{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5JARGHYQSCVPJMHCWLSAWP3CFZ","short_pith_number":"pith:5JARGHYQ","schema_version":"1.0","canonical_sha256":"ea41131f1090aaf4b0e2b2e40b3f622e52808963806f2c5b56138ed24d0303e0","source":{"kind":"arxiv","id":"2205.11107","version":3},"attestation_state":"computed","paper":{"title":"Learning to branch with Tree MDPs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Andrea Lodi, Didier Ch\\'etelat, Feng Yang Chen, Karen Aardal, Lara Scavuzzo, Maxime Gasse, Neil Yorke-Smith","submitted_at":"2022-05-23T07:57:32Z","abstract_excerpt":"State-of-the-art Mixed Integer Linear Program (MILP) solvers combine systematic tree search with a plethora of hard-coded heuristics, such as the branching rule. The idea of learning branching rules from data has received increasing attention recently, and promising results have been obtained by learning fast approximations of the strong branching expert. In this work, we instead propose to learn branching rules from scratch via Reinforcement Learning (RL). We revisit the work of Etheve et al. (2020) and propose tree Markov Decision Processes, or tree MDPs, a generalization of temporal MDPs th"},"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":"2205.11107","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T07:57:32Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"700389a2314e923c521fe8a73fdf78811a0280e085bf878910c8732ba5014dff","abstract_canon_sha256":"a52cf26782eb8fee0a8433bc716c51b325efabafb12c2584453b4599f234f1c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:12.014932Z","signature_b64":"UhRXwiDrRs5uxbLmCTAZbwGMhxXx0jddL+BK7dno4lsFhzDI5JT/Vl6tj82JRkOMQGe7ED37fcn/qOpM7/R1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea41131f1090aaf4b0e2b2e40b3f622e52808963806f2c5b56138ed24d0303e0","last_reissued_at":"2026-07-05T05:06:12.014445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:12.014445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to branch with Tree MDPs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Andrea Lodi, Didier Ch\\'etelat, Feng Yang Chen, Karen Aardal, Lara Scavuzzo, Maxime Gasse, Neil Yorke-Smith","submitted_at":"2022-05-23T07:57:32Z","abstract_excerpt":"State-of-the-art Mixed Integer Linear Program (MILP) solvers combine systematic tree search with a plethora of hard-coded heuristics, such as the branching rule. The idea of learning branching rules from data has received increasing attention recently, and promising results have been obtained by learning fast approximations of the strong branching expert. In this work, we instead propose to learn branching rules from scratch via Reinforcement Learning (RL). We revisit the work of Etheve et al. (2020) and propose tree Markov Decision Processes, or tree MDPs, a generalization of temporal MDPs th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11107","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/2205.11107/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":"2205.11107","created_at":"2026-07-05T05:06:12.014505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11107v3","created_at":"2026-07-05T05:06:12.014505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11107","created_at":"2026-07-05T05:06:12.014505+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JARGHYQSCVP","created_at":"2026-07-05T05:06:12.014505+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JARGHYQSCVPJMHC","created_at":"2026-07-05T05:06:12.014505+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JARGHYQ","created_at":"2026-07-05T05:06:12.014505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04099","citing_title":"Conversation Forests: The Key to Fine Tuning Large Language Models for Multi-Turn Medical Conversations is Branching","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5JARGHYQSCVPJMHCWLSAWP3CFZ","json":"https://pith.science/pith/5JARGHYQSCVPJMHCWLSAWP3CFZ.json","graph_json":"https://pith.science/api/pith-number/5JARGHYQSCVPJMHCWLSAWP3CFZ/graph.json","events_json":"https://pith.science/api/pith-number/5JARGHYQSCVPJMHCWLSAWP3CFZ/events.json","paper":"https://pith.science/paper/5JARGHYQ"},"agent_actions":{"view_html":"https://pith.science/pith/5JARGHYQSCVPJMHCWLSAWP3CFZ","download_json":"https://pith.science/pith/5JARGHYQSCVPJMHCWLSAWP3CFZ.json","view_paper":"https://pith.science/paper/5JARGHYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11107&json=true","fetch_graph":"https://pith.science/api/pith-number/5JARGHYQSCVPJMHCWLSAWP3CFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5JARGHYQSCVPJMHCWLSAWP3CFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JARGHYQSCVPJMHCWLSAWP3CFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JARGHYQSCVPJMHCWLSAWP3CFZ/action/storage_attestation","attest_author":"https://pith.science/pith/5JARGHYQSCVPJMHCWLSAWP3CFZ/action/author_attestation","sign_citation":"https://pith.science/pith/5JARGHYQSCVPJMHCWLSAWP3CFZ/action/citation_signature","submit_replication":"https://pith.science/pith/5JARGHYQSCVPJMHCWLSAWP3CFZ/action/replication_record"}},"created_at":"2026-07-05T05:06:12.014505+00:00","updated_at":"2026-07-05T05:06:12.014505+00:00"}