{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O7IQE3Q4TPAMBUPJG5SEL6MKPE","short_pith_number":"pith:O7IQE3Q4","schema_version":"1.0","canonical_sha256":"77d1026e1c9bc0c0d1e9376445f98a7939f5edccddb1b91cce9a0de8b2d97213","source":{"kind":"arxiv","id":"2509.10753","version":1},"attestation_state":"computed","paper":{"title":"HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brian K. Tran, Geigh Zollicoffer, Manish Bhattarai, Minh Vu, Nhat Hoang-Xuan, Syed A. Shah","submitted_at":"2025-09-12T23:49:52Z","abstract_excerpt":"Large Language Models (LLMs) exhibit impressive reasoning and question-answering capabilities. However, they often produce inaccurate or unreliable content known as hallucinations. This unreliability significantly limits their deployment in high-stakes applications. Thus, there is a growing need for a general-purpose method to detect hallucinations in LLMs. In this work, we introduce HalluField, a novel field-theoretic approach for hallucination detection based on a parametrized variational principle and thermodynamics. Inspired by thermodynamics, HalluField models an LLM's response to a given"},"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":"2509.10753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-12T23:49:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a57d05446716ee214f714cb4ba2e938237f341c0512ad2ce8020c459719b5242","abstract_canon_sha256":"3b722a8c02b8abe4684ad2cf0ee30a51a247c880edc77ce5c994d1f26bbb5cc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:27.428363Z","signature_b64":"SnJRCKiybi7c2MXKhsyWzSyUPcElKkblQPeobpqgVawFiaMG+gz22PhFeAtNNSAMAa+LBQKzm7k+99mLdMztBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77d1026e1c9bc0c0d1e9376445f98a7939f5edccddb1b91cce9a0de8b2d97213","last_reissued_at":"2026-07-05T12:11:27.427793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:27.427793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brian K. Tran, Geigh Zollicoffer, Manish Bhattarai, Minh Vu, Nhat Hoang-Xuan, Syed A. Shah","submitted_at":"2025-09-12T23:49:52Z","abstract_excerpt":"Large Language Models (LLMs) exhibit impressive reasoning and question-answering capabilities. However, they often produce inaccurate or unreliable content known as hallucinations. This unreliability significantly limits their deployment in high-stakes applications. Thus, there is a growing need for a general-purpose method to detect hallucinations in LLMs. In this work, we introduce HalluField, a novel field-theoretic approach for hallucination detection based on a parametrized variational principle and thermodynamics. Inspired by thermodynamics, HalluField models an LLM's response to a given"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10753","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/2509.10753/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":"2509.10753","created_at":"2026-07-05T12:11:27.427851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.10753v1","created_at":"2026-07-05T12:11:27.427851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10753","created_at":"2026-07-05T12:11:27.427851+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7IQE3Q4TPAM","created_at":"2026-07-05T12:11:27.427851+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7IQE3Q4TPAMBUPJ","created_at":"2026-07-05T12:11:27.427851+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7IQE3Q4","created_at":"2026-07-05T12:11:27.427851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25634","citing_title":"The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7IQE3Q4TPAMBUPJG5SEL6MKPE","json":"https://pith.science/pith/O7IQE3Q4TPAMBUPJG5SEL6MKPE.json","graph_json":"https://pith.science/api/pith-number/O7IQE3Q4TPAMBUPJG5SEL6MKPE/graph.json","events_json":"https://pith.science/api/pith-number/O7IQE3Q4TPAMBUPJG5SEL6MKPE/events.json","paper":"https://pith.science/paper/O7IQE3Q4"},"agent_actions":{"view_html":"https://pith.science/pith/O7IQE3Q4TPAMBUPJG5SEL6MKPE","download_json":"https://pith.science/pith/O7IQE3Q4TPAMBUPJG5SEL6MKPE.json","view_paper":"https://pith.science/paper/O7IQE3Q4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.10753&json=true","fetch_graph":"https://pith.science/api/pith-number/O7IQE3Q4TPAMBUPJG5SEL6MKPE/graph.json","fetch_events":"https://pith.science/api/pith-number/O7IQE3Q4TPAMBUPJG5SEL6MKPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7IQE3Q4TPAMBUPJG5SEL6MKPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7IQE3Q4TPAMBUPJG5SEL6MKPE/action/storage_attestation","attest_author":"https://pith.science/pith/O7IQE3Q4TPAMBUPJG5SEL6MKPE/action/author_attestation","sign_citation":"https://pith.science/pith/O7IQE3Q4TPAMBUPJG5SEL6MKPE/action/citation_signature","submit_replication":"https://pith.science/pith/O7IQE3Q4TPAMBUPJG5SEL6MKPE/action/replication_record"}},"created_at":"2026-07-05T12:11:27.427851+00:00","updated_at":"2026-07-05T12:11:27.427851+00:00"}