{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GOLNWU4IHQFEOOTL44MPJGFGDS","short_pith_number":"pith:GOLNWU4I","schema_version":"1.0","canonical_sha256":"3396db53883c0a473a6be718f498a61ca67cad042f8d69b0cb0985f1efaf2b65","source":{"kind":"arxiv","id":"2606.00301","version":1},"attestation_state":"computed","paper":{"title":"FLaG: Fine-Grained Latent Grouping for Hallucination Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haobo Wang, Jiaqi Hu, Liyao Li, Muzhi Zhu, Sean Du, Wentao Ye, Xiaomeng Hu, Zhanming Shen, Zhiqing Xiao","submitted_at":"2026-05-29T19:30:39Z","abstract_excerpt":"Hallucinations in large language models (LLMs) arise from heterogeneous failure mechanisms, making reliable detection difficult for any single global uncertainty score. In this work, we formulate hallucination detection as a mechanism-aware evidence aggregation problem, where diverse representation- and token-level signals must be interpreted under multiple latent explanations. We propose FLaG, a lightweight hallucination detection framework that models correctness through a set of latent evidence groups. Each instance is softly associated with multiple groups via an energy-based routing mecha"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.00301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T19:30:39Z","cross_cats_sorted":[],"title_canon_sha256":"ac8845def2c6a0421ea0066097e06dd1383ca9355c10b5b97f3e5cb7d8a00376","abstract_canon_sha256":"393fe6c02e76d9b18090f3ded0352549df408223088ea14c76cbfdea6e85648f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:51.086381Z","signature_b64":"b8dicNJ/iUCyk077/whJJrtC4uJgXFqroV19oLL2XKPPyUEk/y6AeDnaVGBWqsNmUi4DxJvm9I30eHO6ZoCjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3396db53883c0a473a6be718f498a61ca67cad042f8d69b0cb0985f1efaf2b65","last_reissued_at":"2026-06-02T01:03:51.085816Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:51.085816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLaG: Fine-Grained Latent Grouping for Hallucination Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haobo Wang, Jiaqi Hu, Liyao Li, Muzhi Zhu, Sean Du, Wentao Ye, Xiaomeng Hu, Zhanming Shen, Zhiqing Xiao","submitted_at":"2026-05-29T19:30:39Z","abstract_excerpt":"Hallucinations in large language models (LLMs) arise from heterogeneous failure mechanisms, making reliable detection difficult for any single global uncertainty score. In this work, we formulate hallucination detection as a mechanism-aware evidence aggregation problem, where diverse representation- and token-level signals must be interpreted under multiple latent explanations. We propose FLaG, a lightweight hallucination detection framework that models correctness through a set of latent evidence groups. Each instance is softly associated with multiple groups via an energy-based routing mecha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00301","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/2606.00301/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.00301","created_at":"2026-06-02T01:03:51.085898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00301v1","created_at":"2026-06-02T01:03:51.085898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00301","created_at":"2026-06-02T01:03:51.085898+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOLNWU4IHQFE","created_at":"2026-06-02T01:03:51.085898+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOLNWU4IHQFEOOTL","created_at":"2026-06-02T01:03:51.085898+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOLNWU4I","created_at":"2026-06-02T01:03:51.085898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOLNWU4IHQFEOOTL44MPJGFGDS","json":"https://pith.science/pith/GOLNWU4IHQFEOOTL44MPJGFGDS.json","graph_json":"https://pith.science/api/pith-number/GOLNWU4IHQFEOOTL44MPJGFGDS/graph.json","events_json":"https://pith.science/api/pith-number/GOLNWU4IHQFEOOTL44MPJGFGDS/events.json","paper":"https://pith.science/paper/GOLNWU4I"},"agent_actions":{"view_html":"https://pith.science/pith/GOLNWU4IHQFEOOTL44MPJGFGDS","download_json":"https://pith.science/pith/GOLNWU4IHQFEOOTL44MPJGFGDS.json","view_paper":"https://pith.science/paper/GOLNWU4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00301&json=true","fetch_graph":"https://pith.science/api/pith-number/GOLNWU4IHQFEOOTL44MPJGFGDS/graph.json","fetch_events":"https://pith.science/api/pith-number/GOLNWU4IHQFEOOTL44MPJGFGDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOLNWU4IHQFEOOTL44MPJGFGDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOLNWU4IHQFEOOTL44MPJGFGDS/action/storage_attestation","attest_author":"https://pith.science/pith/GOLNWU4IHQFEOOTL44MPJGFGDS/action/author_attestation","sign_citation":"https://pith.science/pith/GOLNWU4IHQFEOOTL44MPJGFGDS/action/citation_signature","submit_replication":"https://pith.science/pith/GOLNWU4IHQFEOOTL44MPJGFGDS/action/replication_record"}},"created_at":"2026-06-02T01:03:51.085898+00:00","updated_at":"2026-06-02T01:03:51.085898+00:00"}