{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DOQXLNFXMPDLNSRZSOHTEE5CJY","short_pith_number":"pith:DOQXLNFX","canonical_record":{"source":{"id":"2405.01563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T11:32:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"57e2621a505546ab1c58a99396fc6caafc88daee10a70bc4148ff1bcbc0b9f02","abstract_canon_sha256":"e2ca3daa807ab80db7894f6834d2cc0ae626c9c5ae14fe04e6484cf330a37b02"},"schema_version":"1.0"},"canonical_sha256":"1ba175b4b763c6b6ca39938f3213a24e2f5c1abcd114951115023d19e56d09ac","source":{"kind":"arxiv","id":"2405.01563","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01563","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01563v1","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01563","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"DOQXLNFXMPDL","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"DOQXLNFXMPDLNSRZ","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"DOQXLNFX","created_at":"2026-07-05T08:14:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DOQXLNFXMPDLNSRZSOHTEE5CJY","target":"record","payload":{"canonical_record":{"source":{"id":"2405.01563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T11:32:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"57e2621a505546ab1c58a99396fc6caafc88daee10a70bc4148ff1bcbc0b9f02","abstract_canon_sha256":"e2ca3daa807ab80db7894f6834d2cc0ae626c9c5ae14fe04e6484cf330a37b02"},"schema_version":"1.0"},"canonical_sha256":"1ba175b4b763c6b6ca39938f3213a24e2f5c1abcd114951115023d19e56d09ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:57.969795Z","signature_b64":"s6L7e1CRtm2rcZxxifmN5CP37NGA0jXy1RtV9vM0t+Bfjuej8aQU0M0xG5ORinE812dc6pfp2IcdmNL6TwlFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ba175b4b763c6b6ca39938f3213a24e2f5c1abcd114951115023d19e56d09ac","last_reissued_at":"2026-07-05T08:14:57.969304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:57.969304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.01563","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":"2026-07-05T08:14:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1bi3LClEjK/e/iaXB8+b/NDqgCHLp4MhM0kcZYG8cp4KoLD1dOXxlkQkgUzbAZmBNNI0XeSSU8gh+H1fnvPKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:54:14.672513Z"},"content_sha256":"4e1aabae7a45f45b1b166a729a4e427bdd01b96c33eb0328ebe5fd6905af11a1","schema_version":"1.0","event_id":"sha256:4e1aabae7a45f45b1b166a729a4e427bdd01b96c33eb0328ebe5fd6905af11a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DOQXLNFXMPDLNSRZSOHTEE5CJY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating LLM Hallucinations via Conformal Abstention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Adam Fisch, Ali Taylan Cemgil, Andr\\'as Gy\\\"orgy, Arnaud Doucet, Csaba Szepesv\\'ari, David Stutz, Ilja Kuzborskij, Iuliya Beloshapka, Nenad Tomasev, Wei-Hung Weng, Yao-Yuan Yang, Yasin Abbasi Yadkori","submitted_at":"2024-04-04T11:32:03Z","abstract_excerpt":"We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e.g., by saying \"I don't know\") in a general domain, instead of resorting to possibly \"hallucinating\" a non-sensical or incorrect answer. Building on earlier approaches that use self-consistency as a more reliable measure of model confidence, we propose using the LLM itself to self-evaluate the similarity between each of its sampled responses for a given query. We then further leverage conformal prediction techniques to develop an abstention procedure that benefits from rigorous "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01563","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/2405.01563/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":"2026-07-05T08:14:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUxltAA7VHlc1B6klzkYUbVUuxkRLPTpKLhQE+KKtTh1DklE0nglS+1VlzXKv2PChkYKoQ3P7+00+Te7vKtXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:54:14.673042Z"},"content_sha256":"465a4309f9a228160be48e15a7a7c0574c0f00de29a42ae1199534f8128c284e","schema_version":"1.0","event_id":"sha256:465a4309f9a228160be48e15a7a7c0574c0f00de29a42ae1199534f8128c284e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DOQXLNFXMPDLNSRZSOHTEE5CJY/bundle.json","state_url":"https://pith.science/pith/DOQXLNFXMPDLNSRZSOHTEE5CJY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DOQXLNFXMPDLNSRZSOHTEE5CJY/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":"2026-08-03T17:54:14Z","links":{"resolver":"https://pith.science/pith/DOQXLNFXMPDLNSRZSOHTEE5CJY","bundle":"https://pith.science/pith/DOQXLNFXMPDLNSRZSOHTEE5CJY/bundle.json","state":"https://pith.science/pith/DOQXLNFXMPDLNSRZSOHTEE5CJY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DOQXLNFXMPDLNSRZSOHTEE5CJY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DOQXLNFXMPDLNSRZSOHTEE5CJY","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":"e2ca3daa807ab80db7894f6834d2cc0ae626c9c5ae14fe04e6484cf330a37b02","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T11:32:03Z","title_canon_sha256":"57e2621a505546ab1c58a99396fc6caafc88daee10a70bc4148ff1bcbc0b9f02"},"schema_version":"1.0","source":{"id":"2405.01563","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01563","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01563v1","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01563","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"DOQXLNFXMPDL","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"DOQXLNFXMPDLNSRZ","created_at":"2026-07-05T08:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"DOQXLNFX","created_at":"2026-07-05T08:14:57Z"}],"graph_snapshots":[{"event_id":"sha256:465a4309f9a228160be48e15a7a7c0574c0f00de29a42ae1199534f8128c284e","target":"graph","created_at":"2026-07-05T08:14:57Z","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/2405.01563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e.g., by saying \"I don't know\") in a general domain, instead of resorting to possibly \"hallucinating\" a non-sensical or incorrect answer. Building on earlier approaches that use self-consistency as a more reliable measure of model confidence, we propose using the LLM itself to self-evaluate the similarity between each of its sampled responses for a given query. We then further leverage conformal prediction techniques to develop an abstention procedure that benefits from rigorous ","authors_text":"Adam Fisch, Ali Taylan Cemgil, Andr\\'as Gy\\\"orgy, Arnaud Doucet, Csaba Szepesv\\'ari, David Stutz, Ilja Kuzborskij, Iuliya Beloshapka, Nenad Tomasev, Wei-Hung Weng, Yao-Yuan Yang, Yasin Abbasi Yadkori","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T11:32:03Z","title":"Mitigating LLM Hallucinations via Conformal Abstention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01563","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":"sha256:4e1aabae7a45f45b1b166a729a4e427bdd01b96c33eb0328ebe5fd6905af11a1","target":"record","created_at":"2026-07-05T08:14:57Z","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":"e2ca3daa807ab80db7894f6834d2cc0ae626c9c5ae14fe04e6484cf330a37b02","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T11:32:03Z","title_canon_sha256":"57e2621a505546ab1c58a99396fc6caafc88daee10a70bc4148ff1bcbc0b9f02"},"schema_version":"1.0","source":{"id":"2405.01563","kind":"arxiv","version":1}},"canonical_sha256":"1ba175b4b763c6b6ca39938f3213a24e2f5c1abcd114951115023d19e56d09ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ba175b4b763c6b6ca39938f3213a24e2f5c1abcd114951115023d19e56d09ac","first_computed_at":"2026-07-05T08:14:57.969304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:57.969304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s6L7e1CRtm2rcZxxifmN5CP37NGA0jXy1RtV9vM0t+Bfjuej8aQU0M0xG5ORinE812dc6pfp2IcdmNL6TwlFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:57.969795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.01563","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e1aabae7a45f45b1b166a729a4e427bdd01b96c33eb0328ebe5fd6905af11a1","sha256:465a4309f9a228160be48e15a7a7c0574c0f00de29a42ae1199534f8128c284e"],"state_sha256":"5f73d420f0a516df133d6af3da6314d02dc5ff2ce566fda3245e45099176050d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4BfZeeqSFf2gpg6Ulnnt22Fs1qKl78DraIOC6jtwcM9qNFqm53mpeTggHZAN2TkpYMk6/6m/IORq9omvNCNYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:54:14.678120Z","bundle_sha256":"dbd1c3a06198e3a1275dc2e49040f04c13f6634f1d5261e221f95f0001c73386"}}