{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R4ZPAVD2OFL6FBD2DELERRBY7L","short_pith_number":"pith:R4ZPAVD2","schema_version":"1.0","canonical_sha256":"8f32f0547a7157e2847a191648c438faede8ed4d1a73afaee43ac5363fe1d66e","source":{"kind":"arxiv","id":"2511.13174","version":2},"attestation_state":"computed","paper":{"title":"Warm-starting active-set solvers using graph neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Arnstr\\\"om, Ella J. Schmidtobreick, Jens Sj\\\"olund, Paul H\\\"ausner","submitted_at":"2025-11-17T09:22:45Z","abstract_excerpt":"Quadratic programming (QP) solvers are widely used in real-time control and optimization, but their computational cost often limits applicability in time-critical settings. To resolve this, we propose a learning-to-optimize approach using graph neural networks (GNNs) to predict active constraints in the dual active-set solver DAQP. Our method exploits the structural properties of QPs by representing them as bipartite graphs and learns to approximate the optimal active set for effectively warm-starting the solver. Across varying problem sizes, the GNN consistently reduces the number of solver i"},"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":"2511.13174","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-17T09:22:45Z","cross_cats_sorted":[],"title_canon_sha256":"99274d458e168a66f724cbc59eb421e12bf22ac265d34c803a864dea121ef960","abstract_canon_sha256":"d277fb5f367b794c791315c59b9a29f623628c8d374b3b7401fc3f856f791204"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:05:38.213214Z","signature_b64":"JzF3jgUQkhj9gsBkjCbttUxXDZmPDT/Xhgcgd2RBexWSDAmUQdt6HJvvBBciRr62QqGXN9YO9LcFINk0H0xhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f32f0547a7157e2847a191648c438faede8ed4d1a73afaee43ac5363fe1d66e","last_reissued_at":"2026-05-20T02:05:38.212404Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:05:38.212404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Warm-starting active-set solvers using graph neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Arnstr\\\"om, Ella J. Schmidtobreick, Jens Sj\\\"olund, Paul H\\\"ausner","submitted_at":"2025-11-17T09:22:45Z","abstract_excerpt":"Quadratic programming (QP) solvers are widely used in real-time control and optimization, but their computational cost often limits applicability in time-critical settings. To resolve this, we propose a learning-to-optimize approach using graph neural networks (GNNs) to predict active constraints in the dual active-set solver DAQP. Our method exploits the structural properties of QPs by representing them as bipartite graphs and learns to approximate the optimal active set for effectively warm-starting the solver. Across varying problem sizes, the GNN consistently reduces the number of solver i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.13174","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/2511.13174/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":"2511.13174","created_at":"2026-05-20T02:05:38.212510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.13174v2","created_at":"2026-05-20T02:05:38.212510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.13174","created_at":"2026-05-20T02:05:38.212510+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4ZPAVD2OFL6","created_at":"2026-05-20T02:05:38.212510+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4ZPAVD2OFL6FBD2","created_at":"2026-05-20T02:05:38.212510+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4ZPAVD2","created_at":"2026-05-20T02:05:38.212510+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/R4ZPAVD2OFL6FBD2DELERRBY7L","json":"https://pith.science/pith/R4ZPAVD2OFL6FBD2DELERRBY7L.json","graph_json":"https://pith.science/api/pith-number/R4ZPAVD2OFL6FBD2DELERRBY7L/graph.json","events_json":"https://pith.science/api/pith-number/R4ZPAVD2OFL6FBD2DELERRBY7L/events.json","paper":"https://pith.science/paper/R4ZPAVD2"},"agent_actions":{"view_html":"https://pith.science/pith/R4ZPAVD2OFL6FBD2DELERRBY7L","download_json":"https://pith.science/pith/R4ZPAVD2OFL6FBD2DELERRBY7L.json","view_paper":"https://pith.science/paper/R4ZPAVD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.13174&json=true","fetch_graph":"https://pith.science/api/pith-number/R4ZPAVD2OFL6FBD2DELERRBY7L/graph.json","fetch_events":"https://pith.science/api/pith-number/R4ZPAVD2OFL6FBD2DELERRBY7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4ZPAVD2OFL6FBD2DELERRBY7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4ZPAVD2OFL6FBD2DELERRBY7L/action/storage_attestation","attest_author":"https://pith.science/pith/R4ZPAVD2OFL6FBD2DELERRBY7L/action/author_attestation","sign_citation":"https://pith.science/pith/R4ZPAVD2OFL6FBD2DELERRBY7L/action/citation_signature","submit_replication":"https://pith.science/pith/R4ZPAVD2OFL6FBD2DELERRBY7L/action/replication_record"}},"created_at":"2026-05-20T02:05:38.212510+00:00","updated_at":"2026-05-20T02:05:38.212510+00:00"}