{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PVBB52MWWJHDAEGJI5K26BEUOZ","short_pith_number":"pith:PVBB52MW","schema_version":"1.0","canonical_sha256":"7d421ee996b24e3010c94755af04947660cca86e5364746fc232e6d94d65e53f","source":{"kind":"arxiv","id":"2307.04347","version":1},"attestation_state":"computed","paper":{"title":"Injecting Logical Constraints into Neural Networks via Straight-Through Estimators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Chiyoun Park, Joohyung Lee, Zhun Yang","submitted_at":"2023-07-10T05:12:05Z","abstract_excerpt":"Injecting discrete logical constraints into neural network learning is one of the main challenges in neuro-symbolic AI. We find that a straight-through-estimator, a method introduced to train binary neural networks, could effectively be applied to incorporate logical constraints into neural network learning. More specifically, we design a systematic way to represent discrete logical constraints as a loss function; minimizing this loss using gradient descent via a straight-through-estimator updates the neural network's weights in the direction that the binarized outputs satisfy the logical cons"},"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":"2307.04347","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-10T05:12:05Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"36c7f296beef63024f703a5a6dc99fded532f01840e0608cb3e68d426bb4c9cc","abstract_canon_sha256":"bc4130882511608b87a50f79039e357574d49e1b59a55bb4d8e0ad6223b15706"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:11.976996Z","signature_b64":"CYsoPRRFqfDFs0FZ5fv9E3jH3+nQiOuedjMJ1E0Ie4gNpfDwBdmDsVaOix2QuCVrKR6Cp41y1JCNRr7iHiUJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d421ee996b24e3010c94755af04947660cca86e5364746fc232e6d94d65e53f","last_reissued_at":"2026-07-05T06:29:11.976585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:11.976585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Injecting Logical Constraints into Neural Networks via Straight-Through Estimators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Chiyoun Park, Joohyung Lee, Zhun Yang","submitted_at":"2023-07-10T05:12:05Z","abstract_excerpt":"Injecting discrete logical constraints into neural network learning is one of the main challenges in neuro-symbolic AI. We find that a straight-through-estimator, a method introduced to train binary neural networks, could effectively be applied to incorporate logical constraints into neural network learning. More specifically, we design a systematic way to represent discrete logical constraints as a loss function; minimizing this loss using gradient descent via a straight-through-estimator updates the neural network's weights in the direction that the binarized outputs satisfy the logical cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04347","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/2307.04347/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":"2307.04347","created_at":"2026-07-05T06:29:11.976675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04347v1","created_at":"2026-07-05T06:29:11.976675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04347","created_at":"2026-07-05T06:29:11.976675+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVBB52MWWJHD","created_at":"2026-07-05T06:29:11.976675+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVBB52MWWJHDAEGJ","created_at":"2026-07-05T06:29:11.976675+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVBB52MW","created_at":"2026-07-05T06:29:11.976675+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/PVBB52MWWJHDAEGJI5K26BEUOZ","json":"https://pith.science/pith/PVBB52MWWJHDAEGJI5K26BEUOZ.json","graph_json":"https://pith.science/api/pith-number/PVBB52MWWJHDAEGJI5K26BEUOZ/graph.json","events_json":"https://pith.science/api/pith-number/PVBB52MWWJHDAEGJI5K26BEUOZ/events.json","paper":"https://pith.science/paper/PVBB52MW"},"agent_actions":{"view_html":"https://pith.science/pith/PVBB52MWWJHDAEGJI5K26BEUOZ","download_json":"https://pith.science/pith/PVBB52MWWJHDAEGJI5K26BEUOZ.json","view_paper":"https://pith.science/paper/PVBB52MW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04347&json=true","fetch_graph":"https://pith.science/api/pith-number/PVBB52MWWJHDAEGJI5K26BEUOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PVBB52MWWJHDAEGJI5K26BEUOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVBB52MWWJHDAEGJI5K26BEUOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVBB52MWWJHDAEGJI5K26BEUOZ/action/storage_attestation","attest_author":"https://pith.science/pith/PVBB52MWWJHDAEGJI5K26BEUOZ/action/author_attestation","sign_citation":"https://pith.science/pith/PVBB52MWWJHDAEGJI5K26BEUOZ/action/citation_signature","submit_replication":"https://pith.science/pith/PVBB52MWWJHDAEGJI5K26BEUOZ/action/replication_record"}},"created_at":"2026-07-05T06:29:11.976675+00:00","updated_at":"2026-07-05T06:29:11.976675+00:00"}