{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M7VPP2ANPBZ3MTKZBCQKNMQ7NU","short_pith_number":"pith:M7VPP2AN","canonical_record":{"source":{"id":"2408.07852","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T23:34:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5ac4c7826badb70529805711e093a4917010cf3554625e69b8122db236818f41","abstract_canon_sha256":"4cc83af42faa699969f0239ce57364286ca7d781c9b1b7bc7cf8e53b38cc736c"},"schema_version":"1.0"},"canonical_sha256":"67eaf7e80d7873b64d5908a0a6b21f6d1e279a9005182327a4c248bcac46612d","source":{"kind":"arxiv","id":"2408.07852","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07852","created_at":"2026-07-05T08:55:40Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07852v1","created_at":"2026-07-05T08:55:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07852","created_at":"2026-07-05T08:55:40Z"},{"alias_kind":"pith_short_12","alias_value":"M7VPP2ANPBZ3","created_at":"2026-07-05T08:55:40Z"},{"alias_kind":"pith_short_16","alias_value":"M7VPP2ANPBZ3MTKZ","created_at":"2026-07-05T08:55:40Z"},{"alias_kind":"pith_short_8","alias_value":"M7VPP2AN","created_at":"2026-07-05T08:55:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M7VPP2ANPBZ3MTKZBCQKNMQ7NU","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07852","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T23:34:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5ac4c7826badb70529805711e093a4917010cf3554625e69b8122db236818f41","abstract_canon_sha256":"4cc83af42faa699969f0239ce57364286ca7d781c9b1b7bc7cf8e53b38cc736c"},"schema_version":"1.0"},"canonical_sha256":"67eaf7e80d7873b64d5908a0a6b21f6d1e279a9005182327a4c248bcac46612d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:40.912097Z","signature_b64":"r0LGQd6Dm0AcVHo0TyqN0gmWUN1/cUAhwx4/C/jajhN2yrdlSvseHK3uUhDTex9D4hhOF75Tsox45v8SV6rXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67eaf7e80d7873b64d5908a0a6b21f6d1e279a9005182327a4c248bcac46612d","last_reissued_at":"2026-07-05T08:55:40.911571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:40.911571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07852","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":"2026-07-05T08:55:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7tElllO94pRwKa2/SQpFHup3vdsSpqh/NC0E4vmn88of/0AjCTNawGomqoQEa0n6qhRllcXu6ZHGipVPV1YzBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:26:02.118232Z"},"content_sha256":"6aeeaec3a1a17115009d37c1d3f05bae85a881187d4eb6bd91a1be6fc19e59aa","schema_version":"1.0","event_id":"sha256:6aeeaec3a1a17115009d37c1d3f05bae85a881187d4eb6bd91a1be6fc19e59aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M7VPP2ANPBZ3MTKZBCQKNMQ7NU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron Parisi, Alex Rizkowsky, Azade Nova, Ben Adlam, Bernd Bohnet, C. Daniel Freeman, Gamaleldin Elsayed, Gaurav Mishra, Hanie Sedghi, Igor Mordatch, Isabelle Simpson, Izzeddin Gur, Jaehoon Lee, Jascha Sohl-Dickstein, Jasper Snoek, JD Co-Reyes, Jeffrey Pennington, Jiri Hron, Kathleen Kenealy, Kelvin Xu, Kevin Swersky, Laura Culp, Lechao Xiao, Maxwell Bileschi, Noah Fiedel, Peter J. Liu, Roman Novak, Rosanne Liu, Sharad Vikram, Simon Kornblith, Tris Warkentin","submitted_at":"2024-08-14T23:34:28Z","abstract_excerpt":"While many capabilities of language models (LMs) improve with increased training budget, the influence of scale on hallucinations is not yet fully understood. Hallucinations come in many forms, and there is no universally accepted definition. We thus focus on studying only those hallucinations where a correct answer appears verbatim in the training set. To fully control the training data content, we construct a knowledge graph (KG)-based dataset, and use it to train a set of increasingly large LMs. We find that for a fixed dataset, larger and longer-trained LMs hallucinate less. However, hallu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07852","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/2408.07852/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":"2026-07-05T08:55:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S3BDBGXdYBBz26ffyDasP4raFpDcLglbU79HwDVtZH2gag9Wtrrhy33GimsSY8bBJHtgZgGQa0wivUCZvcq6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:26:02.118707Z"},"content_sha256":"95512ba18c5d004d6769ea8905e170b812a275fe0ee799b9200b16a391c9c26f","schema_version":"1.0","event_id":"sha256:95512ba18c5d004d6769ea8905e170b812a275fe0ee799b9200b16a391c9c26f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7VPP2ANPBZ3MTKZBCQKNMQ7NU/bundle.json","state_url":"https://pith.science/pith/M7VPP2ANPBZ3MTKZBCQKNMQ7NU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7VPP2ANPBZ3MTKZBCQKNMQ7NU/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":"2026-08-05T02:26:02Z","links":{"resolver":"https://pith.science/pith/M7VPP2ANPBZ3MTKZBCQKNMQ7NU","bundle":"https://pith.science/pith/M7VPP2ANPBZ3MTKZBCQKNMQ7NU/bundle.json","state":"https://pith.science/pith/M7VPP2ANPBZ3MTKZBCQKNMQ7NU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7VPP2ANPBZ3MTKZBCQKNMQ7NU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M7VPP2ANPBZ3MTKZBCQKNMQ7NU","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":"4cc83af42faa699969f0239ce57364286ca7d781c9b1b7bc7cf8e53b38cc736c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T23:34:28Z","title_canon_sha256":"5ac4c7826badb70529805711e093a4917010cf3554625e69b8122db236818f41"},"schema_version":"1.0","source":{"id":"2408.07852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07852","created_at":"2026-07-05T08:55:40Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07852v1","created_at":"2026-07-05T08:55:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07852","created_at":"2026-07-05T08:55:40Z"},{"alias_kind":"pith_short_12","alias_value":"M7VPP2ANPBZ3","created_at":"2026-07-05T08:55:40Z"},{"alias_kind":"pith_short_16","alias_value":"M7VPP2ANPBZ3MTKZ","created_at":"2026-07-05T08:55:40Z"},{"alias_kind":"pith_short_8","alias_value":"M7VPP2AN","created_at":"2026-07-05T08:55:40Z"}],"graph_snapshots":[{"event_id":"sha256:95512ba18c5d004d6769ea8905e170b812a275fe0ee799b9200b16a391c9c26f","target":"graph","created_at":"2026-07-05T08:55:40Z","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/2408.07852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While many capabilities of language models (LMs) improve with increased training budget, the influence of scale on hallucinations is not yet fully understood. Hallucinations come in many forms, and there is no universally accepted definition. We thus focus on studying only those hallucinations where a correct answer appears verbatim in the training set. To fully control the training data content, we construct a knowledge graph (KG)-based dataset, and use it to train a set of increasingly large LMs. We find that for a fixed dataset, larger and longer-trained LMs hallucinate less. However, hallu","authors_text":"Aaron Parisi, Alex Rizkowsky, Azade Nova, Ben Adlam, Bernd Bohnet, C. Daniel Freeman, Gamaleldin Elsayed, Gaurav Mishra, Hanie Sedghi, Igor Mordatch, Isabelle Simpson, Izzeddin Gur, Jaehoon Lee, Jascha Sohl-Dickstein, Jasper Snoek, JD Co-Reyes, Jeffrey Pennington, Jiri Hron, Kathleen Kenealy, Kelvin Xu, Kevin Swersky, Laura Culp, Lechao Xiao, Maxwell Bileschi, Noah Fiedel, Peter J. Liu, Roman Novak, Rosanne Liu, Sharad Vikram, Simon Kornblith, Tris Warkentin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T23:34:28Z","title":"Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07852","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":"sha256:6aeeaec3a1a17115009d37c1d3f05bae85a881187d4eb6bd91a1be6fc19e59aa","target":"record","created_at":"2026-07-05T08:55:40Z","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":"4cc83af42faa699969f0239ce57364286ca7d781c9b1b7bc7cf8e53b38cc736c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T23:34:28Z","title_canon_sha256":"5ac4c7826badb70529805711e093a4917010cf3554625e69b8122db236818f41"},"schema_version":"1.0","source":{"id":"2408.07852","kind":"arxiv","version":1}},"canonical_sha256":"67eaf7e80d7873b64d5908a0a6b21f6d1e279a9005182327a4c248bcac46612d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67eaf7e80d7873b64d5908a0a6b21f6d1e279a9005182327a4c248bcac46612d","first_computed_at":"2026-07-05T08:55:40.911571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:40.911571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r0LGQd6Dm0AcVHo0TyqN0gmWUN1/cUAhwx4/C/jajhN2yrdlSvseHK3uUhDTex9D4hhOF75Tsox45v8SV6rXDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:40.912097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aeeaec3a1a17115009d37c1d3f05bae85a881187d4eb6bd91a1be6fc19e59aa","sha256:95512ba18c5d004d6769ea8905e170b812a275fe0ee799b9200b16a391c9c26f"],"state_sha256":"5c4382f1861198719e05eb5c960b13605425411603878745d0478da2f630b431"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RLjb4Gns7SaObpPlmo/le5GlMD6XsSxGA6+PSEr1pK2lnBTFZ6XL0I9ya9cYbwS7/paxMqmpAtomthsF/Xq4DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:26:02.121937Z","bundle_sha256":"b59056f496dc9e12707901e2e1e41cf6eee30556a250f24eaeab3dc48ba55974"}}