{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JDFX6KBCBJHE2VJIQLKX6XJSXL","short_pith_number":"pith:JDFX6KBC","canonical_record":{"source":{"id":"2503.22362","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T12:12:38Z","cross_cats_sorted":[],"title_canon_sha256":"b177b6387b304a889239615d33bd0132a870edddafebb73d884b2cee2465eca4","abstract_canon_sha256":"14427dfe4e6ae9398f1d657e1fe59c7cf6841d5fcbd2ae3d342fdbfbc87f719d"},"schema_version":"1.0"},"canonical_sha256":"48cb7f28220a4e4d552882d57f5d32bad14348da55a094d93021c060cae11e87","source":{"kind":"arxiv","id":"2503.22362","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22362","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22362v2","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22362","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"pith_short_12","alias_value":"JDFX6KBCBJHE","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"pith_short_16","alias_value":"JDFX6KBCBJHE2VJI","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"pith_short_8","alias_value":"JDFX6KBC","created_at":"2026-07-05T11:35:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JDFX6KBCBJHE2VJIQLKX6XJSXL","target":"record","payload":{"canonical_record":{"source":{"id":"2503.22362","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T12:12:38Z","cross_cats_sorted":[],"title_canon_sha256":"b177b6387b304a889239615d33bd0132a870edddafebb73d884b2cee2465eca4","abstract_canon_sha256":"14427dfe4e6ae9398f1d657e1fe59c7cf6841d5fcbd2ae3d342fdbfbc87f719d"},"schema_version":"1.0"},"canonical_sha256":"48cb7f28220a4e4d552882d57f5d32bad14348da55a094d93021c060cae11e87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:54.818097Z","signature_b64":"jIIhXyBM8YJw14vI6hDpLqDRLNjt8yiv9YyGIhQmcERwIFcjBnfQyPl8m7Pm0DVt352y1dyE8enmQW2MZQspAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48cb7f28220a4e4d552882d57f5d32bad14348da55a094d93021c060cae11e87","last_reissued_at":"2026-07-05T11:35:54.817607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:54.817607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.22362","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":"2026-07-05T11:35:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GoqCqDHvw+XGL4hVPGPvzTQHn4017RHYuytSTE+ky/SveAU5N8khQcQi3NEsE0nt8WWlYPfdvHfhdE61vtiVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:49:29.357390Z"},"content_sha256":"5cc26246b0da7bdbecbd681746bce0400e0aaa0b01629f42614e4dbafeb93544","schema_version":"1.0","event_id":"sha256:5cc26246b0da7bdbecbd681746bce0400e0aaa0b01629f42614e4dbafeb93544"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JDFX6KBCBJHE2VJIQLKX6XJSXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Supposedly Equivalent Facts That Aren't? Entity Frequency in Pre-training Induces Asymmetry in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alisia Lupidi, Bailan He, Caiqi Zhang, Ian Horrocks, Jiaoyan Chen, Shuo Chen, Volker Tresp, Yuan He, Yunpu Ma, Yuqicheng Zhu, Zifeng Ding","submitted_at":"2025-03-28T12:12:38Z","abstract_excerpt":"Understanding and mitigating hallucinations in Large Language Models (LLMs) is crucial for ensuring reliable content generation. While previous research has primarily focused on \"when\" LLMs hallucinate, our work explains \"why\" and directly links model behaviour to the pre-training data that forms their prior knowledge. Specifically, we demonstrate that an asymmetry exists in the recognition of logically equivalent facts, which can be attributed to frequency discrepancies of entities appearing as subjects versus objects. Given that most pre-training datasets are inaccessible, we leverage the fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22362","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/2503.22362/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":"2026-07-05T11:35:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lLdURAcVRha9/JWhNBE3RSS+Qa/xqICKoFNrsaU7123jUJbczsmeQC/73BeXst1dR/nmt6fWJ8GHwFMKMdNOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:49:29.358003Z"},"content_sha256":"7469e884613b9c1601bc25165fb316b6752acb219844d226bfcc41e3477a7589","schema_version":"1.0","event_id":"sha256:7469e884613b9c1601bc25165fb316b6752acb219844d226bfcc41e3477a7589"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JDFX6KBCBJHE2VJIQLKX6XJSXL/bundle.json","state_url":"https://pith.science/pith/JDFX6KBCBJHE2VJIQLKX6XJSXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JDFX6KBCBJHE2VJIQLKX6XJSXL/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":"2026-08-04T17:49:29Z","links":{"resolver":"https://pith.science/pith/JDFX6KBCBJHE2VJIQLKX6XJSXL","bundle":"https://pith.science/pith/JDFX6KBCBJHE2VJIQLKX6XJSXL/bundle.json","state":"https://pith.science/pith/JDFX6KBCBJHE2VJIQLKX6XJSXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JDFX6KBCBJHE2VJIQLKX6XJSXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JDFX6KBCBJHE2VJIQLKX6XJSXL","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":"14427dfe4e6ae9398f1d657e1fe59c7cf6841d5fcbd2ae3d342fdbfbc87f719d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T12:12:38Z","title_canon_sha256":"b177b6387b304a889239615d33bd0132a870edddafebb73d884b2cee2465eca4"},"schema_version":"1.0","source":{"id":"2503.22362","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22362","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22362v2","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22362","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"pith_short_12","alias_value":"JDFX6KBCBJHE","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"pith_short_16","alias_value":"JDFX6KBCBJHE2VJI","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"pith_short_8","alias_value":"JDFX6KBC","created_at":"2026-07-05T11:35:54Z"}],"graph_snapshots":[{"event_id":"sha256:7469e884613b9c1601bc25165fb316b6752acb219844d226bfcc41e3477a7589","target":"graph","created_at":"2026-07-05T11:35:54Z","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/2503.22362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding and mitigating hallucinations in Large Language Models (LLMs) is crucial for ensuring reliable content generation. While previous research has primarily focused on \"when\" LLMs hallucinate, our work explains \"why\" and directly links model behaviour to the pre-training data that forms their prior knowledge. Specifically, we demonstrate that an asymmetry exists in the recognition of logically equivalent facts, which can be attributed to frequency discrepancies of entities appearing as subjects versus objects. Given that most pre-training datasets are inaccessible, we leverage the fu","authors_text":"Alisia Lupidi, Bailan He, Caiqi Zhang, Ian Horrocks, Jiaoyan Chen, Shuo Chen, Volker Tresp, Yuan He, Yunpu Ma, Yuqicheng Zhu, Zifeng Ding","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T12:12:38Z","title":"Supposedly Equivalent Facts That Aren't? Entity Frequency in Pre-training Induces Asymmetry in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22362","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":"sha256:5cc26246b0da7bdbecbd681746bce0400e0aaa0b01629f42614e4dbafeb93544","target":"record","created_at":"2026-07-05T11:35:54Z","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":"14427dfe4e6ae9398f1d657e1fe59c7cf6841d5fcbd2ae3d342fdbfbc87f719d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T12:12:38Z","title_canon_sha256":"b177b6387b304a889239615d33bd0132a870edddafebb73d884b2cee2465eca4"},"schema_version":"1.0","source":{"id":"2503.22362","kind":"arxiv","version":2}},"canonical_sha256":"48cb7f28220a4e4d552882d57f5d32bad14348da55a094d93021c060cae11e87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48cb7f28220a4e4d552882d57f5d32bad14348da55a094d93021c060cae11e87","first_computed_at":"2026-07-05T11:35:54.817607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:54.817607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jIIhXyBM8YJw14vI6hDpLqDRLNjt8yiv9YyGIhQmcERwIFcjBnfQyPl8m7Pm0DVt352y1dyE8enmQW2MZQspAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:54.818097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22362","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cc26246b0da7bdbecbd681746bce0400e0aaa0b01629f42614e4dbafeb93544","sha256:7469e884613b9c1601bc25165fb316b6752acb219844d226bfcc41e3477a7589"],"state_sha256":"693f01affd7d7a0f97943241f4b01150ee25756ba88bd2a1043c64f862574ce2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mO7ku69Nn/IVVYPGR/ug/OQPMWRPIomDKHguSlhSPHHPpoz6ad/7NziNAoOSh6ExcDgUbHJRYTibjmRLJlCoBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:49:29.398950Z","bundle_sha256":"524b9b40db2e8db3cd53fd9f09738a7e826ddf1d602b6f1eb704fcd94dc3c4b1"}}