{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PFIXBGMHFN4PDASOMRJC74PXOI","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":"e7b3f5932278d298207fbca9df7391530d3af14d501f3a2fd35b2dd0b2ef497f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-10T11:56:01Z","title_canon_sha256":"19e3c586199d10a10b02df36c8849ecc3c265c3a21ce57ee2e3c4699709af644"},"schema_version":"1.0","source":{"id":"2404.06948","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06948","created_at":"2026-07-05T08:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06948v2","created_at":"2026-07-05T08:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06948","created_at":"2026-07-05T08:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"PFIXBGMHFN4P","created_at":"2026-07-05T08:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"PFIXBGMHFN4PDASO","created_at":"2026-07-05T08:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"PFIXBGMH","created_at":"2026-07-05T08:06:49Z"}],"graph_snapshots":[{"event_id":"sha256:acf947cdaa01a95ec9ad941bf3427d0b903182407d954f4a11abcb4bfc5e6950","target":"graph","created_at":"2026-07-05T08:06:49Z","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/2404.06948/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucinations in large language models (LLMs) have recently become a significant problem. A recent effort in this direction is a shared task at Semeval 2024 Task 6, SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. This paper describes our winning solution ranked 1st and 2nd in the 2 sub-tasks of model agnostic and model aware tracks respectively. We propose a meta-regressor framework of LLMs for model evaluation and integration that achieves the highest scores on the leaderboard. We also experiment with various transformer-based models and black box meth","authors_text":"Andrew Hoblitzell, Hyeju Jang, Jack O'Keefe, Rahul Mehta, Vasudeva Varma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-10T11:56:01Z","title":"MetaCheckGPT -- A Multi-task Hallucination Detector Using LLM Uncertainty and Meta-models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06948","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":"sha256:63d72afd6d9fe365483ccfdeb6639a193674a5d48b97f16381496862215b8304","target":"record","created_at":"2026-07-05T08:06:49Z","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":"e7b3f5932278d298207fbca9df7391530d3af14d501f3a2fd35b2dd0b2ef497f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-10T11:56:01Z","title_canon_sha256":"19e3c586199d10a10b02df36c8849ecc3c265c3a21ce57ee2e3c4699709af644"},"schema_version":"1.0","source":{"id":"2404.06948","kind":"arxiv","version":2}},"canonical_sha256":"79517099872b78f1824e64522ff1f772242a40daeaee6195d97f526c1b5f8757","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79517099872b78f1824e64522ff1f772242a40daeaee6195d97f526c1b5f8757","first_computed_at":"2026-07-05T08:06:49.140838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:49.140838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vNgEmaLvoxD7pHDsZnGwFmG1qyZXsAqu8xHhV4zGWSquWqG/0AhtqvrkxJ16mOWDWDYfGp2dKilVAJHSLkdMCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:49.141329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06948","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63d72afd6d9fe365483ccfdeb6639a193674a5d48b97f16381496862215b8304","sha256:acf947cdaa01a95ec9ad941bf3427d0b903182407d954f4a11abcb4bfc5e6950"],"state_sha256":"c8e634a966a9d8dc30c88b9d3997766c19fc843718b31f5dfbb01d20fd969405"}