{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CPUFOK5WDLEPWM53GVBAU6RVPM","short_pith_number":"pith:CPUFOK5W","schema_version":"1.0","canonical_sha256":"13e8572bb61ac8fb33bb35420a7a357b10b7b1aeefb612e05ec53f517d10716c","source":{"kind":"arxiv","id":"2401.10467","version":2},"attestation_state":"computed","paper":{"title":"Learning Backdoors for Mixed Integer Linear Programs with Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.AI","authors_text":"Bistra Dilkina, Junyang Cai, Taoan Huang","submitted_at":"2024-01-19T03:39:43Z","abstract_excerpt":"Many real-world problems can be efficiently modeled as Mixed Integer Linear Programs (MILPs) and solved with the Branch-and-Bound method. Prior work has shown the existence of MILP backdoors, small sets of variables such that prioritizing branching on them when possible leads to faster running times. However, finding high-quality backdoors that improve running times remains an open question. Previous work learns to estimate the relative solver speed of randomly sampled backdoors through ranking and then decide whether to use the highest-ranked backdoor candidate. In this paper, we utilize the "},"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":"2401.10467","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-01-19T03:39:43Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"09ba01346ade095a7b080fe90a7d0b4e08d29895b4a77ba32f23579ca14fe7f1","abstract_canon_sha256":"4597869d4c51e745dd559228566459c64d9c912c076d292b063eadc138d3da5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:53.553499Z","signature_b64":"hiA47NBh0hq0k66Dn8pwvmue1JnLDDsIvxNsNV4nay0aLcGMsOVogdWYg54cOVTvbdRyDvPxG/R61yV5IANJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e8572bb61ac8fb33bb35420a7a357b10b7b1aeefb612e05ec53f517d10716c","last_reissued_at":"2026-07-05T08:50:53.553030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:53.553030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Backdoors for Mixed Integer Linear Programs with Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.AI","authors_text":"Bistra Dilkina, Junyang Cai, Taoan Huang","submitted_at":"2024-01-19T03:39:43Z","abstract_excerpt":"Many real-world problems can be efficiently modeled as Mixed Integer Linear Programs (MILPs) and solved with the Branch-and-Bound method. Prior work has shown the existence of MILP backdoors, small sets of variables such that prioritizing branching on them when possible leads to faster running times. However, finding high-quality backdoors that improve running times remains an open question. Previous work learns to estimate the relative solver speed of randomly sampled backdoors through ranking and then decide whether to use the highest-ranked backdoor candidate. In this paper, we utilize the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10467","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/2401.10467/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":"2401.10467","created_at":"2026-07-05T08:50:53.553082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10467v2","created_at":"2026-07-05T08:50:53.553082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10467","created_at":"2026-07-05T08:50:53.553082+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPUFOK5WDLEP","created_at":"2026-07-05T08:50:53.553082+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPUFOK5WDLEPWM53","created_at":"2026-07-05T08:50:53.553082+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPUFOK5W","created_at":"2026-07-05T08:50:53.553082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21440","citing_title":"Fusing Backdoors, Machine Learning, and Optimization for Large-Scale Parametric Mixed-Integer Programs","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPUFOK5WDLEPWM53GVBAU6RVPM","json":"https://pith.science/pith/CPUFOK5WDLEPWM53GVBAU6RVPM.json","graph_json":"https://pith.science/api/pith-number/CPUFOK5WDLEPWM53GVBAU6RVPM/graph.json","events_json":"https://pith.science/api/pith-number/CPUFOK5WDLEPWM53GVBAU6RVPM/events.json","paper":"https://pith.science/paper/CPUFOK5W"},"agent_actions":{"view_html":"https://pith.science/pith/CPUFOK5WDLEPWM53GVBAU6RVPM","download_json":"https://pith.science/pith/CPUFOK5WDLEPWM53GVBAU6RVPM.json","view_paper":"https://pith.science/paper/CPUFOK5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10467&json=true","fetch_graph":"https://pith.science/api/pith-number/CPUFOK5WDLEPWM53GVBAU6RVPM/graph.json","fetch_events":"https://pith.science/api/pith-number/CPUFOK5WDLEPWM53GVBAU6RVPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPUFOK5WDLEPWM53GVBAU6RVPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPUFOK5WDLEPWM53GVBAU6RVPM/action/storage_attestation","attest_author":"https://pith.science/pith/CPUFOK5WDLEPWM53GVBAU6RVPM/action/author_attestation","sign_citation":"https://pith.science/pith/CPUFOK5WDLEPWM53GVBAU6RVPM/action/citation_signature","submit_replication":"https://pith.science/pith/CPUFOK5WDLEPWM53GVBAU6RVPM/action/replication_record"}},"created_at":"2026-07-05T08:50:53.553082+00:00","updated_at":"2026-07-05T08:50:53.553082+00:00"}