{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y4CRR7SVWA3DLVVJN3EZ7TNTS6","short_pith_number":"pith:Y4CRR7SV","canonical_record":{"source":{"id":"2410.04784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T06:49:41Z","cross_cats_sorted":[],"title_canon_sha256":"5095f9a14ed898b6916218a3c6b76650b3f974610151bec10a617c5bbb0399ea","abstract_canon_sha256":"85a7b5c77c87f8eb754faef57fee278ac3da9a129c6c79164f1ef9968defc850"},"schema_version":"1.0"},"canonical_sha256":"c70518fe55b03635d6a96ec99fcdb3978dffa123f8bafb4d256f83b72419e701","source":{"kind":"arxiv","id":"2410.04784","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04784","created_at":"2026-07-05T09:16:56Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04784v1","created_at":"2026-07-05T09:16:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04784","created_at":"2026-07-05T09:16:56Z"},{"alias_kind":"pith_short_12","alias_value":"Y4CRR7SVWA3D","created_at":"2026-07-05T09:16:56Z"},{"alias_kind":"pith_short_16","alias_value":"Y4CRR7SVWA3DLVVJ","created_at":"2026-07-05T09:16:56Z"},{"alias_kind":"pith_short_8","alias_value":"Y4CRR7SV","created_at":"2026-07-05T09:16:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y4CRR7SVWA3DLVVJN3EZ7TNTS6","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T06:49:41Z","cross_cats_sorted":[],"title_canon_sha256":"5095f9a14ed898b6916218a3c6b76650b3f974610151bec10a617c5bbb0399ea","abstract_canon_sha256":"85a7b5c77c87f8eb754faef57fee278ac3da9a129c6c79164f1ef9968defc850"},"schema_version":"1.0"},"canonical_sha256":"c70518fe55b03635d6a96ec99fcdb3978dffa123f8bafb4d256f83b72419e701","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:56.067372Z","signature_b64":"jKsygs7QdzycPLEm82uAc4y1kMb7brSZLyDBK6mnYkyHlVYZRYRSu/edQzyXwD1h3JUIM6glOgyb9DpdqooZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c70518fe55b03635d6a96ec99fcdb3978dffa123f8bafb4d256f83b72419e701","last_reissued_at":"2026-07-05T09:16:56.066899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:56.066899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04784","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":"2026-07-05T09:16:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w/e3AQhtOaHEBUCaHxcwAuqdF8Bf+sPAjP1KiR7AM9CoXghfrA8COUIg8gV3qpehmEQzSYB0pNJS8EISRo9HBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:04:45.952133Z"},"content_sha256":"8979bf09af555f4fc3b3a3e6574aed01ecb651775f7333369fe8a0485fb1d869","schema_version":"1.0","event_id":"sha256:8979bf09af555f4fc3b3a3e6574aed01ecb651775f7333369fe8a0485fb1d869"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y4CRR7SVWA3DLVVJN3EZ7TNTS6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiahuan Li, Jiajun Chen, Shujian Huang, Yiqing Cao","submitted_at":"2024-10-07T06:49:41Z","abstract_excerpt":"Having been trained on massive pretraining data, large language models have shown excellent performance on many knowledge-intensive tasks. However, pretraining data tends to contain misleading and even conflicting information, and it is intriguing to understand how LLMs handle these noisy data during training. In this study, we systematically analyze LLMs' learning preferences for data with conflicting knowledge. We find that pretrained LLMs establish learning preferences similar to humans, i.e., preferences towards formal texts and texts with fewer spelling errors, resulting in faster learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04784","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/2410.04784/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":"2026-07-05T09:16:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QP1h9sKMXN+tj1kD3fgFlT4IGR1cjUsJbWOz4dVAYAeUKER8+l11lHd74sTpVWBhKtMXXiSlKNzfvUFalhaaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:04:45.953040Z"},"content_sha256":"dcde12b56449afd2d7014d0e705b8e7e29aba5ac215c6a5ffcb67dd76e08c6fb","schema_version":"1.0","event_id":"sha256:dcde12b56449afd2d7014d0e705b8e7e29aba5ac215c6a5ffcb67dd76e08c6fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y4CRR7SVWA3DLVVJN3EZ7TNTS6/bundle.json","state_url":"https://pith.science/pith/Y4CRR7SVWA3DLVVJN3EZ7TNTS6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y4CRR7SVWA3DLVVJN3EZ7TNTS6/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":"2026-08-14T17:04:45Z","links":{"resolver":"https://pith.science/pith/Y4CRR7SVWA3DLVVJN3EZ7TNTS6","bundle":"https://pith.science/pith/Y4CRR7SVWA3DLVVJN3EZ7TNTS6/bundle.json","state":"https://pith.science/pith/Y4CRR7SVWA3DLVVJN3EZ7TNTS6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y4CRR7SVWA3DLVVJN3EZ7TNTS6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y4CRR7SVWA3DLVVJN3EZ7TNTS6","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":"85a7b5c77c87f8eb754faef57fee278ac3da9a129c6c79164f1ef9968defc850","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T06:49:41Z","title_canon_sha256":"5095f9a14ed898b6916218a3c6b76650b3f974610151bec10a617c5bbb0399ea"},"schema_version":"1.0","source":{"id":"2410.04784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04784","created_at":"2026-07-05T09:16:56Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04784v1","created_at":"2026-07-05T09:16:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04784","created_at":"2026-07-05T09:16:56Z"},{"alias_kind":"pith_short_12","alias_value":"Y4CRR7SVWA3D","created_at":"2026-07-05T09:16:56Z"},{"alias_kind":"pith_short_16","alias_value":"Y4CRR7SVWA3DLVVJ","created_at":"2026-07-05T09:16:56Z"},{"alias_kind":"pith_short_8","alias_value":"Y4CRR7SV","created_at":"2026-07-05T09:16:56Z"}],"graph_snapshots":[{"event_id":"sha256:dcde12b56449afd2d7014d0e705b8e7e29aba5ac215c6a5ffcb67dd76e08c6fb","target":"graph","created_at":"2026-07-05T09:16:56Z","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/2410.04784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Having been trained on massive pretraining data, large language models have shown excellent performance on many knowledge-intensive tasks. However, pretraining data tends to contain misleading and even conflicting information, and it is intriguing to understand how LLMs handle these noisy data during training. In this study, we systematically analyze LLMs' learning preferences for data with conflicting knowledge. We find that pretrained LLMs establish learning preferences similar to humans, i.e., preferences towards formal texts and texts with fewer spelling errors, resulting in faster learnin","authors_text":"Jiahuan Li, Jiajun Chen, Shujian Huang, Yiqing Cao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T06:49:41Z","title":"Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04784","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":"sha256:8979bf09af555f4fc3b3a3e6574aed01ecb651775f7333369fe8a0485fb1d869","target":"record","created_at":"2026-07-05T09:16:56Z","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":"85a7b5c77c87f8eb754faef57fee278ac3da9a129c6c79164f1ef9968defc850","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T06:49:41Z","title_canon_sha256":"5095f9a14ed898b6916218a3c6b76650b3f974610151bec10a617c5bbb0399ea"},"schema_version":"1.0","source":{"id":"2410.04784","kind":"arxiv","version":1}},"canonical_sha256":"c70518fe55b03635d6a96ec99fcdb3978dffa123f8bafb4d256f83b72419e701","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c70518fe55b03635d6a96ec99fcdb3978dffa123f8bafb4d256f83b72419e701","first_computed_at":"2026-07-05T09:16:56.066899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:56.066899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jKsygs7QdzycPLEm82uAc4y1kMb7brSZLyDBK6mnYkyHlVYZRYRSu/edQzyXwD1h3JUIM6glOgyb9DpdqooZBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:56.067372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8979bf09af555f4fc3b3a3e6574aed01ecb651775f7333369fe8a0485fb1d869","sha256:dcde12b56449afd2d7014d0e705b8e7e29aba5ac215c6a5ffcb67dd76e08c6fb"],"state_sha256":"75ee666e706516f78d516df9b04ed9abb6867b385a7faf0bd2e61d8a71f2b16c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lC2JFL1iHtSOBse++uYtik3LdtRgwOFKaVZcNMSB79xtt5iJwvX7rfrB8wTD0netMZ1KeZztBwmTWBpBkV4ABA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T17:04:45.963064Z","bundle_sha256":"303697604acb6320e4c8abb8112fbafeed6182e25ea361cab50db32e55f0c4fa"}}