{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZPQ2YBXZ3X6MIJMQVNH7OAASH7","short_pith_number":"pith:ZPQ2YBXZ","schema_version":"1.0","canonical_sha256":"cbe1ac06f9ddfcc42590ab4ff700123fe437d5af8d88623b4b352b0ad87075f3","source":{"kind":"arxiv","id":"1802.03685","version":4},"attestation_state":"computed","paper":{"title":"Learning a SAT Solver from Single-Bit Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Benedikt B\\\"unz, Daniel Selsam, David L. Dill, Leonardo de Moura, Matthew Lamm, Percy Liang","submitted_at":"2018-02-11T03:04:28Z","abstract_excerpt":"We present NeuroSAT, a message passing neural network that learns to solve SAT problems after only being trained as a classifier to predict satisfiability. Although it is not competitive with state-of-the-art SAT solvers, NeuroSAT can solve problems that are substantially larger and more difficult than it ever saw during training by simply running for more iterations. Moreover, NeuroSAT generalizes to novel distributions; after training only on random SAT problems, at test time it can solve SAT problems encoding graph coloring, clique detection, dominating set, and vertex cover problems, all o"},"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":"1802.03685","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-11T03:04:28Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"fc2711353c7875eab9ce6e656bcfe91903aeb37a072bebeadcc559d9b4ec1af7","abstract_canon_sha256":"dfb0d51307eca6bffb7b5ff86b0cdc1d954aeec69915781dc083e5e55b299e3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:34.168426Z","signature_b64":"bfg/nonoCS3Nx6yL+gjs64jn+lZG9LdOnzdJRGLGUezLumMfCUy44eVTYSuHpjOssQqCRv5rbmFQtcFjVII8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbe1ac06f9ddfcc42590ab4ff700123fe437d5af8d88623b4b352b0ad87075f3","last_reissued_at":"2026-05-17T23:51:34.167749Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:34.167749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a SAT Solver from Single-Bit Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Benedikt B\\\"unz, Daniel Selsam, David L. Dill, Leonardo de Moura, Matthew Lamm, Percy Liang","submitted_at":"2018-02-11T03:04:28Z","abstract_excerpt":"We present NeuroSAT, a message passing neural network that learns to solve SAT problems after only being trained as a classifier to predict satisfiability. Although it is not competitive with state-of-the-art SAT solvers, NeuroSAT can solve problems that are substantially larger and more difficult than it ever saw during training by simply running for more iterations. Moreover, NeuroSAT generalizes to novel distributions; after training only on random SAT problems, at test time it can solve SAT problems encoding graph coloring, clique detection, dominating set, and vertex cover problems, all o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03685","kind":"arxiv","version":4},"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":"1802.03685","created_at":"2026-05-17T23:51:34.167838+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03685v4","created_at":"2026-05-17T23:51:34.167838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03685","created_at":"2026-05-17T23:51:34.167838+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPQ2YBXZ3X6M","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPQ2YBXZ3X6MIJMQ","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPQ2YBXZ","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.23395","citing_title":"Convex Compositional Reasoning Models","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2009.03393","citing_title":"Generative Language Modeling for Automated Theorem Proving","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16632","citing_title":"Learning How to Cube","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"1806.01261","citing_title":"Relational inductive biases, deep learning, and graph networks","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27324","citing_title":"Q3SAT-GPT: A Generative Model for Discovering Quantum Circuits for the 3-SAT Problem","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18839","citing_title":"One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models","ref_index":212,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPQ2YBXZ3X6MIJMQVNH7OAASH7","json":"https://pith.science/pith/ZPQ2YBXZ3X6MIJMQVNH7OAASH7.json","graph_json":"https://pith.science/api/pith-number/ZPQ2YBXZ3X6MIJMQVNH7OAASH7/graph.json","events_json":"https://pith.science/api/pith-number/ZPQ2YBXZ3X6MIJMQVNH7OAASH7/events.json","paper":"https://pith.science/paper/ZPQ2YBXZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZPQ2YBXZ3X6MIJMQVNH7OAASH7","download_json":"https://pith.science/pith/ZPQ2YBXZ3X6MIJMQVNH7OAASH7.json","view_paper":"https://pith.science/paper/ZPQ2YBXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03685&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPQ2YBXZ3X6MIJMQVNH7OAASH7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPQ2YBXZ3X6MIJMQVNH7OAASH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPQ2YBXZ3X6MIJMQVNH7OAASH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPQ2YBXZ3X6MIJMQVNH7OAASH7/action/storage_attestation","attest_author":"https://pith.science/pith/ZPQ2YBXZ3X6MIJMQVNH7OAASH7/action/author_attestation","sign_citation":"https://pith.science/pith/ZPQ2YBXZ3X6MIJMQVNH7OAASH7/action/citation_signature","submit_replication":"https://pith.science/pith/ZPQ2YBXZ3X6MIJMQVNH7OAASH7/action/replication_record"}},"created_at":"2026-05-17T23:51:34.167838+00:00","updated_at":"2026-05-17T23:51:34.167838+00:00"}