{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UO7E3TLNEUAS7V56Q2CTHITSYZ","short_pith_number":"pith:UO7E3TLN","schema_version":"1.0","canonical_sha256":"a3be4dcd6d25012fd7be868533a272c67b2953d2f79a0f9ca87d54e71253f9ad","source":{"kind":"arxiv","id":"2206.06965","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","math.OC"],"primary_cat":"cs.LG","authors_text":"Amin Banitalebi-Dehkordi, Tianyu Zhang, Yong Zhang","submitted_at":"2022-06-14T16:35:58Z","abstract_excerpt":"Branch-and-bound is a systematic enumerative method for combinatorial optimization, where the performance highly relies on the variable selection strategy. State-of-the-art handcrafted heuristic strategies suffer from relatively slow inference time for each selection, while the current machine learning methods require a significant amount of labeled data. We propose a new approach for solving the data labeling and inference latency issues in combinatorial optimization based on the use of the reinforcement learning (RL) paradigm. We use imitation learning to bootstrap an RL agent and then use P"},"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":"2206.06965","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T16:35:58Z","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"title_canon_sha256":"918b9a32d0bfd6f57b73ca638d931a2465bf3eb00e71b7795a8f4bfe18a36dc0","abstract_canon_sha256":"97e667377ced3e85972145aa40e7a97797059c5d7ccd53ca81a8a8ca9a9b81c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:47.749971Z","signature_b64":"MqfHi8tbjFr3VQ0tkLBC2ZE+O1R0y5qSfJuFnusZOzFE5Coy0yYfJOJeXYKCpEykDg1R2CEXNIDRKJJc1f+wDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3be4dcd6d25012fd7be868533a272c67b2953d2f79a0f9ca87d54e71253f9ad","last_reissued_at":"2026-07-05T04:31:47.749528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:47.749528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","math.OC"],"primary_cat":"cs.LG","authors_text":"Amin Banitalebi-Dehkordi, Tianyu Zhang, Yong Zhang","submitted_at":"2022-06-14T16:35:58Z","abstract_excerpt":"Branch-and-bound is a systematic enumerative method for combinatorial optimization, where the performance highly relies on the variable selection strategy. State-of-the-art handcrafted heuristic strategies suffer from relatively slow inference time for each selection, while the current machine learning methods require a significant amount of labeled data. We propose a new approach for solving the data labeling and inference latency issues in combinatorial optimization based on the use of the reinforcement learning (RL) paradigm. We use imitation learning to bootstrap an RL agent and then use P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06965","kind":"arxiv","version":1},"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/2206.06965/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":"2206.06965","created_at":"2026-07-05T04:31:47.749580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.06965v1","created_at":"2026-07-05T04:31:47.749580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06965","created_at":"2026-07-05T04:31:47.749580+00:00"},{"alias_kind":"pith_short_12","alias_value":"UO7E3TLNEUAS","created_at":"2026-07-05T04:31:47.749580+00:00"},{"alias_kind":"pith_short_16","alias_value":"UO7E3TLNEUAS7V56","created_at":"2026-07-05T04:31:47.749580+00:00"},{"alias_kind":"pith_short_8","alias_value":"UO7E3TLN","created_at":"2026-07-05T04:31:47.749580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15534","citing_title":"SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UO7E3TLNEUAS7V56Q2CTHITSYZ","json":"https://pith.science/pith/UO7E3TLNEUAS7V56Q2CTHITSYZ.json","graph_json":"https://pith.science/api/pith-number/UO7E3TLNEUAS7V56Q2CTHITSYZ/graph.json","events_json":"https://pith.science/api/pith-number/UO7E3TLNEUAS7V56Q2CTHITSYZ/events.json","paper":"https://pith.science/paper/UO7E3TLN"},"agent_actions":{"view_html":"https://pith.science/pith/UO7E3TLNEUAS7V56Q2CTHITSYZ","download_json":"https://pith.science/pith/UO7E3TLNEUAS7V56Q2CTHITSYZ.json","view_paper":"https://pith.science/paper/UO7E3TLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.06965&json=true","fetch_graph":"https://pith.science/api/pith-number/UO7E3TLNEUAS7V56Q2CTHITSYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UO7E3TLNEUAS7V56Q2CTHITSYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UO7E3TLNEUAS7V56Q2CTHITSYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UO7E3TLNEUAS7V56Q2CTHITSYZ/action/storage_attestation","attest_author":"https://pith.science/pith/UO7E3TLNEUAS7V56Q2CTHITSYZ/action/author_attestation","sign_citation":"https://pith.science/pith/UO7E3TLNEUAS7V56Q2CTHITSYZ/action/citation_signature","submit_replication":"https://pith.science/pith/UO7E3TLNEUAS7V56Q2CTHITSYZ/action/replication_record"}},"created_at":"2026-07-05T04:31:47.749580+00:00","updated_at":"2026-07-05T04:31:47.749580+00:00"}