{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HA3U425YCRDICMNJFHUZVCAPS5","short_pith_number":"pith:HA3U425Y","schema_version":"1.0","canonical_sha256":"38374e6bb814468131a929e99a880f974989a91804989cfc67eb67a166202730","source":{"kind":"arxiv","id":"2502.15776","version":1},"attestation_state":"computed","paper":{"title":"Logic.py: Bridging the Gap between LLMs and Constraint Solvers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.AI","authors_text":"Pascal Kesseli, Peter O'Hearn, Ricardo Silveira Cabral","submitted_at":"2025-02-17T00:36:54Z","abstract_excerpt":"We present a novel approach to formalise and solve search-based problems using large language models, which significantly improves upon previous state-of-the-art results. We demonstrate the efficacy of this approach on the logic puzzles benchmark ZebraLogicBench. Instead of letting the LLM attempt to directly solve the puzzles, our method prompts the model to formalise the problem in a logic-focused domain-specific language (DSL) called Logic.py. This formalised representation is then solved using a constraint solver, leveraging the strengths of both the language model and the solver. Our appr"},"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":"2502.15776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T00:36:54Z","cross_cats_sorted":["cs.LO"],"title_canon_sha256":"c564ec8a780059088607a342d2bf584c62f27a00da3fea9b0b1201f32259277d","abstract_canon_sha256":"840805c73381d415c6d2465548ea0541a4cf7b1d43b8c28752c3ed9d78291120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:16.190049Z","signature_b64":"K5QhD0zd60y9YH/Dn5GeyOfbPw/BuEcgZk45s1enTp1q7hroVt8h9UhiinqUcZwfaqNZdnh0vV6JulURgBTxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38374e6bb814468131a929e99a880f974989a91804989cfc67eb67a166202730","last_reissued_at":"2026-07-05T10:18:16.189678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:16.189678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logic.py: Bridging the Gap between LLMs and Constraint Solvers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.AI","authors_text":"Pascal Kesseli, Peter O'Hearn, Ricardo Silveira Cabral","submitted_at":"2025-02-17T00:36:54Z","abstract_excerpt":"We present a novel approach to formalise and solve search-based problems using large language models, which significantly improves upon previous state-of-the-art results. We demonstrate the efficacy of this approach on the logic puzzles benchmark ZebraLogicBench. Instead of letting the LLM attempt to directly solve the puzzles, our method prompts the model to formalise the problem in a logic-focused domain-specific language (DSL) called Logic.py. This formalised representation is then solved using a constraint solver, leveraging the strengths of both the language model and the solver. Our appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15776","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/2502.15776/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":"2502.15776","created_at":"2026-07-05T10:18:16.189748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15776v1","created_at":"2026-07-05T10:18:16.189748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15776","created_at":"2026-07-05T10:18:16.189748+00:00"},{"alias_kind":"pith_short_12","alias_value":"HA3U425YCRDI","created_at":"2026-07-05T10:18:16.189748+00:00"},{"alias_kind":"pith_short_16","alias_value":"HA3U425YCRDICMNJ","created_at":"2026-07-05T10:18:16.189748+00:00"},{"alias_kind":"pith_short_8","alias_value":"HA3U425Y","created_at":"2026-07-05T10:18:16.189748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.10249","citing_title":"Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HA3U425YCRDICMNJFHUZVCAPS5","json":"https://pith.science/pith/HA3U425YCRDICMNJFHUZVCAPS5.json","graph_json":"https://pith.science/api/pith-number/HA3U425YCRDICMNJFHUZVCAPS5/graph.json","events_json":"https://pith.science/api/pith-number/HA3U425YCRDICMNJFHUZVCAPS5/events.json","paper":"https://pith.science/paper/HA3U425Y"},"agent_actions":{"view_html":"https://pith.science/pith/HA3U425YCRDICMNJFHUZVCAPS5","download_json":"https://pith.science/pith/HA3U425YCRDICMNJFHUZVCAPS5.json","view_paper":"https://pith.science/paper/HA3U425Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15776&json=true","fetch_graph":"https://pith.science/api/pith-number/HA3U425YCRDICMNJFHUZVCAPS5/graph.json","fetch_events":"https://pith.science/api/pith-number/HA3U425YCRDICMNJFHUZVCAPS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HA3U425YCRDICMNJFHUZVCAPS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HA3U425YCRDICMNJFHUZVCAPS5/action/storage_attestation","attest_author":"https://pith.science/pith/HA3U425YCRDICMNJFHUZVCAPS5/action/author_attestation","sign_citation":"https://pith.science/pith/HA3U425YCRDICMNJFHUZVCAPS5/action/citation_signature","submit_replication":"https://pith.science/pith/HA3U425YCRDICMNJFHUZVCAPS5/action/replication_record"}},"created_at":"2026-07-05T10:18:16.189748+00:00","updated_at":"2026-07-05T10:18:16.189748+00:00"}