{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O64MALBGM4TSNOHZPTVY4G4Q36","short_pith_number":"pith:O64MALBG","schema_version":"1.0","canonical_sha256":"77b8c02c26672726b8f97ceb8e1b90df9f6345f18fab19f1495aceb28dd8e4c3","source":{"kind":"arxiv","id":"2107.10201","version":3},"attestation_state":"computed","paper":{"title":"Learning a Large Neighborhood Search Algorithm for Mixed Integer Programs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Ira Ktena, Nicolas Sonnerat, Pengming Wang, Sergey Bartunov, Vinod Nair","submitted_at":"2021-07-21T16:43:46Z","abstract_excerpt":"Large Neighborhood Search (LNS) is a combinatorial optimization heuristic that starts with an assignment of values for the variables to be optimized, and iteratively improves it by searching a large neighborhood around the current assignment. In this paper we consider a learning-based LNS approach for mixed integer programs (MIPs). We train a Neural Diving model to represent a probability distribution over assignments, which, together with an off-the-shelf MIP solver, generates an initial assignment. Formulating the subsequent search steps as a Markov Decision Process, we train a Neural Neighb"},"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":"2107.10201","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-07-21T16:43:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9f7ec39cab4dc937536049cdefad4882d0fb12880385d5f0d5cf74b7e3293730","abstract_canon_sha256":"f443beb62805c10b2a62406b7209ed56d0581f8757143b324a83de1a2e95d6e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:55.917550Z","signature_b64":"rxBPbP+WbtTn1OpfR4QoZQbQL1uh6W2hpgQ1jm7pg9IQ62nA1Fwm50uE9nMECawNpohMTF8jKYP1i++SLMxjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77b8c02c26672726b8f97ceb8e1b90df9f6345f18fab19f1495aceb28dd8e4c3","last_reissued_at":"2026-07-05T04:24:55.916990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:55.916990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Large Neighborhood Search Algorithm for Mixed Integer Programs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Ira Ktena, Nicolas Sonnerat, Pengming Wang, Sergey Bartunov, Vinod Nair","submitted_at":"2021-07-21T16:43:46Z","abstract_excerpt":"Large Neighborhood Search (LNS) is a combinatorial optimization heuristic that starts with an assignment of values for the variables to be optimized, and iteratively improves it by searching a large neighborhood around the current assignment. In this paper we consider a learning-based LNS approach for mixed integer programs (MIPs). We train a Neural Diving model to represent a probability distribution over assignments, which, together with an off-the-shelf MIP solver, generates an initial assignment. Formulating the subsequent search steps as a Markov Decision Process, we train a Neural Neighb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10201","kind":"arxiv","version":3},"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/2107.10201/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":"2107.10201","created_at":"2026-07-05T04:24:55.917048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10201v3","created_at":"2026-07-05T04:24:55.917048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10201","created_at":"2026-07-05T04:24:55.917048+00:00"},{"alias_kind":"pith_short_12","alias_value":"O64MALBGM4TS","created_at":"2026-07-05T04:24:55.917048+00:00"},{"alias_kind":"pith_short_16","alias_value":"O64MALBGM4TSNOHZ","created_at":"2026-07-05T04:24:55.917048+00:00"},{"alias_kind":"pith_short_8","alias_value":"O64MALBG","created_at":"2026-07-05T04:24:55.917048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.19517","citing_title":"RL-SPH: Learning to Achieve Feasible Solutions for Integer Linear Programs","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22107","citing_title":"A Hybrid Reinforcement and Self-Supervised Learning Aided Benders Decomposition Algorithm","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07239","citing_title":"Sample Complexity of Stochastic Optimization with Integer Variables","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O64MALBGM4TSNOHZPTVY4G4Q36","json":"https://pith.science/pith/O64MALBGM4TSNOHZPTVY4G4Q36.json","graph_json":"https://pith.science/api/pith-number/O64MALBGM4TSNOHZPTVY4G4Q36/graph.json","events_json":"https://pith.science/api/pith-number/O64MALBGM4TSNOHZPTVY4G4Q36/events.json","paper":"https://pith.science/paper/O64MALBG"},"agent_actions":{"view_html":"https://pith.science/pith/O64MALBGM4TSNOHZPTVY4G4Q36","download_json":"https://pith.science/pith/O64MALBGM4TSNOHZPTVY4G4Q36.json","view_paper":"https://pith.science/paper/O64MALBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10201&json=true","fetch_graph":"https://pith.science/api/pith-number/O64MALBGM4TSNOHZPTVY4G4Q36/graph.json","fetch_events":"https://pith.science/api/pith-number/O64MALBGM4TSNOHZPTVY4G4Q36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O64MALBGM4TSNOHZPTVY4G4Q36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O64MALBGM4TSNOHZPTVY4G4Q36/action/storage_attestation","attest_author":"https://pith.science/pith/O64MALBGM4TSNOHZPTVY4G4Q36/action/author_attestation","sign_citation":"https://pith.science/pith/O64MALBGM4TSNOHZPTVY4G4Q36/action/citation_signature","submit_replication":"https://pith.science/pith/O64MALBGM4TSNOHZPTVY4G4Q36/action/replication_record"}},"created_at":"2026-07-05T04:24:55.917048+00:00","updated_at":"2026-07-05T04:24:55.917048+00:00"}