{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2KT5OONIELNQLNYJKUW3DOFBSN","short_pith_number":"pith:2KT5OONI","canonical_record":{"source":{"id":"2501.04662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T18:15:47Z","cross_cats_sorted":[],"title_canon_sha256":"f823ff74e7976baf3e0fad51f2fd5dcc9604b614a2cc7ae6fde10ee810bc43c1","abstract_canon_sha256":"7b232907de95907985c0fb7c1b93ea5272a9a1d421460e37af350e74c9c8c110"},"schema_version":"1.0"},"canonical_sha256":"d2a7d739a822db05b709552db1b8a19361d0375c64ab54eff59ffe21ff54c7c0","source":{"kind":"arxiv","id":"2501.04662","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04662","created_at":"2026-07-05T09:58:38Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04662v1","created_at":"2026-07-05T09:58:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04662","created_at":"2026-07-05T09:58:38Z"},{"alias_kind":"pith_short_12","alias_value":"2KT5OONIELNQ","created_at":"2026-07-05T09:58:38Z"},{"alias_kind":"pith_short_16","alias_value":"2KT5OONIELNQLNYJ","created_at":"2026-07-05T09:58:38Z"},{"alias_kind":"pith_short_8","alias_value":"2KT5OONI","created_at":"2026-07-05T09:58:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2KT5OONIELNQLNYJKUW3DOFBSN","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T18:15:47Z","cross_cats_sorted":[],"title_canon_sha256":"f823ff74e7976baf3e0fad51f2fd5dcc9604b614a2cc7ae6fde10ee810bc43c1","abstract_canon_sha256":"7b232907de95907985c0fb7c1b93ea5272a9a1d421460e37af350e74c9c8c110"},"schema_version":"1.0"},"canonical_sha256":"d2a7d739a822db05b709552db1b8a19361d0375c64ab54eff59ffe21ff54c7c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:38.581812Z","signature_b64":"HXJ17OORVWAatjZd8touDOtD5PafA344zCdt71H/K+y9SqLJQG4gJULNtG9pmo+/kUa0oUsZHP+YD3fF9AmpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2a7d739a822db05b709552db1b8a19361d0375c64ab54eff59ffe21ff54c7c0","last_reissued_at":"2026-07-05T09:58:38.581327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:38.581327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04662","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":"2026-07-05T09:58:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DGyMSSfa1diR6Hcv+q9UUlHB/snnsT5AK2jIPjC9MpawU/qe4KxLE3nQ2UdzRbAhW/tJf4BgllpEO71dRoWVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:08:02.873684Z"},"content_sha256":"71a6b406373f20ca7e0a438b10ca966460bf81ae2cf02440186329aca61dd08e","schema_version":"1.0","event_id":"sha256:71a6b406373f20ca7e0a438b10ca966460bf81ae2cf02440186329aca61dd08e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2KT5OONIELNQLNYJKUW3DOFBSN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Tarek Naous, Wei Xu","submitted_at":"2025-01-08T18:15:47Z","abstract_excerpt":"Language Models (LMs) have been shown to exhibit a strong preference towards entities associated with Western culture when operating in non-Western languages. In this paper, we aim to uncover the origins of entity-related cultural biases in LMs by analyzing several contributing factors, including the representation of entities in pre-training data and the impact of variations in linguistic phenomena across languages. We introduce CAMeL-2, a parallel Arabic-English benchmark of 58,086 entities associated with Arab and Western cultures and 367 masked natural contexts for entities. Our evaluation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04662","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/2501.04662/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":"2026-07-05T09:58:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NhB+/Oz2hNoFjnj3ByHYmtWGx2usEJjgZ1XIGlmjIqyepKshYfvp7FP6//TDN1jdDpeq500h6bJwdH09wUXqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:08:02.875017Z"},"content_sha256":"f6a6fec9a3cb392ce60ce6480ff510ddcd90cd82213441fde8ce17201fa1dd05","schema_version":"1.0","event_id":"sha256:f6a6fec9a3cb392ce60ce6480ff510ddcd90cd82213441fde8ce17201fa1dd05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2KT5OONIELNQLNYJKUW3DOFBSN/bundle.json","state_url":"https://pith.science/pith/2KT5OONIELNQLNYJKUW3DOFBSN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2KT5OONIELNQLNYJKUW3DOFBSN/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":"2026-08-11T17:08:02Z","links":{"resolver":"https://pith.science/pith/2KT5OONIELNQLNYJKUW3DOFBSN","bundle":"https://pith.science/pith/2KT5OONIELNQLNYJKUW3DOFBSN/bundle.json","state":"https://pith.science/pith/2KT5OONIELNQLNYJKUW3DOFBSN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2KT5OONIELNQLNYJKUW3DOFBSN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2KT5OONIELNQLNYJKUW3DOFBSN","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":"7b232907de95907985c0fb7c1b93ea5272a9a1d421460e37af350e74c9c8c110","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T18:15:47Z","title_canon_sha256":"f823ff74e7976baf3e0fad51f2fd5dcc9604b614a2cc7ae6fde10ee810bc43c1"},"schema_version":"1.0","source":{"id":"2501.04662","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04662","created_at":"2026-07-05T09:58:38Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04662v1","created_at":"2026-07-05T09:58:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04662","created_at":"2026-07-05T09:58:38Z"},{"alias_kind":"pith_short_12","alias_value":"2KT5OONIELNQ","created_at":"2026-07-05T09:58:38Z"},{"alias_kind":"pith_short_16","alias_value":"2KT5OONIELNQLNYJ","created_at":"2026-07-05T09:58:38Z"},{"alias_kind":"pith_short_8","alias_value":"2KT5OONI","created_at":"2026-07-05T09:58:38Z"}],"graph_snapshots":[{"event_id":"sha256:f6a6fec9a3cb392ce60ce6480ff510ddcd90cd82213441fde8ce17201fa1dd05","target":"graph","created_at":"2026-07-05T09:58:38Z","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/2501.04662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language Models (LMs) have been shown to exhibit a strong preference towards entities associated with Western culture when operating in non-Western languages. In this paper, we aim to uncover the origins of entity-related cultural biases in LMs by analyzing several contributing factors, including the representation of entities in pre-training data and the impact of variations in linguistic phenomena across languages. We introduce CAMeL-2, a parallel Arabic-English benchmark of 58,086 entities associated with Arab and Western cultures and 367 masked natural contexts for entities. Our evaluation","authors_text":"Tarek Naous, Wei Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T18:15:47Z","title":"On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04662","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":"sha256:71a6b406373f20ca7e0a438b10ca966460bf81ae2cf02440186329aca61dd08e","target":"record","created_at":"2026-07-05T09:58:38Z","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":"7b232907de95907985c0fb7c1b93ea5272a9a1d421460e37af350e74c9c8c110","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T18:15:47Z","title_canon_sha256":"f823ff74e7976baf3e0fad51f2fd5dcc9604b614a2cc7ae6fde10ee810bc43c1"},"schema_version":"1.0","source":{"id":"2501.04662","kind":"arxiv","version":1}},"canonical_sha256":"d2a7d739a822db05b709552db1b8a19361d0375c64ab54eff59ffe21ff54c7c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2a7d739a822db05b709552db1b8a19361d0375c64ab54eff59ffe21ff54c7c0","first_computed_at":"2026-07-05T09:58:38.581327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:38.581327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HXJ17OORVWAatjZd8touDOtD5PafA344zCdt71H/K+y9SqLJQG4gJULNtG9pmo+/kUa0oUsZHP+YD3fF9AmpCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:38.581812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04662","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71a6b406373f20ca7e0a438b10ca966460bf81ae2cf02440186329aca61dd08e","sha256:f6a6fec9a3cb392ce60ce6480ff510ddcd90cd82213441fde8ce17201fa1dd05"],"state_sha256":"6e87a4da22e2dd30bc278aaab9bbb75aac7faac309c4374d09e24372ae7f8cd2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTkpO7vwmqjsXk42wZaJmRZOPMKZEnUluny4Z+weXSBCtZfRPM1KrWkYdhr2TxREzdQ5aL/K/9QR6JYBx1V/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T17:08:02.884584Z","bundle_sha256":"08fa4009541ddc029f68814aeb78d611d3467f97796b190f7c4f92e704ecc957"}}