{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NZYRFEVGHLU4AE4BXI2LB3OIYM","short_pith_number":"pith:NZYRFEVG","schema_version":"1.0","canonical_sha256":"6e711292a63ae9c01381ba34b0edc8c337a9e6ab319b07f8010b1c70f9671a96","source":{"kind":"arxiv","id":"2601.04509","version":2},"attestation_state":"computed","paper":{"title":"A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cathy Wu, Peixin Huang, Wei Zhang, Wen Song, Yaoxin Wu, Yining Ma","submitted_at":"2026-01-08T02:23:47Z","abstract_excerpt":"Mixed-integer linear programming (MILP) is a foundational framework for combinatorial optimization across science and engineering, but remains hard to solve at scale due to NP-hardness. Recent learning-based methods typically model MILP instances as variable-constraint bipartite graphs and use Graph Neural Networks (GNNs) for representation learning, yet their locality limits representation power. We propose an attention-driven neural backbone that adopts an element-centric view of variables and constraints, with dual attention performing parallel intra-type self-attention and inter-type cross"},"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":"2601.04509","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-08T02:23:47Z","cross_cats_sorted":[],"title_canon_sha256":"f50278b1b0a459dcbb8ff36d095ac5c2c4973663ced69b65cfe090de8caae2e6","abstract_canon_sha256":"435edda2ba4738c5ae70986a746fbffb1c0dd096d2a396c258b262abd2f3c0dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:16:50.825671Z","signature_b64":"a4TIowSKaoZv0iT6Eh0SiWSzaysVxFjw9NykomCeVc+JSN2rcTWW+0O3rCJes5n7wFfBf3HMIaP3MPAcRexVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e711292a63ae9c01381ba34b0edc8c337a9e6ab319b07f8010b1c70f9671a96","last_reissued_at":"2026-07-03T01:16:50.825138Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:16:50.825138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cathy Wu, Peixin Huang, Wei Zhang, Wen Song, Yaoxin Wu, Yining Ma","submitted_at":"2026-01-08T02:23:47Z","abstract_excerpt":"Mixed-integer linear programming (MILP) is a foundational framework for combinatorial optimization across science and engineering, but remains hard to solve at scale due to NP-hardness. Recent learning-based methods typically model MILP instances as variable-constraint bipartite graphs and use Graph Neural Networks (GNNs) for representation learning, yet their locality limits representation power. We propose an attention-driven neural backbone that adopts an element-centric view of variables and constraints, with dual attention performing parallel intra-type self-attention and inter-type cross"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.04509","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/2601.04509/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":"2601.04509","created_at":"2026-07-03T01:16:50.825206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.04509v2","created_at":"2026-07-03T01:16:50.825206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.04509","created_at":"2026-07-03T01:16:50.825206+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZYRFEVGHLU4","created_at":"2026-07-03T01:16:50.825206+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZYRFEVGHLU4AE4B","created_at":"2026-07-03T01:16:50.825206+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZYRFEVG","created_at":"2026-07-03T01:16:50.825206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.29366","citing_title":"Solving Integer Linear Programming with Parallel Tempering","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZYRFEVGHLU4AE4BXI2LB3OIYM","json":"https://pith.science/pith/NZYRFEVGHLU4AE4BXI2LB3OIYM.json","graph_json":"https://pith.science/api/pith-number/NZYRFEVGHLU4AE4BXI2LB3OIYM/graph.json","events_json":"https://pith.science/api/pith-number/NZYRFEVGHLU4AE4BXI2LB3OIYM/events.json","paper":"https://pith.science/paper/NZYRFEVG"},"agent_actions":{"view_html":"https://pith.science/pith/NZYRFEVGHLU4AE4BXI2LB3OIYM","download_json":"https://pith.science/pith/NZYRFEVGHLU4AE4BXI2LB3OIYM.json","view_paper":"https://pith.science/paper/NZYRFEVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.04509&json=true","fetch_graph":"https://pith.science/api/pith-number/NZYRFEVGHLU4AE4BXI2LB3OIYM/graph.json","fetch_events":"https://pith.science/api/pith-number/NZYRFEVGHLU4AE4BXI2LB3OIYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZYRFEVGHLU4AE4BXI2LB3OIYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZYRFEVGHLU4AE4BXI2LB3OIYM/action/storage_attestation","attest_author":"https://pith.science/pith/NZYRFEVGHLU4AE4BXI2LB3OIYM/action/author_attestation","sign_citation":"https://pith.science/pith/NZYRFEVGHLU4AE4BXI2LB3OIYM/action/citation_signature","submit_replication":"https://pith.science/pith/NZYRFEVGHLU4AE4BXI2LB3OIYM/action/replication_record"}},"created_at":"2026-07-03T01:16:50.825206+00:00","updated_at":"2026-07-03T01:16:50.825206+00:00"}