{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EPQO5T44URRAAEJ4NHX5MYYVSZ","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":"317b23600c6d1ad843b11b889836ce8cc0b0f378bb183029c1f83343b315deeb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T16:55:25Z","title_canon_sha256":"e31019d2f6abbaf73ff9dfc5fe980f2e832870357917bf0fb2d9af3ea476fee9"},"schema_version":"1.0","source":{"id":"2409.11353","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11353","created_at":"2026-07-05T10:02:51Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11353v3","created_at":"2026-07-05T10:02:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11353","created_at":"2026-07-05T10:02:51Z"},{"alias_kind":"pith_short_12","alias_value":"EPQO5T44URRA","created_at":"2026-07-05T10:02:51Z"},{"alias_kind":"pith_short_16","alias_value":"EPQO5T44URRAAEJ4","created_at":"2026-07-05T10:02:51Z"},{"alias_kind":"pith_short_8","alias_value":"EPQO5T44","created_at":"2026-07-05T10:02:51Z"}],"graph_snapshots":[{"event_id":"sha256:528dd607bd88c06405fc7ca40cefb6e2037045af37196ba5bbdb415afbcb925d","target":"graph","created_at":"2026-07-05T10:02:51Z","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/2409.11353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models (LLMs). Existing detection and mitigation methods are often isolated and insufficient for domain-specific needs, lacking a standardized pipeline. This paper introduces THaMES (Tool for Hallucination Mitigations and EvaluationS), an integrated framework and library addressing this gap. THaMES offers an end-to-end solution for evaluating and mitigating hallucinations in LLMs, featuring automated test set generation, multifaceted benchmarking, and adaptable mitigation strategies. It autom","authors_text":"Adriano Koshiyama, Archish Arun, Cristian Munoz, Emre Kazim, Jonathan Lutch, Mengfei Liang, Philip Treleaven, Zekun Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T16:55:25Z","title":"THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11353","kind":"arxiv","version":3},"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:b7c3ef14f867a20b76e67291fd156796d2e4cd7a44070b26e5664b3dda3a36dc","target":"record","created_at":"2026-07-05T10:02:51Z","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":"317b23600c6d1ad843b11b889836ce8cc0b0f378bb183029c1f83343b315deeb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T16:55:25Z","title_canon_sha256":"e31019d2f6abbaf73ff9dfc5fe980f2e832870357917bf0fb2d9af3ea476fee9"},"schema_version":"1.0","source":{"id":"2409.11353","kind":"arxiv","version":3}},"canonical_sha256":"23e0eecf9ca46200113c69efd66315966984e508bb7893d924c39520c071b24b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23e0eecf9ca46200113c69efd66315966984e508bb7893d924c39520c071b24b","first_computed_at":"2026-07-05T10:02:51.860952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:51.860952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ijOXasM6BXtgWRbUFy1gnKyCCy0AAjfMKeWRKu1NHoCdlCf8e3BHIMPoPqa0gu4S4b00oEwtMTtrD5m9NmbkCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:51.861447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11353","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7c3ef14f867a20b76e67291fd156796d2e4cd7a44070b26e5664b3dda3a36dc","sha256:528dd607bd88c06405fc7ca40cefb6e2037045af37196ba5bbdb415afbcb925d"],"state_sha256":"ffebba5351ffbf445685018260dc7fe8d70abfcde4a90b3e70165d536c7b98f4"}