{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DTID57NUKKK4TQRHJPBVGTZLT4","short_pith_number":"pith:DTID57NU","schema_version":"1.0","canonical_sha256":"1cd03efdb45295c9c2274bc3534f2b9f1bcbc5515ef6b67757493d1fffbaaa81","source":{"kind":"arxiv","id":"2505.24012","version":1},"attestation_state":"computed","paper":{"title":"Large Language Model Meets Constraint Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandre Bonlarron, Elisabetta De Maria, Florian R\\'egin, Jean-Charles R\\'egin","submitted_at":"2025-05-29T21:18:12Z","abstract_excerpt":"Large Language Models (LLMs) excel at generating fluent text but struggle to enforce external constraints because they generate tokens sequentially without explicit control mechanisms. GenCP addresses this limitation by combining LLM predictions with Constraint Programming (CP) reasoning, formulating text generation as a Constraint Satisfaction Problem (CSP). In this paper, we improve GenCP by integrating Masked Language Models (MLMs) for domain generation, which allows bidirectional constraint propagation that leverages both past and future tokens. This integration bridges the gap between tok"},"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":"2505.24012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T21:18:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"890f778200ab97e64d88b7e604b857d0c3db49a96af62b1ffc59405ecff10199","abstract_canon_sha256":"32c530f86c79697149d73433acfc84e57f108bcd691f1c6fcac990bf3c78cede"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:40.124302Z","signature_b64":"vkKveuKh1HZjBN2sTRltpkMWKOPa3D5ifILbNMqIuytYzl3RDo6924ov8YtAquuOv4TUUaiczzsr8RSXbikEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cd03efdb45295c9c2274bc3534f2b9f1bcbc5515ef6b67757493d1fffbaaa81","last_reissued_at":"2026-07-05T11:12:40.123865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:40.123865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model Meets Constraint Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandre Bonlarron, Elisabetta De Maria, Florian R\\'egin, Jean-Charles R\\'egin","submitted_at":"2025-05-29T21:18:12Z","abstract_excerpt":"Large Language Models (LLMs) excel at generating fluent text but struggle to enforce external constraints because they generate tokens sequentially without explicit control mechanisms. GenCP addresses this limitation by combining LLM predictions with Constraint Programming (CP) reasoning, formulating text generation as a Constraint Satisfaction Problem (CSP). In this paper, we improve GenCP by integrating Masked Language Models (MLMs) for domain generation, which allows bidirectional constraint propagation that leverages both past and future tokens. This integration bridges the gap between tok"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24012","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/2505.24012/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":"2505.24012","created_at":"2026-07-05T11:12:40.123930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24012v1","created_at":"2026-07-05T11:12:40.123930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24012","created_at":"2026-07-05T11:12:40.123930+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTID57NUKKK4","created_at":"2026-07-05T11:12:40.123930+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTID57NUKKK4TQRH","created_at":"2026-07-05T11:12:40.123930+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTID57NU","created_at":"2026-07-05T11:12:40.123930+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/DTID57NUKKK4TQRHJPBVGTZLT4","json":"https://pith.science/pith/DTID57NUKKK4TQRHJPBVGTZLT4.json","graph_json":"https://pith.science/api/pith-number/DTID57NUKKK4TQRHJPBVGTZLT4/graph.json","events_json":"https://pith.science/api/pith-number/DTID57NUKKK4TQRHJPBVGTZLT4/events.json","paper":"https://pith.science/paper/DTID57NU"},"agent_actions":{"view_html":"https://pith.science/pith/DTID57NUKKK4TQRHJPBVGTZLT4","download_json":"https://pith.science/pith/DTID57NUKKK4TQRHJPBVGTZLT4.json","view_paper":"https://pith.science/paper/DTID57NU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24012&json=true","fetch_graph":"https://pith.science/api/pith-number/DTID57NUKKK4TQRHJPBVGTZLT4/graph.json","fetch_events":"https://pith.science/api/pith-number/DTID57NUKKK4TQRHJPBVGTZLT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTID57NUKKK4TQRHJPBVGTZLT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTID57NUKKK4TQRHJPBVGTZLT4/action/storage_attestation","attest_author":"https://pith.science/pith/DTID57NUKKK4TQRHJPBVGTZLT4/action/author_attestation","sign_citation":"https://pith.science/pith/DTID57NUKKK4TQRHJPBVGTZLT4/action/citation_signature","submit_replication":"https://pith.science/pith/DTID57NUKKK4TQRHJPBVGTZLT4/action/replication_record"}},"created_at":"2026-07-05T11:12:40.123930+00:00","updated_at":"2026-07-05T11:12:40.123930+00:00"}