{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:URWLF3GMVQULD5VOHPVETCS45J","short_pith_number":"pith:URWLF3GM","schema_version":"1.0","canonical_sha256":"a46cb2ecccac28b1f6ae3bea498a5cea53a3b7ec292ad0e3994683f4c75314fe","source":{"kind":"arxiv","id":"2501.03443","version":1},"attestation_state":"computed","paper":{"title":"Optimization Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"math.OC","authors_text":"Pascal Van Hentenryck","submitted_at":"2025-01-07T00:09:52Z","abstract_excerpt":"This article introduces the concept of optimization learning, a methodology to design optimization proxies that learn the input/output mapping of parametric optimization problems. These optimization proxies are trustworthy by design: they compute feasible solutions to the underlying optimization problems, provide quality guarantees on the returned solutions, and scale to large instances. Optimization proxies are differentiable programs that combine traditional deep learning technology with repair or completion layers to produce feasible solutions. The article shows that optimization proxies ca"},"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":"2501.03443","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-01-07T00:09:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c547983f008fde2650a559d1a58bbe62257b53215626c80fe4bb8e3519c173ec","abstract_canon_sha256":"fd215aa67bf3c111f884404fefd8dec31b05151d816b9f8bdbc88221261add20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:54.844987Z","signature_b64":"7brC8MHurS6ZA1+i+QT8CSmMTjWIXOl2qLm9xiHKn8+m5VBsCxaoEWCkNTTxxdSRunSzFnr0NHQ+Q14w4YOpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a46cb2ecccac28b1f6ae3bea498a5cea53a3b7ec292ad0e3994683f4c75314fe","last_reissued_at":"2026-07-05T09:57:54.844514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:54.844514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimization Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"math.OC","authors_text":"Pascal Van Hentenryck","submitted_at":"2025-01-07T00:09:52Z","abstract_excerpt":"This article introduces the concept of optimization learning, a methodology to design optimization proxies that learn the input/output mapping of parametric optimization problems. These optimization proxies are trustworthy by design: they compute feasible solutions to the underlying optimization problems, provide quality guarantees on the returned solutions, and scale to large instances. Optimization proxies are differentiable programs that combine traditional deep learning technology with repair or completion layers to produce feasible solutions. The article shows that optimization proxies ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03443","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/2501.03443/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":"2501.03443","created_at":"2026-07-05T09:57:54.844574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03443v1","created_at":"2026-07-05T09:57:54.844574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03443","created_at":"2026-07-05T09:57:54.844574+00:00"},{"alias_kind":"pith_short_12","alias_value":"URWLF3GMVQUL","created_at":"2026-07-05T09:57:54.844574+00:00"},{"alias_kind":"pith_short_16","alias_value":"URWLF3GMVQULD5VO","created_at":"2026-07-05T09:57:54.844574+00:00"},{"alias_kind":"pith_short_8","alias_value":"URWLF3GM","created_at":"2026-07-05T09:57:54.844574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25362","citing_title":"Learning Optimization Proxies for Sequential Contextual Stochastic Programs: An Order Fulfillment Application","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28340","citing_title":"Decision-focused learning for optimal PV-Battery scheduling","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09317","citing_title":"SnareNet: Flexible Repair Layers for Neural Networks with Hard Constraints","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03489","citing_title":"Improving Feasibility via Fast Autoencoder-Based Projections","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URWLF3GMVQULD5VOHPVETCS45J","json":"https://pith.science/pith/URWLF3GMVQULD5VOHPVETCS45J.json","graph_json":"https://pith.science/api/pith-number/URWLF3GMVQULD5VOHPVETCS45J/graph.json","events_json":"https://pith.science/api/pith-number/URWLF3GMVQULD5VOHPVETCS45J/events.json","paper":"https://pith.science/paper/URWLF3GM"},"agent_actions":{"view_html":"https://pith.science/pith/URWLF3GMVQULD5VOHPVETCS45J","download_json":"https://pith.science/pith/URWLF3GMVQULD5VOHPVETCS45J.json","view_paper":"https://pith.science/paper/URWLF3GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03443&json=true","fetch_graph":"https://pith.science/api/pith-number/URWLF3GMVQULD5VOHPVETCS45J/graph.json","fetch_events":"https://pith.science/api/pith-number/URWLF3GMVQULD5VOHPVETCS45J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URWLF3GMVQULD5VOHPVETCS45J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URWLF3GMVQULD5VOHPVETCS45J/action/storage_attestation","attest_author":"https://pith.science/pith/URWLF3GMVQULD5VOHPVETCS45J/action/author_attestation","sign_citation":"https://pith.science/pith/URWLF3GMVQULD5VOHPVETCS45J/action/citation_signature","submit_replication":"https://pith.science/pith/URWLF3GMVQULD5VOHPVETCS45J/action/replication_record"}},"created_at":"2026-07-05T09:57:54.844574+00:00","updated_at":"2026-07-05T09:57:54.844574+00:00"}