{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7WSBQWVJ2JY3AZUKR7L2IALOOT","short_pith_number":"pith:7WSBQWVJ","schema_version":"1.0","canonical_sha256":"fda4185aa9d271b0668a8fd7a4016e74cdfd79793af8618f388406f93d407e26","source":{"kind":"arxiv","id":"2502.17638","version":1},"attestation_state":"computed","paper":{"title":"Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Manav Kant, Manuj Kant, Marzieh Nabi, Megan Ma, Roland Scharrer, Sareh Nabi","submitted_at":"2025-02-24T20:38:17Z","abstract_excerpt":"Legal services rely heavily on text processing. While large language models (LLMs) show promise, their application in legal contexts demands higher accuracy, repeatability, and transparency. Logic programs, by encoding legal concepts as structured rules and facts, offer reliable automation, but require sophisticated text extraction. We propose a neuro-symbolic approach that integrates LLMs' natural language understanding with logic-based reasoning to address these limitations.\n  As a legal document case study, we applied neuro-symbolic AI to coverage-related queries in insurance contracts usin"},"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":"2502.17638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-02-24T20:38:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aee3702a83be7786b486a520307fd3a20ca4de88117ad662c1b15be3bbb2ba5a","abstract_canon_sha256":"53ae26534e7a82c6056936ea90b99e64050e2c11ae67ff34dc5bd9566809476d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:41.685113Z","signature_b64":"AlQuadLqOpTREMxfTZmmeVJdKU2mzIgK7PbLn30woymYVm2h7OHugYm4kMErE+Ctdq3+pTGJ2RpNCQGQK8q+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fda4185aa9d271b0668a8fd7a4016e74cdfd79793af8618f388406f93d407e26","last_reissued_at":"2026-07-05T10:19:41.684614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:41.684614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Manav Kant, Manuj Kant, Marzieh Nabi, Megan Ma, Roland Scharrer, Sareh Nabi","submitted_at":"2025-02-24T20:38:17Z","abstract_excerpt":"Legal services rely heavily on text processing. While large language models (LLMs) show promise, their application in legal contexts demands higher accuracy, repeatability, and transparency. Logic programs, by encoding legal concepts as structured rules and facts, offer reliable automation, but require sophisticated text extraction. We propose a neuro-symbolic approach that integrates LLMs' natural language understanding with logic-based reasoning to address these limitations.\n  As a legal document case study, we applied neuro-symbolic AI to coverage-related queries in insurance contracts usin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17638","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/2502.17638/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":"2502.17638","created_at":"2026-07-05T10:19:41.684676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17638v1","created_at":"2026-07-05T10:19:41.684676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17638","created_at":"2026-07-05T10:19:41.684676+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WSBQWVJ2JY3","created_at":"2026-07-05T10:19:41.684676+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WSBQWVJ2JY3AZUK","created_at":"2026-07-05T10:19:41.684676+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WSBQWVJ","created_at":"2026-07-05T10:19:41.684676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23913","citing_title":"Closing the Loop: Formally Verified Law as a Reward Signal for Self-Improving Legal AI","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.16118","citing_title":"Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26530","citing_title":"Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16280","citing_title":"Beyond Imperfect Alternatives with Rulemapping: A Neuro-Symbolic Case Study on Online Hate Speech","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15599","citing_title":"Autonomous Business System via Neuro-symbolic AI","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14607","citing_title":"GDPR Auto-Formalization with AI Agents and Human Verification","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WSBQWVJ2JY3AZUKR7L2IALOOT","json":"https://pith.science/pith/7WSBQWVJ2JY3AZUKR7L2IALOOT.json","graph_json":"https://pith.science/api/pith-number/7WSBQWVJ2JY3AZUKR7L2IALOOT/graph.json","events_json":"https://pith.science/api/pith-number/7WSBQWVJ2JY3AZUKR7L2IALOOT/events.json","paper":"https://pith.science/paper/7WSBQWVJ"},"agent_actions":{"view_html":"https://pith.science/pith/7WSBQWVJ2JY3AZUKR7L2IALOOT","download_json":"https://pith.science/pith/7WSBQWVJ2JY3AZUKR7L2IALOOT.json","view_paper":"https://pith.science/paper/7WSBQWVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17638&json=true","fetch_graph":"https://pith.science/api/pith-number/7WSBQWVJ2JY3AZUKR7L2IALOOT/graph.json","fetch_events":"https://pith.science/api/pith-number/7WSBQWVJ2JY3AZUKR7L2IALOOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WSBQWVJ2JY3AZUKR7L2IALOOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WSBQWVJ2JY3AZUKR7L2IALOOT/action/storage_attestation","attest_author":"https://pith.science/pith/7WSBQWVJ2JY3AZUKR7L2IALOOT/action/author_attestation","sign_citation":"https://pith.science/pith/7WSBQWVJ2JY3AZUKR7L2IALOOT/action/citation_signature","submit_replication":"https://pith.science/pith/7WSBQWVJ2JY3AZUKR7L2IALOOT/action/replication_record"}},"created_at":"2026-07-05T10:19:41.684676+00:00","updated_at":"2026-07-05T10:19:41.684676+00:00"}