{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CB5EH24QPGQS5SUIYQWIMW5VVD","short_pith_number":"pith:CB5EH24Q","schema_version":"1.0","canonical_sha256":"107a43eb9079a12eca88c42c865bb5a8c9b76fe62bf267180b76b179b680e087","source":{"kind":"arxiv","id":"2012.02342","version":1},"attestation_state":"computed","paper":{"title":"Divide and Learn: A Divide and Conquer Approach for Predict+Optimize","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Ali Ugur Guler, Christopher Leckie, Emir Demirovic, James Bailey, Jeffrey Chan, Peter J. Stuckey","submitted_at":"2020-12-04T00:26:56Z","abstract_excerpt":"The predict+optimize problem combines machine learning ofproblem coefficients with a combinatorial optimization prob-lem that uses the predicted coefficients. While this problemcan be solved in two separate stages, it is better to directlyminimize the optimization loss. However, this requires dif-ferentiating through a discrete, non-differentiable combina-torial function. Most existing approaches use some form ofsurrogate gradient. Demirovicet alshowed how to directlyexpress the loss of the optimization problem in terms of thepredicted coefficients as a piece-wise linear function. How-ever, 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":"2012.02342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T00:26:56Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"e4a75e6fad6f7938b66a922b2f0a0de6ea47978b3680c71ae6e0d762327f0485","abstract_canon_sha256":"c48d3dff825e8d3cb4e1dbcff205f7dff63f9433b710fa076bf3d8222f8a60c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:58.760680Z","signature_b64":"efdZkoSwN06lUqpufwTH2JZx/zt3VcDocsKdbL678nk7uhsWLTWzMYNSDRBaBCsB7rAKGBNz1vEBDQSQQq2mBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"107a43eb9079a12eca88c42c865bb5a8c9b76fe62bf267180b76b179b680e087","last_reissued_at":"2026-07-05T01:56:58.760269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:58.760269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Divide and Learn: A Divide and Conquer Approach for Predict+Optimize","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Ali Ugur Guler, Christopher Leckie, Emir Demirovic, James Bailey, Jeffrey Chan, Peter J. Stuckey","submitted_at":"2020-12-04T00:26:56Z","abstract_excerpt":"The predict+optimize problem combines machine learning ofproblem coefficients with a combinatorial optimization prob-lem that uses the predicted coefficients. While this problemcan be solved in two separate stages, it is better to directlyminimize the optimization loss. However, this requires dif-ferentiating through a discrete, non-differentiable combina-torial function. Most existing approaches use some form ofsurrogate gradient. Demirovicet alshowed how to directlyexpress the loss of the optimization problem in terms of thepredicted coefficients as a piece-wise linear function. How-ever, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02342","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/2012.02342/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":"2012.02342","created_at":"2026-07-05T01:56:58.760333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.02342v1","created_at":"2026-07-05T01:56:58.760333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02342","created_at":"2026-07-05T01:56:58.760333+00:00"},{"alias_kind":"pith_short_12","alias_value":"CB5EH24QPGQS","created_at":"2026-07-05T01:56:58.760333+00:00"},{"alias_kind":"pith_short_16","alias_value":"CB5EH24QPGQS5SUI","created_at":"2026-07-05T01:56:58.760333+00:00"},{"alias_kind":"pith_short_8","alias_value":"CB5EH24Q","created_at":"2026-07-05T01:56:58.760333+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/CB5EH24QPGQS5SUIYQWIMW5VVD","json":"https://pith.science/pith/CB5EH24QPGQS5SUIYQWIMW5VVD.json","graph_json":"https://pith.science/api/pith-number/CB5EH24QPGQS5SUIYQWIMW5VVD/graph.json","events_json":"https://pith.science/api/pith-number/CB5EH24QPGQS5SUIYQWIMW5VVD/events.json","paper":"https://pith.science/paper/CB5EH24Q"},"agent_actions":{"view_html":"https://pith.science/pith/CB5EH24QPGQS5SUIYQWIMW5VVD","download_json":"https://pith.science/pith/CB5EH24QPGQS5SUIYQWIMW5VVD.json","view_paper":"https://pith.science/paper/CB5EH24Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.02342&json=true","fetch_graph":"https://pith.science/api/pith-number/CB5EH24QPGQS5SUIYQWIMW5VVD/graph.json","fetch_events":"https://pith.science/api/pith-number/CB5EH24QPGQS5SUIYQWIMW5VVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CB5EH24QPGQS5SUIYQWIMW5VVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CB5EH24QPGQS5SUIYQWIMW5VVD/action/storage_attestation","attest_author":"https://pith.science/pith/CB5EH24QPGQS5SUIYQWIMW5VVD/action/author_attestation","sign_citation":"https://pith.science/pith/CB5EH24QPGQS5SUIYQWIMW5VVD/action/citation_signature","submit_replication":"https://pith.science/pith/CB5EH24QPGQS5SUIYQWIMW5VVD/action/replication_record"}},"created_at":"2026-07-05T01:56:58.760333+00:00","updated_at":"2026-07-05T01:56:58.760333+00:00"}