{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:66JQ3MSDQ5ZGYWTQVYPOGW7XG3","short_pith_number":"pith:66JQ3MSD","schema_version":"1.0","canonical_sha256":"f7930db24387726c5a70ae1ee35bf736cc71cd4fd32a49c24409464c2afebceb","source":{"kind":"arxiv","id":"2207.13513","version":2},"attestation_state":"computed","paper":{"title":"Learning with Combinatorial Optimization Layers: a Probabilistic Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Axel Parmentier, Guillaume Dalle, L\\'eo Baty, Louis Bouvier","submitted_at":"2022-07-27T13:37:22Z","abstract_excerpt":"Combinatorial optimization (CO) layers in machine learning (ML) pipelines are a powerful tool to tackle data-driven decision tasks, but they come with two main challenges. First, the solution of a CO problem often behaves as a piecewise constant function of its objective parameters. Given that ML pipelines are typically trained using stochastic gradient descent, the absence of slope information is very detrimental. Second, standard ML losses do not work well in combinatorial settings. A growing body of research addresses these challenges through diverse methods. Unfortunately, the lack of well"},"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":"2207.13513","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-27T13:37:22Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"2ed6d15aa46bcf20ad0018a50e714f65da30959959d00698d55cd1b1dac52725","abstract_canon_sha256":"88444a1c4ecd22bc256bc0ca600007c97bcd4663c781b6b6d55493a78317ed21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:09.488603Z","signature_b64":"LPoGqhhnFfSgmbot9+va9tgCD0JN7JEGftNzRE8Ow9Bfx1FlQIju7SJBP9uIfK4z8zxfWJwkqDvb4XebfpImDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7930db24387726c5a70ae1ee35bf736cc71cd4fd32a49c24409464c2afebceb","last_reissued_at":"2026-07-05T05:22:09.488086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:09.488086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with Combinatorial Optimization Layers: a Probabilistic Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Axel Parmentier, Guillaume Dalle, L\\'eo Baty, Louis Bouvier","submitted_at":"2022-07-27T13:37:22Z","abstract_excerpt":"Combinatorial optimization (CO) layers in machine learning (ML) pipelines are a powerful tool to tackle data-driven decision tasks, but they come with two main challenges. First, the solution of a CO problem often behaves as a piecewise constant function of its objective parameters. Given that ML pipelines are typically trained using stochastic gradient descent, the absence of slope information is very detrimental. Second, standard ML losses do not work well in combinatorial settings. A growing body of research addresses these challenges through diverse methods. Unfortunately, the lack of well"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13513","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/2207.13513/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":"2207.13513","created_at":"2026-07-05T05:22:09.488152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.13513v2","created_at":"2026-07-05T05:22:09.488152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13513","created_at":"2026-07-05T05:22:09.488152+00:00"},{"alias_kind":"pith_short_12","alias_value":"66JQ3MSDQ5ZG","created_at":"2026-07-05T05:22:09.488152+00:00"},{"alias_kind":"pith_short_16","alias_value":"66JQ3MSDQ5ZGYWTQ","created_at":"2026-07-05T05:22:09.488152+00:00"},{"alias_kind":"pith_short_8","alias_value":"66JQ3MSD","created_at":"2026-07-05T05:22:09.488152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02294","citing_title":"Regularized Large Neighborhood Search","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2407.17200","citing_title":"Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66JQ3MSDQ5ZGYWTQVYPOGW7XG3","json":"https://pith.science/pith/66JQ3MSDQ5ZGYWTQVYPOGW7XG3.json","graph_json":"https://pith.science/api/pith-number/66JQ3MSDQ5ZGYWTQVYPOGW7XG3/graph.json","events_json":"https://pith.science/api/pith-number/66JQ3MSDQ5ZGYWTQVYPOGW7XG3/events.json","paper":"https://pith.science/paper/66JQ3MSD"},"agent_actions":{"view_html":"https://pith.science/pith/66JQ3MSDQ5ZGYWTQVYPOGW7XG3","download_json":"https://pith.science/pith/66JQ3MSDQ5ZGYWTQVYPOGW7XG3.json","view_paper":"https://pith.science/paper/66JQ3MSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.13513&json=true","fetch_graph":"https://pith.science/api/pith-number/66JQ3MSDQ5ZGYWTQVYPOGW7XG3/graph.json","fetch_events":"https://pith.science/api/pith-number/66JQ3MSDQ5ZGYWTQVYPOGW7XG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66JQ3MSDQ5ZGYWTQVYPOGW7XG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66JQ3MSDQ5ZGYWTQVYPOGW7XG3/action/storage_attestation","attest_author":"https://pith.science/pith/66JQ3MSDQ5ZGYWTQVYPOGW7XG3/action/author_attestation","sign_citation":"https://pith.science/pith/66JQ3MSDQ5ZGYWTQVYPOGW7XG3/action/citation_signature","submit_replication":"https://pith.science/pith/66JQ3MSDQ5ZGYWTQVYPOGW7XG3/action/replication_record"}},"created_at":"2026-07-05T05:22:09.488152+00:00","updated_at":"2026-07-05T05:22:09.488152+00:00"}