{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:27QCRUSX4DX6K2V7EMAV2K2T44","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":"e0fbd689b25c38c2f1b4af1db69212633fac1e1827734f4926870eeb56c8a105","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:30:05Z","title_canon_sha256":"79b204d11bacde9c7bca0f4aafda2516e2ec7c3f1d80adb6109093abe552e514"},"schema_version":"1.0","source":{"id":"2406.11277","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11277","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11277v1","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11277","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"pith_short_12","alias_value":"27QCRUSX4DX6","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"pith_short_16","alias_value":"27QCRUSX4DX6K2V7","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"pith_short_8","alias_value":"27QCRUSX","created_at":"2026-07-05T08:32:51Z"}],"graph_snapshots":[{"event_id":"sha256:22f5f8001b50b60bafd51e92632f9679216d05992972450468a124c8746f4e74","target":"graph","created_at":"2026-07-05T08:32:51Z","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/2406.11277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucination detection is a challenging task for large language models (LLMs), and existing studies heavily rely on powerful closed-source LLMs such as GPT-4. In this paper, we propose an autonomous LLM-based agent framework, called HaluAgent, which enables relatively smaller LLMs (e.g. Baichuan2-Chat 7B) to actively select suitable tools for detecting multiple hallucination types such as text, code, and mathematical expression. In HaluAgent, we integrate the LLM, multi-functional toolbox, and design a fine-grained three-stage detection framework along with memory mechanism. To facilitate the","authors_text":"Di Zhang, Fuzheng Zhang, Hongzhi Zhang, Ji-Rong Wen, Junyi Li, Kun Gai, Wayne Xin Zhao, Xiaoxue Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:30:05Z","title":"Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11277","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":"sha256:0dac9ce24d3de7522723923796e82807bdfce3eae9b5699823b6cc350263521e","target":"record","created_at":"2026-07-05T08:32:51Z","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":"e0fbd689b25c38c2f1b4af1db69212633fac1e1827734f4926870eeb56c8a105","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T07:30:05Z","title_canon_sha256":"79b204d11bacde9c7bca0f4aafda2516e2ec7c3f1d80adb6109093abe552e514"},"schema_version":"1.0","source":{"id":"2406.11277","kind":"arxiv","version":1}},"canonical_sha256":"d7e028d257e0efe56abf23015d2b53e73f21487a1d0d684335852ddd13b64bde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7e028d257e0efe56abf23015d2b53e73f21487a1d0d684335852ddd13b64bde","first_computed_at":"2026-07-05T08:32:51.277061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:51.277061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pNOiXTOiLuKz0FspgE5Mz6uf0hVFPw6OodmB+DCQrP0qverhbhLKa2TatKqp52xldNOrvsUu+eEkLVHV4T9lCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:51.277553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11277","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0dac9ce24d3de7522723923796e82807bdfce3eae9b5699823b6cc350263521e","sha256:22f5f8001b50b60bafd51e92632f9679216d05992972450468a124c8746f4e74"],"state_sha256":"803b32f041c3e2a751259f6edbc3f9cc21ff026cb675dfaa29951218267407bd"}