{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6RCTS72FXC5VNECUJ6VNNWEYIF","short_pith_number":"pith:6RCTS72F","canonical_record":{"source":{"id":"2401.12292","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T19:00:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35ca42f3f92347d2844899666a176f79f68889edbbc656941e0281de26176f81","abstract_canon_sha256":"3a3f398b49cafa1ed7e56989fb39544ee73fee089d9a399482982c7840299602"},"schema_version":"1.0"},"canonical_sha256":"f445397f45b8bb5690544faad6d898414c2ae56e4ddc8c4e0e4b62136fa139de","source":{"kind":"arxiv","id":"2401.12292","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12292","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12292v2","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12292","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"pith_short_12","alias_value":"6RCTS72FXC5V","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"pith_short_16","alias_value":"6RCTS72FXC5VNECU","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"pith_short_8","alias_value":"6RCTS72F","created_at":"2026-07-05T07:39:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6RCTS72FXC5VNECUJ6VNNWEYIF","target":"record","payload":{"canonical_record":{"source":{"id":"2401.12292","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T19:00:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35ca42f3f92347d2844899666a176f79f68889edbbc656941e0281de26176f81","abstract_canon_sha256":"3a3f398b49cafa1ed7e56989fb39544ee73fee089d9a399482982c7840299602"},"schema_version":"1.0"},"canonical_sha256":"f445397f45b8bb5690544faad6d898414c2ae56e4ddc8c4e0e4b62136fa139de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:34.094543Z","signature_b64":"Tu3LKZvsK63ewoav29uhYVMFmuK0vLksdZ7O+yi15YbdjzA1yEh+XuRrFX/KRzgqY6OAjgAzQ1dBBG4pczhmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f445397f45b8bb5690544faad6d898414c2ae56e4ddc8c4e0e4b62136fa139de","last_reissued_at":"2026-07-05T07:39:34.094100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:34.094100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.12292","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":"2026-07-05T07:39:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d0/XXrg8BICBZ8JepdYI1Hh5h9XzeH/5aGF3uPuE7tXG+faTbjJTXEB0LS660zPJGVLKyaRq+A1Udm1gSqX+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:36:18.921518Z"},"content_sha256":"a8919202c04214ec6eb16807888025e60b9d35503a4897eefc1d813d48c1a58c","schema_version":"1.0","event_id":"sha256:a8919202c04214ec6eb16807888025e60b9d35503a4897eefc1d813d48c1a58c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6RCTS72FXC5VNECUJ6VNNWEYIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GRATH: Gradual Self-Truthifying for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Li, Dawn Song, Weixin Chen","submitted_at":"2024-01-22T19:00:08Z","abstract_excerpt":"Truthfulness is paramount for large language models (LLMs) as they are increasingly deployed in real-world applications. However, existing LLMs still struggle with generating truthful content, as evidenced by their modest performance on benchmarks like TruthfulQA. To address this issue, we propose GRAdual self-truTHifying (GRATH), a novel post-processing method to enhance truthfulness of LLMs. GRATH utilizes out-of-domain question prompts to generate pairwise truthfulness training data with each pair containing a question and its correct and incorrect answers, and then optimizes the model via "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12292","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/2401.12292/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":"2026-07-05T07:39:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5SuG10cCC3HW5ThKkB/inFEaADkxxyPYIlHxKHOBm6lw7GsQ76zyN5C3nCNGEqxTfcRxbypjSlBOsH70XV0kBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:36:18.922172Z"},"content_sha256":"ff6d491a722d2c4fe799b4c7c23be7bd211babd375a22a3ac10218673f5408a3","schema_version":"1.0","event_id":"sha256:ff6d491a722d2c4fe799b4c7c23be7bd211babd375a22a3ac10218673f5408a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6RCTS72FXC5VNECUJ6VNNWEYIF/bundle.json","state_url":"https://pith.science/pith/6RCTS72FXC5VNECUJ6VNNWEYIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6RCTS72FXC5VNECUJ6VNNWEYIF/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":"2026-08-08T18:36:18Z","links":{"resolver":"https://pith.science/pith/6RCTS72FXC5VNECUJ6VNNWEYIF","bundle":"https://pith.science/pith/6RCTS72FXC5VNECUJ6VNNWEYIF/bundle.json","state":"https://pith.science/pith/6RCTS72FXC5VNECUJ6VNNWEYIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6RCTS72FXC5VNECUJ6VNNWEYIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6RCTS72FXC5VNECUJ6VNNWEYIF","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":"3a3f398b49cafa1ed7e56989fb39544ee73fee089d9a399482982c7840299602","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T19:00:08Z","title_canon_sha256":"35ca42f3f92347d2844899666a176f79f68889edbbc656941e0281de26176f81"},"schema_version":"1.0","source":{"id":"2401.12292","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12292","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12292v2","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12292","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"pith_short_12","alias_value":"6RCTS72FXC5V","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"pith_short_16","alias_value":"6RCTS72FXC5VNECU","created_at":"2026-07-05T07:39:34Z"},{"alias_kind":"pith_short_8","alias_value":"6RCTS72F","created_at":"2026-07-05T07:39:34Z"}],"graph_snapshots":[{"event_id":"sha256:ff6d491a722d2c4fe799b4c7c23be7bd211babd375a22a3ac10218673f5408a3","target":"graph","created_at":"2026-07-05T07:39:34Z","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/2401.12292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Truthfulness is paramount for large language models (LLMs) as they are increasingly deployed in real-world applications. However, existing LLMs still struggle with generating truthful content, as evidenced by their modest performance on benchmarks like TruthfulQA. To address this issue, we propose GRAdual self-truTHifying (GRATH), a novel post-processing method to enhance truthfulness of LLMs. GRATH utilizes out-of-domain question prompts to generate pairwise truthfulness training data with each pair containing a question and its correct and incorrect answers, and then optimizes the model via ","authors_text":"Bo Li, Dawn Song, Weixin Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T19:00:08Z","title":"GRATH: Gradual Self-Truthifying for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12292","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:a8919202c04214ec6eb16807888025e60b9d35503a4897eefc1d813d48c1a58c","target":"record","created_at":"2026-07-05T07:39:34Z","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":"3a3f398b49cafa1ed7e56989fb39544ee73fee089d9a399482982c7840299602","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T19:00:08Z","title_canon_sha256":"35ca42f3f92347d2844899666a176f79f68889edbbc656941e0281de26176f81"},"schema_version":"1.0","source":{"id":"2401.12292","kind":"arxiv","version":2}},"canonical_sha256":"f445397f45b8bb5690544faad6d898414c2ae56e4ddc8c4e0e4b62136fa139de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f445397f45b8bb5690544faad6d898414c2ae56e4ddc8c4e0e4b62136fa139de","first_computed_at":"2026-07-05T07:39:34.094100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:34.094100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tu3LKZvsK63ewoav29uhYVMFmuK0vLksdZ7O+yi15YbdjzA1yEh+XuRrFX/KRzgqY6OAjgAzQ1dBBG4pczhmAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:34.094543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12292","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8919202c04214ec6eb16807888025e60b9d35503a4897eefc1d813d48c1a58c","sha256:ff6d491a722d2c4fe799b4c7c23be7bd211babd375a22a3ac10218673f5408a3"],"state_sha256":"56f33deee7dcc4a3586a8a321a4ac9a524e4cf453aadd33b6d2007f5b8a97c6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j2g6btLOl1nCeLkli6jcl2JLLmDfYUfmMMd2Kjfg7CD/M+TokKoJURCTmwpQUz/OSTDVewIiitsw+pcKIuZ0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:36:18.979199Z","bundle_sha256":"9a0b3d0d9d3156b8cbfc2d77bf0c111d49bdd0534b89d1d06227d6bd573d3725"}}