{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B4YR6KVQLUWUD3Z2PYJ63UZFMN","short_pith_number":"pith:B4YR6KVQ","schema_version":"1.0","canonical_sha256":"0f311f2ab05d2d41ef3a7e13edd3256341da1079b2715457913425ac7e50e41e","source":{"kind":"arxiv","id":"2102.09663","version":2},"attestation_state":"computed","paper":{"title":"Smart Feasibility Pump: Reinforcement Learning for (Mixed) Integer Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Meng Qi, Mengxin Wang, Zuo-Jun Shen","submitted_at":"2021-02-18T23:18:17Z","abstract_excerpt":"In this work, we propose a deep reinforcement learning (DRL) model for finding a feasible solution for (mixed) integer programming (MIP) problems. Finding a feasible solution for MIP problems is critical because many successful heuristics rely on a known initial feasible solution. However, it is in general NP-hard. Inspired by the feasibility pump (FP), a well-known heuristic for searching feasible MIP solutions, we develop a smart feasibility pump (SFP) method using DRL. In addition to multi-layer perception (MLP), we propose a novel convolution neural network (CNN) structure for the policy n"},"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":"2102.09663","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T23:18:17Z","cross_cats_sorted":[],"title_canon_sha256":"342479171d30ee0e70e4f0c44f0d77b02e3fecdcf3d597142fa2e635f068d7d7","abstract_canon_sha256":"797c6f7aa1fae57bf44f838bbf4c5c4ae633f99bb95786e48866dbac4bea19f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:39.616194Z","signature_b64":"jxRARMzgWFgkRarKq55jc5jfD8M8IWTrl0eJT2Mh2cgW2C2iPiKJTgbsMc4lMwahOi+Tt2lNS7MEAoTfWRU7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f311f2ab05d2d41ef3a7e13edd3256341da1079b2715457913425ac7e50e41e","last_reissued_at":"2026-07-05T02:58:39.615701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:39.615701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smart Feasibility Pump: Reinforcement Learning for (Mixed) Integer Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Meng Qi, Mengxin Wang, Zuo-Jun Shen","submitted_at":"2021-02-18T23:18:17Z","abstract_excerpt":"In this work, we propose a deep reinforcement learning (DRL) model for finding a feasible solution for (mixed) integer programming (MIP) problems. Finding a feasible solution for MIP problems is critical because many successful heuristics rely on a known initial feasible solution. However, it is in general NP-hard. Inspired by the feasibility pump (FP), a well-known heuristic for searching feasible MIP solutions, we develop a smart feasibility pump (SFP) method using DRL. In addition to multi-layer perception (MLP), we propose a novel convolution neural network (CNN) structure for the policy n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09663","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/2102.09663/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":"2102.09663","created_at":"2026-07-05T02:58:39.615769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09663v2","created_at":"2026-07-05T02:58:39.615769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09663","created_at":"2026-07-05T02:58:39.615769+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4YR6KVQLUWU","created_at":"2026-07-05T02:58:39.615769+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4YR6KVQLUWUD3Z2","created_at":"2026-07-05T02:58:39.615769+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4YR6KVQ","created_at":"2026-07-05T02:58:39.615769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00307","citing_title":"Fast and Interpretable Mixed-Integer Linear Program Solving by Learning Model Reduction","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4YR6KVQLUWUD3Z2PYJ63UZFMN","json":"https://pith.science/pith/B4YR6KVQLUWUD3Z2PYJ63UZFMN.json","graph_json":"https://pith.science/api/pith-number/B4YR6KVQLUWUD3Z2PYJ63UZFMN/graph.json","events_json":"https://pith.science/api/pith-number/B4YR6KVQLUWUD3Z2PYJ63UZFMN/events.json","paper":"https://pith.science/paper/B4YR6KVQ"},"agent_actions":{"view_html":"https://pith.science/pith/B4YR6KVQLUWUD3Z2PYJ63UZFMN","download_json":"https://pith.science/pith/B4YR6KVQLUWUD3Z2PYJ63UZFMN.json","view_paper":"https://pith.science/paper/B4YR6KVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09663&json=true","fetch_graph":"https://pith.science/api/pith-number/B4YR6KVQLUWUD3Z2PYJ63UZFMN/graph.json","fetch_events":"https://pith.science/api/pith-number/B4YR6KVQLUWUD3Z2PYJ63UZFMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4YR6KVQLUWUD3Z2PYJ63UZFMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4YR6KVQLUWUD3Z2PYJ63UZFMN/action/storage_attestation","attest_author":"https://pith.science/pith/B4YR6KVQLUWUD3Z2PYJ63UZFMN/action/author_attestation","sign_citation":"https://pith.science/pith/B4YR6KVQLUWUD3Z2PYJ63UZFMN/action/citation_signature","submit_replication":"https://pith.science/pith/B4YR6KVQLUWUD3Z2PYJ63UZFMN/action/replication_record"}},"created_at":"2026-07-05T02:58:39.615769+00:00","updated_at":"2026-07-05T02:58:39.615769+00:00"}