpsPkiT2Oz0VyNsI1L8HOfy3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:57.364076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.10986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25e19e18d856a6aa81dae757009deca5de950abb5c545923dae3a43d7eb70606","sha256:9b497e758fcd48aa5b054a6ccd190582ec239e0cd74c6d3b5da6341f1a61765f"],"state_sha256":"4a4ff444152e4cf0af6e1eec3c0bac8a2164d0b336d0a256a5bc27b385c6368e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0j2LoTcxXOQ7W9ooqTCYdV0aUhD5bWBZ3ScZm60EDv4QwPyOYP102GiUHumOf7WcBa/F9INZ1p6TueDh5yesAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:40:29.775021Z","bundle_sha256":"cbdf54f77e59dabf0d17dfd49e1717a7906d02840919241ef6425b47166b46f7"}}