{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3WXXSK5ITKWSFNSD2FEEBLZNIF","short_pith_number":"pith:3WXXSK5I","canonical_record":{"source":{"id":"2204.09591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-06T18:12:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ef52372f2dcef6ef62c171dd35b9e15ed30ac7c83de190c0846389b798bdb94","abstract_canon_sha256":"0ca362ee033f4f9d1603335c7735ba3717c12793dfa684733b5afc81664452fd"},"schema_version":"1.0"},"canonical_sha256":"ddaf792ba89aad22b643d14840af2d4151ee4ad0dd6c44371135199ec276ffaa","source":{"kind":"arxiv","id":"2204.09591","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.09591","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2204.09591v1","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09591","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"3WXXSK5ITKWS","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"3WXXSK5ITKWSFNSD","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"3WXXSK5I","created_at":"2026-07-05T04:16:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3WXXSK5ITKWSFNSD2FEEBLZNIF","target":"record","payload":{"canonical_record":{"source":{"id":"2204.09591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-06T18:12:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ef52372f2dcef6ef62c171dd35b9e15ed30ac7c83de190c0846389b798bdb94","abstract_canon_sha256":"0ca362ee033f4f9d1603335c7735ba3717c12793dfa684733b5afc81664452fd"},"schema_version":"1.0"},"canonical_sha256":"ddaf792ba89aad22b643d14840af2d4151ee4ad0dd6c44371135199ec276ffaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:31.973737Z","signature_b64":"5cQKt6VRXh5JlW9rElDPAi9OwJ8KQSoNPO57eKuNwJneVO/oLeLQIt1f89jjnYAx0UcB6KM5Av4SsUCfRX6bDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddaf792ba89aad22b643d14840af2d4151ee4ad0dd6c44371135199ec276ffaa","last_reissued_at":"2026-07-05T04:16:31.973199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:31.973199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.09591","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":"2026-07-05T04:16:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ROJGFSA6kw+yqFgBxPhMuzp6hytar7xuD4RRzWUfUV2qefcjpoyg9+ECZzX89wXJ1wDEROJBQAH53RtZ5EnVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:10:54.221039Z"},"content_sha256":"ea3046db9ef1983f594f3cb3928a730b8c4df9ec51e5bb5001d558201158633b","schema_version":"1.0","event_id":"sha256:ea3046db9ef1983f594f3cb3928a730b8c4df9ec51e5bb5001d558201158633b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3WXXSK5ITKWSFNSD2FEEBLZNIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Bias and Fairness in Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Rajas Bansal","submitted_at":"2022-03-06T18:12:30Z","abstract_excerpt":"As NLP models become more integrated with the everyday lives of people, it becomes important to examine the social effect that the usage of these systems has. While these models understand language and have increased accuracy on difficult downstream tasks, there is evidence that these models amplify gender, racial and cultural stereotypes and lead to a vicious cycle in many settings. In this survey, we analyze the origins of biases, the definitions of fairness, and how different subfields of NLP mitigate bias. We finally discuss how future studies can work towards eradicating pernicious biases"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09591","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/2204.09591/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":"2026-07-05T04:16:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m0Yy72eAbTcePWgfSGzE5FJqjhsBnGimzHj8KLw5szBXifuLngdFFHQ6Le2DpbFRD73GL/QKQom9ABhBkofYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:10:54.221858Z"},"content_sha256":"626c994f9818f768929fca995181012ea2be9d50fa86c9200c580d530558c634","schema_version":"1.0","event_id":"sha256:626c994f9818f768929fca995181012ea2be9d50fa86c9200c580d530558c634"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3WXXSK5ITKWSFNSD2FEEBLZNIF/bundle.json","state_url":"https://pith.science/pith/3WXXSK5ITKWSFNSD2FEEBLZNIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3WXXSK5ITKWSFNSD2FEEBLZNIF/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":"2026-08-20T01:10:54Z","links":{"resolver":"https://pith.science/pith/3WXXSK5ITKWSFNSD2FEEBLZNIF","bundle":"https://pith.science/pith/3WXXSK5ITKWSFNSD2FEEBLZNIF/bundle.json","state":"https://pith.science/pith/3WXXSK5ITKWSFNSD2FEEBLZNIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3WXXSK5ITKWSFNSD2FEEBLZNIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3WXXSK5ITKWSFNSD2FEEBLZNIF","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":"0ca362ee033f4f9d1603335c7735ba3717c12793dfa684733b5afc81664452fd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-06T18:12:30Z","title_canon_sha256":"9ef52372f2dcef6ef62c171dd35b9e15ed30ac7c83de190c0846389b798bdb94"},"schema_version":"1.0","source":{"id":"2204.09591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.09591","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2204.09591v1","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09591","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"3WXXSK5ITKWS","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"3WXXSK5ITKWSFNSD","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"3WXXSK5I","created_at":"2026-07-05T04:16:31Z"}],"graph_snapshots":[{"event_id":"sha256:626c994f9818f768929fca995181012ea2be9d50fa86c9200c580d530558c634","target":"graph","created_at":"2026-07-05T04:16:31Z","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/2204.09591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As NLP models become more integrated with the everyday lives of people, it becomes important to examine the social effect that the usage of these systems has. While these models understand language and have increased accuracy on difficult downstream tasks, there is evidence that these models amplify gender, racial and cultural stereotypes and lead to a vicious cycle in many settings. In this survey, we analyze the origins of biases, the definitions of fairness, and how different subfields of NLP mitigate bias. We finally discuss how future studies can work towards eradicating pernicious biases","authors_text":"Rajas Bansal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-06T18:12:30Z","title":"A Survey on Bias and Fairness in Natural Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09591","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:ea3046db9ef1983f594f3cb3928a730b8c4df9ec51e5bb5001d558201158633b","target":"record","created_at":"2026-07-05T04:16:31Z","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":"0ca362ee033f4f9d1603335c7735ba3717c12793dfa684733b5afc81664452fd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-06T18:12:30Z","title_canon_sha256":"9ef52372f2dcef6ef62c171dd35b9e15ed30ac7c83de190c0846389b798bdb94"},"schema_version":"1.0","source":{"id":"2204.09591","kind":"arxiv","version":1}},"canonical_sha256":"ddaf792ba89aad22b643d14840af2d4151ee4ad0dd6c44371135199ec276ffaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddaf792ba89aad22b643d14840af2d4151ee4ad0dd6c44371135199ec276ffaa","first_computed_at":"2026-07-05T04:16:31.973199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:31.973199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5cQKt6VRXh5JlW9rElDPAi9OwJ8KQSoNPO57eKuNwJneVO/oLeLQIt1f89jjnYAx0UcB6KM5Av4SsUCfRX6bDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:31.973737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.09591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea3046db9ef1983f594f3cb3928a730b8c4df9ec51e5bb5001d558201158633b","sha256:626c994f9818f768929fca995181012ea2be9d50fa86c9200c580d530558c634"],"state_sha256":"0283520c7ef8902bd9506dbfaf37ce3cf959958a74b1f9259227cde1a8472b82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IuuztO5p5Eihjypm+CpV5sAGgKtylc6sNpOR976v/HCRqQRzh40Sg1FhZhvcOTxF3yeSXvNJfa7aiUNqLwFJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:10:54.227010Z","bundle_sha256":"f206bb34e76120da71d34950f43dd97662dd4db9d4566404b8a51b8f70db91f9"}}