{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4KVGWRX3F5MAQRXVMPQJEO2F5I","short_pith_number":"pith:4KVGWRX3","schema_version":"1.0","canonical_sha256":"e2aa6b46fb2f580846f563e0923b45ea130fd1b28c1d19aff1f98c070e8fcef1","source":{"kind":"arxiv","id":"2412.15534","version":2},"attestation_state":"computed","paper":{"title":"SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shengyu Feng, Yiming Yang","submitted_at":"2024-12-20T03:48:53Z","abstract_excerpt":"Mixed Integer Linear Program (MILP) solvers are mostly built upon a Branch-and-Bound (B\\&B) algorithm, where the efficiency of traditional solvers heavily depends on hand-crafted heuristics for branching. The past few years have witnessed the increasing popularity of data-driven approaches to automatically learn these heuristics. However, the success of these methods is highly dependent on the availability of high-quality demonstrations, which requires either the development of near-optimal heuristics or a time-consuming sampling process. This paper averts this challenge by proposing Suboptima"},"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":"2412.15534","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T03:48:53Z","cross_cats_sorted":[],"title_canon_sha256":"0f14029433e4ea5e86352700d9dabd6f889ca4e9a283f83e4602fcbe8250b5ba","abstract_canon_sha256":"bafc76b78708181f4d6be083bd4cb8c7f79c09f596a7ccc250a137581583611e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:56.793797Z","signature_b64":"8ZAhenI8juej+j9OfeTFJwH8MF+sEcoC65gDLwE0gQHylO6zp4GAKHVk0L/tXz0fAMGxVRpDDPHtlfjPkPKzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2aa6b46fb2f580846f563e0923b45ea130fd1b28c1d19aff1f98c070e8fcef1","last_reissued_at":"2026-07-05T10:19:56.793256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:56.793256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shengyu Feng, Yiming Yang","submitted_at":"2024-12-20T03:48:53Z","abstract_excerpt":"Mixed Integer Linear Program (MILP) solvers are mostly built upon a Branch-and-Bound (B\\&B) algorithm, where the efficiency of traditional solvers heavily depends on hand-crafted heuristics for branching. The past few years have witnessed the increasing popularity of data-driven approaches to automatically learn these heuristics. However, the success of these methods is highly dependent on the availability of high-quality demonstrations, which requires either the development of near-optimal heuristics or a time-consuming sampling process. This paper averts this challenge by proposing Suboptima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15534","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/2412.15534/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":"2412.15534","created_at":"2026-07-05T10:19:56.793340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15534v2","created_at":"2026-07-05T10:19:56.793340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15534","created_at":"2026-07-05T10:19:56.793340+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KVGWRX3F5MA","created_at":"2026-07-05T10:19:56.793340+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KVGWRX3F5MAQRXV","created_at":"2026-07-05T10:19:56.793340+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KVGWRX3","created_at":"2026-07-05T10:19:56.793340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4KVGWRX3F5MAQRXVMPQJEO2F5I","json":"https://pith.science/pith/4KVGWRX3F5MAQRXVMPQJEO2F5I.json","graph_json":"https://pith.science/api/pith-number/4KVGWRX3F5MAQRXVMPQJEO2F5I/graph.json","events_json":"https://pith.science/api/pith-number/4KVGWRX3F5MAQRXVMPQJEO2F5I/events.json","paper":"https://pith.science/paper/4KVGWRX3"},"agent_actions":{"view_html":"https://pith.science/pith/4KVGWRX3F5MAQRXVMPQJEO2F5I","download_json":"https://pith.science/pith/4KVGWRX3F5MAQRXVMPQJEO2F5I.json","view_paper":"https://pith.science/paper/4KVGWRX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15534&json=true","fetch_graph":"https://pith.science/api/pith-number/4KVGWRX3F5MAQRXVMPQJEO2F5I/graph.json","fetch_events":"https://pith.science/api/pith-number/4KVGWRX3F5MAQRXVMPQJEO2F5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KVGWRX3F5MAQRXVMPQJEO2F5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KVGWRX3F5MAQRXVMPQJEO2F5I/action/storage_attestation","attest_author":"https://pith.science/pith/4KVGWRX3F5MAQRXVMPQJEO2F5I/action/author_attestation","sign_citation":"https://pith.science/pith/4KVGWRX3F5MAQRXVMPQJEO2F5I/action/citation_signature","submit_replication":"https://pith.science/pith/4KVGWRX3F5MAQRXVMPQJEO2F5I/action/replication_record"}},"created_at":"2026-07-05T10:19:56.793340+00:00","updated_at":"2026-07-05T10:19:56.793340+00:00"}