{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LM3ZBYGFES55I4IZ2BIPLXSLZZ","short_pith_number":"pith:LM3ZBYGF","schema_version":"1.0","canonical_sha256":"5b3790e0c524bbd47119d050f5de4bce5e9cafaa7f06ef13c4b0ab597bdc3893","source":{"kind":"arxiv","id":"2502.09212","version":1},"attestation_state":"computed","paper":{"title":"LP-LM: No Hallucinations in Question Answering with Logic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Katherine Wu, Yanhong A. Liu","submitted_at":"2025-02-13T11:48:31Z","abstract_excerpt":"Large language models (LLMs) are able to generate human-like responses to user queries. However, LLMs exhibit inherent limitations, especially because they hallucinate. This paper introduces LP-LM, a system that grounds answers to questions in known facts contained in a knowledge base (KB), facilitated through semantic parsing in Prolog, and always produces answers that are reliable.\n  LP-LM generates a most probable constituency parse tree along with a corresponding Prolog term for an input question via Prolog definite clause grammar (DCG) parsing. The term is then executed against a KB of na"},"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":"2502.09212","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-13T11:48:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"96c2291a944d64b8f5d4d44bc3dfb24c709cd3ef80a20a108bcf424103fc1c7c","abstract_canon_sha256":"4dbca8e93fa00998142eaecfbc86795cbeb4e47cc26de9ca7a6fd427a62ab86d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:53.813404Z","signature_b64":"0pSFklmhwzqzzbcYSRAI4Q7xwqkyzpcMaDvHE3cNm1JYRufP11jEAR92nhzuWHHXFbXAsAh4YvETZXZ826PJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b3790e0c524bbd47119d050f5de4bce5e9cafaa7f06ef13c4b0ab597bdc3893","last_reissued_at":"2026-07-05T10:13:53.812922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:53.812922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LP-LM: No Hallucinations in Question Answering with Logic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Katherine Wu, Yanhong A. Liu","submitted_at":"2025-02-13T11:48:31Z","abstract_excerpt":"Large language models (LLMs) are able to generate human-like responses to user queries. However, LLMs exhibit inherent limitations, especially because they hallucinate. This paper introduces LP-LM, a system that grounds answers to questions in known facts contained in a knowledge base (KB), facilitated through semantic parsing in Prolog, and always produces answers that are reliable.\n  LP-LM generates a most probable constituency parse tree along with a corresponding Prolog term for an input question via Prolog definite clause grammar (DCG) parsing. The term is then executed against a KB of na"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09212","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/2502.09212/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":"2502.09212","created_at":"2026-07-05T10:13:53.812982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09212v1","created_at":"2026-07-05T10:13:53.812982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09212","created_at":"2026-07-05T10:13:53.812982+00:00"},{"alias_kind":"pith_short_12","alias_value":"LM3ZBYGFES55","created_at":"2026-07-05T10:13:53.812982+00:00"},{"alias_kind":"pith_short_16","alias_value":"LM3ZBYGFES55I4IZ","created_at":"2026-07-05T10:13:53.812982+00:00"},{"alias_kind":"pith_short_8","alias_value":"LM3ZBYGF","created_at":"2026-07-05T10:13:53.812982+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/LM3ZBYGFES55I4IZ2BIPLXSLZZ","json":"https://pith.science/pith/LM3ZBYGFES55I4IZ2BIPLXSLZZ.json","graph_json":"https://pith.science/api/pith-number/LM3ZBYGFES55I4IZ2BIPLXSLZZ/graph.json","events_json":"https://pith.science/api/pith-number/LM3ZBYGFES55I4IZ2BIPLXSLZZ/events.json","paper":"https://pith.science/paper/LM3ZBYGF"},"agent_actions":{"view_html":"https://pith.science/pith/LM3ZBYGFES55I4IZ2BIPLXSLZZ","download_json":"https://pith.science/pith/LM3ZBYGFES55I4IZ2BIPLXSLZZ.json","view_paper":"https://pith.science/paper/LM3ZBYGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09212&json=true","fetch_graph":"https://pith.science/api/pith-number/LM3ZBYGFES55I4IZ2BIPLXSLZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LM3ZBYGFES55I4IZ2BIPLXSLZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LM3ZBYGFES55I4IZ2BIPLXSLZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LM3ZBYGFES55I4IZ2BIPLXSLZZ/action/storage_attestation","attest_author":"https://pith.science/pith/LM3ZBYGFES55I4IZ2BIPLXSLZZ/action/author_attestation","sign_citation":"https://pith.science/pith/LM3ZBYGFES55I4IZ2BIPLXSLZZ/action/citation_signature","submit_replication":"https://pith.science/pith/LM3ZBYGFES55I4IZ2BIPLXSLZZ/action/replication_record"}},"created_at":"2026-07-05T10:13:53.812982+00:00","updated_at":"2026-07-05T10:13:53.812982+00:00"}