{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KPDFIT4CXDUI44S7L77TKG6HR2","short_pith_number":"pith:KPDFIT4C","schema_version":"1.0","canonical_sha256":"53c6544f82b8e88e725f5fff351bc78eb4ab951fec6103078ca522272c67e37f","source":{"kind":"arxiv","id":"1805.10561","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Constraint Learning for Structured Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyu Ren, Jiaming Song, Russell Stewart, Stefano Ermon, Volodymyr Kuleshov","submitted_at":"2018-05-27T01:27:28Z","abstract_excerpt":"Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these constraints and using them for supervision, bypassing the difficulty of using domain expertise to manually specify constraints. Learning requires a black-box simulator of structured outputs, which generates valid labels, but need not model their corresponding inputs or the input-label relationship. At training time, we constrain the model to produce outputs"},"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":"1805.10561","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-27T01:27:28Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"0e7003f07e806528dea251c6dd9039ab478fa1dc6420a728f0d28312a5041096","abstract_canon_sha256":"69f16b4dd64c2c216053a2d5e9f494080799be56d4ece7c4b88decefc419334c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:33.620020Z","signature_b64":"gVk2ihxw7mlaeOit8JGNMWBYr9HmX2cD96Nj3cwu8U4WomqmHdSY8cwsfrVhQQRekzmyAGspa5FwZ82AEeN1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53c6544f82b8e88e725f5fff351bc78eb4ab951fec6103078ca522272c67e37f","last_reissued_at":"2026-05-18T00:14:33.619448Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:33.619448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Constraint Learning for Structured Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyu Ren, Jiaming Song, Russell Stewart, Stefano Ermon, Volodymyr Kuleshov","submitted_at":"2018-05-27T01:27:28Z","abstract_excerpt":"Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these constraints and using them for supervision, bypassing the difficulty of using domain expertise to manually specify constraints. Learning requires a black-box simulator of structured outputs, which generates valid labels, but need not model their corresponding inputs or the input-label relationship. At training time, we constrain the model to produce outputs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10561","kind":"arxiv","version":2},"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":"1805.10561","created_at":"2026-05-18T00:14:33.619547+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10561v2","created_at":"2026-05-18T00:14:33.619547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10561","created_at":"2026-05-18T00:14:33.619547+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPDFIT4CXDUI","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPDFIT4CXDUI44S7","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPDFIT4C","created_at":"2026-05-18T12:32:33.847187+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/KPDFIT4CXDUI44S7L77TKG6HR2","json":"https://pith.science/pith/KPDFIT4CXDUI44S7L77TKG6HR2.json","graph_json":"https://pith.science/api/pith-number/KPDFIT4CXDUI44S7L77TKG6HR2/graph.json","events_json":"https://pith.science/api/pith-number/KPDFIT4CXDUI44S7L77TKG6HR2/events.json","paper":"https://pith.science/paper/KPDFIT4C"},"agent_actions":{"view_html":"https://pith.science/pith/KPDFIT4CXDUI44S7L77TKG6HR2","download_json":"https://pith.science/pith/KPDFIT4CXDUI44S7L77TKG6HR2.json","view_paper":"https://pith.science/paper/KPDFIT4C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10561&json=true","fetch_graph":"https://pith.science/api/pith-number/KPDFIT4CXDUI44S7L77TKG6HR2/graph.json","fetch_events":"https://pith.science/api/pith-number/KPDFIT4CXDUI44S7L77TKG6HR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPDFIT4CXDUI44S7L77TKG6HR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPDFIT4CXDUI44S7L77TKG6HR2/action/storage_attestation","attest_author":"https://pith.science/pith/KPDFIT4CXDUI44S7L77TKG6HR2/action/author_attestation","sign_citation":"https://pith.science/pith/KPDFIT4CXDUI44S7L77TKG6HR2/action/citation_signature","submit_replication":"https://pith.science/pith/KPDFIT4CXDUI44S7L77TKG6HR2/action/replication_record"}},"created_at":"2026-05-18T00:14:33.619547+00:00","updated_at":"2026-05-18T00:14:33.619547+00:00"}