{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WSP7AIBPUSUBWLKQ42Q5MJIA66","short_pith_number":"pith:WSP7AIBP","schema_version":"1.0","canonical_sha256":"b49ff0202fa4a81b2d50e6a1d62500f7aa5655ca7f8e8bdb6c158c7b48b7e70a","source":{"kind":"arxiv","id":"2402.03086","version":2},"attestation_state":"computed","paper":{"title":"Dual Lagrangian Learning for Conic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Mathieu Tanneau, Pascal Van Hentenryck","submitted_at":"2024-02-05T15:14:08Z","abstract_excerpt":"This paper presents Dual Lagrangian Learning (DLL), a principled learning methodology for dual conic optimization proxies. DLL leverages conic duality and the representation power of ML models to provide high-duality, dual-feasible solutions, and therefore valid Lagrangian dual bounds, for linear and nonlinear conic optimization problems. The paper introduces a systematic dual completion procedure, differentiable conic projection layers, and a self-supervised learning framework based on Lagrangian duality. It also provides closed-form dual completion formulae for broad classes of conic problem"},"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":"2402.03086","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-02-05T15:14:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dbfc04890bc8332cf495c883bef842fb99186febc1c0ec05ec33d87c1208dfe2","abstract_canon_sha256":"77743249aa7526b4b1d476fe07a29933c48e96e664ebbaad5ed712a3d017989b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:36.703800Z","signature_b64":"MLKm+RUSn1IgP5VCfbTBqQrGiC0Djp4CurRsOhzS1KF3zmEVGiMGLylhwdbCaFOKRUUQOiDTpg3E9j2sXyumBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b49ff0202fa4a81b2d50e6a1d62500f7aa5655ca7f8e8bdb6c158c7b48b7e70a","last_reissued_at":"2026-07-05T08:22:36.703240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:36.703240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Lagrangian Learning for Conic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Mathieu Tanneau, Pascal Van Hentenryck","submitted_at":"2024-02-05T15:14:08Z","abstract_excerpt":"This paper presents Dual Lagrangian Learning (DLL), a principled learning methodology for dual conic optimization proxies. DLL leverages conic duality and the representation power of ML models to provide high-duality, dual-feasible solutions, and therefore valid Lagrangian dual bounds, for linear and nonlinear conic optimization problems. The paper introduces a systematic dual completion procedure, differentiable conic projection layers, and a self-supervised learning framework based on Lagrangian duality. It also provides closed-form dual completion formulae for broad classes of conic problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03086","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/2402.03086/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":"2402.03086","created_at":"2026-07-05T08:22:36.703324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03086v2","created_at":"2026-07-05T08:22:36.703324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03086","created_at":"2026-07-05T08:22:36.703324+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSP7AIBPUSUB","created_at":"2026-07-05T08:22:36.703324+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSP7AIBPUSUBWLKQ","created_at":"2026-07-05T08:22:36.703324+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSP7AIBP","created_at":"2026-07-05T08:22:36.703324+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/WSP7AIBPUSUBWLKQ42Q5MJIA66","json":"https://pith.science/pith/WSP7AIBPUSUBWLKQ42Q5MJIA66.json","graph_json":"https://pith.science/api/pith-number/WSP7AIBPUSUBWLKQ42Q5MJIA66/graph.json","events_json":"https://pith.science/api/pith-number/WSP7AIBPUSUBWLKQ42Q5MJIA66/events.json","paper":"https://pith.science/paper/WSP7AIBP"},"agent_actions":{"view_html":"https://pith.science/pith/WSP7AIBPUSUBWLKQ42Q5MJIA66","download_json":"https://pith.science/pith/WSP7AIBPUSUBWLKQ42Q5MJIA66.json","view_paper":"https://pith.science/paper/WSP7AIBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03086&json=true","fetch_graph":"https://pith.science/api/pith-number/WSP7AIBPUSUBWLKQ42Q5MJIA66/graph.json","fetch_events":"https://pith.science/api/pith-number/WSP7AIBPUSUBWLKQ42Q5MJIA66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSP7AIBPUSUBWLKQ42Q5MJIA66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSP7AIBPUSUBWLKQ42Q5MJIA66/action/storage_attestation","attest_author":"https://pith.science/pith/WSP7AIBPUSUBWLKQ42Q5MJIA66/action/author_attestation","sign_citation":"https://pith.science/pith/WSP7AIBPUSUBWLKQ42Q5MJIA66/action/citation_signature","submit_replication":"https://pith.science/pith/WSP7AIBPUSUBWLKQ42Q5MJIA66/action/replication_record"}},"created_at":"2026-07-05T08:22:36.703324+00:00","updated_at":"2026-07-05T08:22:36.703324+00:00"}