{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R3VVBEZOA54IDF5MQTQJBJQOGT","short_pith_number":"pith:R3VVBEZO","canonical_record":{"source":{"id":"2504.14212","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T07:36:02Z","cross_cats_sorted":[],"title_canon_sha256":"8c1257c690396dc79529761a425f43bdfbaaa054717b801851c3281c6de17d33","abstract_canon_sha256":"661f94822aa53556a2ca626b3b6868bccabb2849c88f9484f809f7b1cae6a2e8"},"schema_version":"1.0"},"canonical_sha256":"8eeb50932e07788197ac84e090a60e34ee01297d99ab56452df1288dbb1f7466","source":{"kind":"arxiv","id":"2504.14212","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14212","created_at":"2026-07-05T12:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14212v3","created_at":"2026-07-05T12:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14212","created_at":"2026-07-05T12:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"R3VVBEZOA54I","created_at":"2026-07-05T12:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"R3VVBEZOA54IDF5M","created_at":"2026-07-05T12:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"R3VVBEZO","created_at":"2026-07-05T12:03:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R3VVBEZOA54IDF5MQTQJBJQOGT","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14212","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T07:36:02Z","cross_cats_sorted":[],"title_canon_sha256":"8c1257c690396dc79529761a425f43bdfbaaa054717b801851c3281c6de17d33","abstract_canon_sha256":"661f94822aa53556a2ca626b3b6868bccabb2849c88f9484f809f7b1cae6a2e8"},"schema_version":"1.0"},"canonical_sha256":"8eeb50932e07788197ac84e090a60e34ee01297d99ab56452df1288dbb1f7466","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:47.644044Z","signature_b64":"0h6qDtwLYBMY6RpHyBBlA8WUFBM4EaGkNOvgGMR1M7/ia4Q0cvRGGgtkY7098ex/keKDG8m8I7S+6D8/h3J6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eeb50932e07788197ac84e090a60e34ee01297d99ab56452df1288dbb1f7466","last_reissued_at":"2026-07-05T12:03:47.643524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:47.643524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14212","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AWyS3GIuS+ITATgfGYHvpPyXh59v/ux6wep10M45em4eSzGS/NNfAZcrrcLo1sKUY//7Hvlf8XcH3+9hxggABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:25:18.255028Z"},"content_sha256":"ece030670aadec548496503325d41c93d017efbf94c9c595e28a8f9194bcb75b","schema_version":"1.0","event_id":"sha256:ece030670aadec548496503325d41c93d017efbf94c9c595e28a8f9194bcb75b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R3VVBEZOA54IDF5MQTQJBJQOGT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bishwaranjan Bhattacharjee, Hiroshi Kanayama, Takuma Udagawa, Yang Zhao","submitted_at":"2025-04-19T07:36:02Z","abstract_excerpt":"Large language models (LLMs) acquire general linguistic knowledge from massive-scale pretraining. However, pretraining data mainly comprised of web-crawled texts contain undesirable social biases which can be perpetuated or even amplified by LLMs. In this study, we propose an efficient yet effective annotation pipeline to investigate social biases in the pretraining corpora. Our pipeline consists of protected attribute detection to identify diverse demographics, followed by regard classification to analyze the language polarity towards each attribute. Through our experiments, we demonstrate th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14212","kind":"arxiv","version":3},"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/2504.14212/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":"2026-07-05T12:03:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DwgOiHolrPAmK8XUtD1TbvoD36FHqWdm/mCEgHSXp9hyoqmXD43hqIi/xXluKu60Ps60Gr3bZq+i57qCbZ1nAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:25:18.255401Z"},"content_sha256":"6f6006ad5d6fe531d8ad03599b3dd7ceb42df45d808d0f35c1bb955e6d106153","schema_version":"1.0","event_id":"sha256:6f6006ad5d6fe531d8ad03599b3dd7ceb42df45d808d0f35c1bb955e6d106153"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3VVBEZOA54IDF5MQTQJBJQOGT/bundle.json","state_url":"https://pith.science/pith/R3VVBEZOA54IDF5MQTQJBJQOGT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3VVBEZOA54IDF5MQTQJBJQOGT/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":"2026-08-18T11:25:18Z","links":{"resolver":"https://pith.science/pith/R3VVBEZOA54IDF5MQTQJBJQOGT","bundle":"https://pith.science/pith/R3VVBEZOA54IDF5MQTQJBJQOGT/bundle.json","state":"https://pith.science/pith/R3VVBEZOA54IDF5MQTQJBJQOGT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3VVBEZOA54IDF5MQTQJBJQOGT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R3VVBEZOA54IDF5MQTQJBJQOGT","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":"661f94822aa53556a2ca626b3b6868bccabb2849c88f9484f809f7b1cae6a2e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T07:36:02Z","title_canon_sha256":"8c1257c690396dc79529761a425f43bdfbaaa054717b801851c3281c6de17d33"},"schema_version":"1.0","source":{"id":"2504.14212","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14212","created_at":"2026-07-05T12:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14212v3","created_at":"2026-07-05T12:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14212","created_at":"2026-07-05T12:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"R3VVBEZOA54I","created_at":"2026-07-05T12:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"R3VVBEZOA54IDF5M","created_at":"2026-07-05T12:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"R3VVBEZO","created_at":"2026-07-05T12:03:47Z"}],"graph_snapshots":[{"event_id":"sha256:6f6006ad5d6fe531d8ad03599b3dd7ceb42df45d808d0f35c1bb955e6d106153","target":"graph","created_at":"2026-07-05T12:03:47Z","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/2504.14212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) acquire general linguistic knowledge from massive-scale pretraining. However, pretraining data mainly comprised of web-crawled texts contain undesirable social biases which can be perpetuated or even amplified by LLMs. In this study, we propose an efficient yet effective annotation pipeline to investigate social biases in the pretraining corpora. Our pipeline consists of protected attribute detection to identify diverse demographics, followed by regard classification to analyze the language polarity towards each attribute. Through our experiments, we demonstrate th","authors_text":"Bishwaranjan Bhattacharjee, Hiroshi Kanayama, Takuma Udagawa, Yang Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T07:36:02Z","title":"Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14212","kind":"arxiv","version":3},"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:ece030670aadec548496503325d41c93d017efbf94c9c595e28a8f9194bcb75b","target":"record","created_at":"2026-07-05T12:03:47Z","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":"661f94822aa53556a2ca626b3b6868bccabb2849c88f9484f809f7b1cae6a2e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T07:36:02Z","title_canon_sha256":"8c1257c690396dc79529761a425f43bdfbaaa054717b801851c3281c6de17d33"},"schema_version":"1.0","source":{"id":"2504.14212","kind":"arxiv","version":3}},"canonical_sha256":"8eeb50932e07788197ac84e090a60e34ee01297d99ab56452df1288dbb1f7466","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8eeb50932e07788197ac84e090a60e34ee01297d99ab56452df1288dbb1f7466","first_computed_at":"2026-07-05T12:03:47.643524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:47.643524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0h6qDtwLYBMY6RpHyBBlA8WUFBM4EaGkNOvgGMR1M7/ia4Q0cvRGGgtkY7098ex/keKDG8m8I7S+6D8/h3J6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:47.644044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14212","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ece030670aadec548496503325d41c93d017efbf94c9c595e28a8f9194bcb75b","sha256:6f6006ad5d6fe531d8ad03599b3dd7ceb42df45d808d0f35c1bb955e6d106153"],"state_sha256":"1f30aed13c7d17348d22e3bfb624161c9fbf0c02c6e7a8fc84af71017f1b30a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F+UD8xIoUaV40HYZaejwlohRi9wjLgncfPu6KwL2m+Qwt3JVeWnbd2eQ2JT3Im6CIh6E8AomZ5vigtObAKCfCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:25:18.257858Z","bundle_sha256":"77108372247bb85c2f164795f00544cd018096f47da59096a5c76c03ab7b0289"}}