{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JEY7F7DVGTIJYIHTGBZW7LPEFW","short_pith_number":"pith:JEY7F7DV","schema_version":"1.0","canonical_sha256":"4931f2fc7534d09c20f330736fade42d8457b081210a26a87a635915b45e4801","source":{"kind":"arxiv","id":"2208.09046","version":2},"attestation_state":"computed","paper":{"title":"Self-Supervised Primal-Dual Learning for Constrained Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Pascal Van Hentenryck, Seonho Park","submitted_at":"2022-08-18T20:07:10Z","abstract_excerpt":"This paper studies how to train machine-learning models that directly approximate the optimal solutions of constrained optimization problems. This is an empirical risk minimization under constraints, which is challenging as training must balance optimality and feasibility conditions. Supervised learning methods often approach this challenge by training the model on a large collection of pre-solved instances. This paper takes a different route and proposes the idea of Primal-Dual Learning (PDL), a self-supervised training method that does not require a set of pre-solved instances or an optimiza"},"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":"2208.09046","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-18T20:07:10Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"8a0ac5c016eafcbe299ac1edaed2c0ba86a313315dd9da02afb4e049cad290fb","abstract_canon_sha256":"b1637a900de00204284017c1b2f6ed75e98c564677068eb79ee6e921d77c8c03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:48.648455Z","signature_b64":"BbmgbCi7brZBeA2mr9bNqlyHZRuaCjA7COJdyy57naO7YrDyeST9yaHt2u1tqSV5kFe7GUCMuPOVk4FJfIHvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4931f2fc7534d09c20f330736fade42d8457b081210a26a87a635915b45e4801","last_reissued_at":"2026-07-05T05:18:48.647959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:48.647959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Primal-Dual Learning for Constrained Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Pascal Van Hentenryck, Seonho Park","submitted_at":"2022-08-18T20:07:10Z","abstract_excerpt":"This paper studies how to train machine-learning models that directly approximate the optimal solutions of constrained optimization problems. This is an empirical risk minimization under constraints, which is challenging as training must balance optimality and feasibility conditions. Supervised learning methods often approach this challenge by training the model on a large collection of pre-solved instances. This paper takes a different route and proposes the idea of Primal-Dual Learning (PDL), a self-supervised training method that does not require a set of pre-solved instances or an optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09046","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2208.09046/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":"2208.09046","created_at":"2026-07-05T05:18:48.648022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.09046v2","created_at":"2026-07-05T05:18:48.648022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09046","created_at":"2026-07-05T05:18:48.648022+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEY7F7DVGTIJ","created_at":"2026-07-05T05:18:48.648022+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEY7F7DVGTIJYIHT","created_at":"2026-07-05T05:18:48.648022+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEY7F7DV","created_at":"2026-07-05T05:18:48.648022+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/JEY7F7DVGTIJYIHTGBZW7LPEFW","json":"https://pith.science/pith/JEY7F7DVGTIJYIHTGBZW7LPEFW.json","graph_json":"https://pith.science/api/pith-number/JEY7F7DVGTIJYIHTGBZW7LPEFW/graph.json","events_json":"https://pith.science/api/pith-number/JEY7F7DVGTIJYIHTGBZW7LPEFW/events.json","paper":"https://pith.science/paper/JEY7F7DV"},"agent_actions":{"view_html":"https://pith.science/pith/JEY7F7DVGTIJYIHTGBZW7LPEFW","download_json":"https://pith.science/pith/JEY7F7DVGTIJYIHTGBZW7LPEFW.json","view_paper":"https://pith.science/paper/JEY7F7DV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.09046&json=true","fetch_graph":"https://pith.science/api/pith-number/JEY7F7DVGTIJYIHTGBZW7LPEFW/graph.json","fetch_events":"https://pith.science/api/pith-number/JEY7F7DVGTIJYIHTGBZW7LPEFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEY7F7DVGTIJYIHTGBZW7LPEFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEY7F7DVGTIJYIHTGBZW7LPEFW/action/storage_attestation","attest_author":"https://pith.science/pith/JEY7F7DVGTIJYIHTGBZW7LPEFW/action/author_attestation","sign_citation":"https://pith.science/pith/JEY7F7DVGTIJYIHTGBZW7LPEFW/action/citation_signature","submit_replication":"https://pith.science/pith/JEY7F7DVGTIJYIHTGBZW7LPEFW/action/replication_record"}},"created_at":"2026-07-05T05:18:48.648022+00:00","updated_at":"2026-07-05T05:18:48.648022+00:00"}