{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TXHETB3TX6E5Q75QA4IX53Q3VO","short_pith_number":"pith:TXHETB3T","canonical_record":{"source":{"id":"2302.05508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-10T20:54:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"20ef2f305a20a71c9f5305ff602e1a8ab2de5d7fc1c7a6b5f6bbae26cf547cc7","abstract_canon_sha256":"4816965e24bc92d08cd10f63f61cc7068bac2d136ffc8cb95c2eb694e89050c4"},"schema_version":"1.0"},"canonical_sha256":"9dce498773bf89d87fb007117eee1bab92937d15b4f7bee1fa793101b6cae2ff","source":{"kind":"arxiv","id":"2302.05508","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05508","created_at":"2026-07-05T10:49:02Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05508v2","created_at":"2026-07-05T10:49:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05508","created_at":"2026-07-05T10:49:02Z"},{"alias_kind":"pith_short_12","alias_value":"TXHETB3TX6E5","created_at":"2026-07-05T10:49:02Z"},{"alias_kind":"pith_short_16","alias_value":"TXHETB3TX6E5Q75Q","created_at":"2026-07-05T10:49:02Z"},{"alias_kind":"pith_short_8","alias_value":"TXHETB3T","created_at":"2026-07-05T10:49:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TXHETB3TX6E5Q75QA4IX53Q3VO","target":"record","payload":{"canonical_record":{"source":{"id":"2302.05508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-10T20:54:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"20ef2f305a20a71c9f5305ff602e1a8ab2de5d7fc1c7a6b5f6bbae26cf547cc7","abstract_canon_sha256":"4816965e24bc92d08cd10f63f61cc7068bac2d136ffc8cb95c2eb694e89050c4"},"schema_version":"1.0"},"canonical_sha256":"9dce498773bf89d87fb007117eee1bab92937d15b4f7bee1fa793101b6cae2ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:02.405795Z","signature_b64":"IRhhXmwloPz4TYOLiw/pg2fI5Uo43O/Cgo4qlA3i1Xa9DRqs5Nix4E3MU4vq6IevyjvRZATdCKhiBimy8sTwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dce498773bf89d87fb007117eee1bab92937d15b4f7bee1fa793101b6cae2ff","last_reissued_at":"2026-07-05T10:49:02.405290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:02.405290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.05508","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":"2026-07-05T10:49:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Klrj67BHm8JZkHEmTvWv7dYHL9r0YRyDoHDeLDclFuHI0+FAjSlZBmG9btD7n9MQ9VXqxMCB1cWh++hoTSoNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:48:47.023244Z"},"content_sha256":"502d85acb421e14d06c990539185c53afb4f7b9aa06ef003d4d945fb0ee5a132","schema_version":"1.0","event_id":"sha256:502d85acb421e14d06c990539185c53afb4f7b9aa06ef003d4d945fb0ee5a132"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TXHETB3TX6E5Q75QA4IX53Q3VO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hrishikesh Viswanath, Tianyi Zhang","submitted_at":"2023-02-10T20:54:10Z","abstract_excerpt":"Recent studies have demonstrated that large pretrained language models (LLMs) such as BERT and GPT-2 exhibit biases in token prediction, often inherited from the data distributions present in their training corpora. In response, a number of mathematical frameworks have been proposed to quantify, identify, and mitigate these the likelihood of biased token predictions. In this paper, we present a comprehensive survey of such techniques tailored towards widely used LLMs such as BERT, GPT-2, etc. We additionally introduce Fairpy, a modular and extensible toolkit that provides plug-and-play interfa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05508","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/2302.05508/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":"2026-07-05T10:49:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xZVCqmFskrBFw3vhHIN0i9PWwTjf+2o3w/iplP0K8ItARdWb//rneJubK2VA9xszhVbVcnkAycls7klbwrNPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:48:47.024256Z"},"content_sha256":"79d9f1dbdd9dc6e61719c1f7d232807430f338faf07434ed3143c25d937eb3a5","schema_version":"1.0","event_id":"sha256:79d9f1dbdd9dc6e61719c1f7d232807430f338faf07434ed3143c25d937eb3a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXHETB3TX6E5Q75QA4IX53Q3VO/bundle.json","state_url":"https://pith.science/pith/TXHETB3TX6E5Q75QA4IX53Q3VO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXHETB3TX6E5Q75QA4IX53Q3VO/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":"2026-08-11T13:48:47Z","links":{"resolver":"https://pith.science/pith/TXHETB3TX6E5Q75QA4IX53Q3VO","bundle":"https://pith.science/pith/TXHETB3TX6E5Q75QA4IX53Q3VO/bundle.json","state":"https://pith.science/pith/TXHETB3TX6E5Q75QA4IX53Q3VO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXHETB3TX6E5Q75QA4IX53Q3VO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TXHETB3TX6E5Q75QA4IX53Q3VO","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":"4816965e24bc92d08cd10f63f61cc7068bac2d136ffc8cb95c2eb694e89050c4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-10T20:54:10Z","title_canon_sha256":"20ef2f305a20a71c9f5305ff602e1a8ab2de5d7fc1c7a6b5f6bbae26cf547cc7"},"schema_version":"1.0","source":{"id":"2302.05508","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05508","created_at":"2026-07-05T10:49:02Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05508v2","created_at":"2026-07-05T10:49:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05508","created_at":"2026-07-05T10:49:02Z"},{"alias_kind":"pith_short_12","alias_value":"TXHETB3TX6E5","created_at":"2026-07-05T10:49:02Z"},{"alias_kind":"pith_short_16","alias_value":"TXHETB3TX6E5Q75Q","created_at":"2026-07-05T10:49:02Z"},{"alias_kind":"pith_short_8","alias_value":"TXHETB3T","created_at":"2026-07-05T10:49:02Z"}],"graph_snapshots":[{"event_id":"sha256:79d9f1dbdd9dc6e61719c1f7d232807430f338faf07434ed3143c25d937eb3a5","target":"graph","created_at":"2026-07-05T10:49:02Z","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/2302.05508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have demonstrated that large pretrained language models (LLMs) such as BERT and GPT-2 exhibit biases in token prediction, often inherited from the data distributions present in their training corpora. In response, a number of mathematical frameworks have been proposed to quantify, identify, and mitigate these the likelihood of biased token predictions. In this paper, we present a comprehensive survey of such techniques tailored towards widely used LLMs such as BERT, GPT-2, etc. We additionally introduce Fairpy, a modular and extensible toolkit that provides plug-and-play interfa","authors_text":"Hrishikesh Viswanath, Tianyi Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-10T20:54:10Z","title":"FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05508","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":"sha256:502d85acb421e14d06c990539185c53afb4f7b9aa06ef003d4d945fb0ee5a132","target":"record","created_at":"2026-07-05T10:49:02Z","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":"4816965e24bc92d08cd10f63f61cc7068bac2d136ffc8cb95c2eb694e89050c4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-10T20:54:10Z","title_canon_sha256":"20ef2f305a20a71c9f5305ff602e1a8ab2de5d7fc1c7a6b5f6bbae26cf547cc7"},"schema_version":"1.0","source":{"id":"2302.05508","kind":"arxiv","version":2}},"canonical_sha256":"9dce498773bf89d87fb007117eee1bab92937d15b4f7bee1fa793101b6cae2ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dce498773bf89d87fb007117eee1bab92937d15b4f7bee1fa793101b6cae2ff","first_computed_at":"2026-07-05T10:49:02.405290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:02.405290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IRhhXmwloPz4TYOLiw/pg2fI5Uo43O/Cgo4qlA3i1Xa9DRqs5Nix4E3MU4vq6IevyjvRZATdCKhiBimy8sTwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:02.405795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05508","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:502d85acb421e14d06c990539185c53afb4f7b9aa06ef003d4d945fb0ee5a132","sha256:79d9f1dbdd9dc6e61719c1f7d232807430f338faf07434ed3143c25d937eb3a5"],"state_sha256":"1438fbfc40aebf238b0e758464654f9da24aef123f0abc2def36b723fc55ba7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1c7Xj6dzSh3Vh5JI0NXw7jcvcvw3UDGXs+qDESH8em112KOseFIdZYIyT60Y4S3VzjhAtX9MR4YVCXTyLCt5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T13:48:47.029895Z","bundle_sha256":"45adacd194d3c58d0d17e88e8eb8dbce60e49c49f27281ca761fa679322a34c7"}}