{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DNY5AXTXHHHOMXKCXR2PCTX3PS","short_pith_number":"pith:DNY5AXTX","schema_version":"1.0","canonical_sha256":"1b71d05e7739cee65d42bc74f14efb7cb85d4cfde92543dbb6f6dedf2f2f4d8a","source":{"kind":"arxiv","id":"1905.12149","version":1},"attestation_state":"computed","paper":{"title":"SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bryan Wilder, Po-Wei Wang, Priya L. Donti, Zico Kolter","submitted_at":"2019-05-29T00:47:35Z","abstract_excerpt":"Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems. In this paper, we propose a new direction toward this goal by introducing a differentiable (smoothed) maximum satisfiability (MAXSAT) solver that can be integrated into the loop of larger deep learning systems. Our (approximate) solver is based upon a fast coordinate descent approach to solving the semidefinite program (SDP) associated with the MAXSAT problem. We show how to analytically differentiate through the solution to this SDP and efficiently solve the associated backward pass. W"},"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":"1905.12149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T00:47:35Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"82caba2a83e493e6ab2e9cb088cebeb4a16b932cf7b7a3db800ab7a189f55a6a","abstract_canon_sha256":"17b173e7f682bf416c95a4c5887ac984758b17829010b140d563d6542aeb575d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:47.019303Z","signature_b64":"+yi+hUW5csxWbnYvHBrZySUjWBtb+N99ZJHRdgbYWD4iBc7eoaBrUOIGOn3p4KsL1TiJdwP78YBExHLD7B3ZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b71d05e7739cee65d42bc74f14efb7cb85d4cfde92543dbb6f6dedf2f2f4d8a","last_reissued_at":"2026-05-17T23:44:47.018823Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:47.018823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bryan Wilder, Po-Wei Wang, Priya L. Donti, Zico Kolter","submitted_at":"2019-05-29T00:47:35Z","abstract_excerpt":"Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems. In this paper, we propose a new direction toward this goal by introducing a differentiable (smoothed) maximum satisfiability (MAXSAT) solver that can be integrated into the loop of larger deep learning systems. Our (approximate) solver is based upon a fast coordinate descent approach to solving the semidefinite program (SDP) associated with the MAXSAT problem. We show how to analytically differentiate through the solution to this SDP and efficiently solve the associated backward pass. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12149","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":""},"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":"1905.12149","created_at":"2026-05-17T23:44:47.018896+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12149v1","created_at":"2026-05-17T23:44:47.018896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12149","created_at":"2026-05-17T23:44:47.018896+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNY5AXTXHHHO","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNY5AXTXHHHOMXKC","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNY5AXTX","created_at":"2026-05-18T12:33:15.570797+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/DNY5AXTXHHHOMXKCXR2PCTX3PS","json":"https://pith.science/pith/DNY5AXTXHHHOMXKCXR2PCTX3PS.json","graph_json":"https://pith.science/api/pith-number/DNY5AXTXHHHOMXKCXR2PCTX3PS/graph.json","events_json":"https://pith.science/api/pith-number/DNY5AXTXHHHOMXKCXR2PCTX3PS/events.json","paper":"https://pith.science/paper/DNY5AXTX"},"agent_actions":{"view_html":"https://pith.science/pith/DNY5AXTXHHHOMXKCXR2PCTX3PS","download_json":"https://pith.science/pith/DNY5AXTXHHHOMXKCXR2PCTX3PS.json","view_paper":"https://pith.science/paper/DNY5AXTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12149&json=true","fetch_graph":"https://pith.science/api/pith-number/DNY5AXTXHHHOMXKCXR2PCTX3PS/graph.json","fetch_events":"https://pith.science/api/pith-number/DNY5AXTXHHHOMXKCXR2PCTX3PS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNY5AXTXHHHOMXKCXR2PCTX3PS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNY5AXTXHHHOMXKCXR2PCTX3PS/action/storage_attestation","attest_author":"https://pith.science/pith/DNY5AXTXHHHOMXKCXR2PCTX3PS/action/author_attestation","sign_citation":"https://pith.science/pith/DNY5AXTXHHHOMXKCXR2PCTX3PS/action/citation_signature","submit_replication":"https://pith.science/pith/DNY5AXTXHHHOMXKCXR2PCTX3PS/action/replication_record"}},"created_at":"2026-05-17T23:44:47.018896+00:00","updated_at":"2026-05-17T23:44:47.018896+00:00"}