{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TTM445TAUS7PN64TAMOA6XI6UK","short_pith_number":"pith:TTM445TA","schema_version":"1.0","canonical_sha256":"9cd9ce7660a4bef6fb93031c0f5d1ea298503c49fc9dd462687b7742cba16eb2","source":{"kind":"arxiv","id":"2011.05354","version":2},"attestation_state":"computed","paper":{"title":"Contrastive Losses and Solution Caching for Predict-and-Optimize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jayanta Mandi, Maxime Mulamba, Michelangelo Diligenti, Michele Lombardi, Tias Guns, Victor Bucarey","submitted_at":"2020-11-10T19:09:12Z","abstract_excerpt":"Many decision-making processes involve solving a combinatorial optimization problem with uncertain input that can be estimated from historic data. Recently, problems in this class have been successfully addressed via end-to-end learning approaches, which rely on solving one optimization problem for each training instance at every epoch. In this context, we provide two distinct contributions. First, we use a Noise Contrastive approach to motivate a family of surrogate loss functions, based on viewing non-optimal solutions as negative examples. Second, we address a major bottleneck of all predic"},"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":"2011.05354","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-10T19:09:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6e3965057aecd629151f810f264e6aeaa0e85ae81ea6ef9a753e8d90eb4e12b","abstract_canon_sha256":"693ed9e7a5e52dde8fbc2c6ed26da29c8464a0d3b0b52a876c265f1bc9616e9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:08.644824Z","signature_b64":"/CyhZ50XK3N1AZMz0Y2yz3cp/HetFHDIFNInElUG864EYUtidNAM4T9YGWCVpm4J/xka+a1ElJ6v+uKK8wi0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cd9ce7660a4bef6fb93031c0f5d1ea298503c49fc9dd462687b7742cba16eb2","last_reissued_at":"2026-07-05T02:55:08.644339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:08.644339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Losses and Solution Caching for Predict-and-Optimize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jayanta Mandi, Maxime Mulamba, Michelangelo Diligenti, Michele Lombardi, Tias Guns, Victor Bucarey","submitted_at":"2020-11-10T19:09:12Z","abstract_excerpt":"Many decision-making processes involve solving a combinatorial optimization problem with uncertain input that can be estimated from historic data. Recently, problems in this class have been successfully addressed via end-to-end learning approaches, which rely on solving one optimization problem for each training instance at every epoch. In this context, we provide two distinct contributions. First, we use a Noise Contrastive approach to motivate a family of surrogate loss functions, based on viewing non-optimal solutions as negative examples. Second, we address a major bottleneck of all predic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05354","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/2011.05354/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":"2011.05354","created_at":"2026-07-05T02:55:08.644395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.05354v2","created_at":"2026-07-05T02:55:08.644395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05354","created_at":"2026-07-05T02:55:08.644395+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTM445TAUS7P","created_at":"2026-07-05T02:55:08.644395+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTM445TAUS7PN64T","created_at":"2026-07-05T02:55:08.644395+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTM445TA","created_at":"2026-07-05T02:55:08.644395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01361","citing_title":"Decision-Focused Learning via Tangent-Space Projection of Prediction Error","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01361","citing_title":"Decision-Focused Learning via Tangent-Space Projection of Prediction Error","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTM445TAUS7PN64TAMOA6XI6UK","json":"https://pith.science/pith/TTM445TAUS7PN64TAMOA6XI6UK.json","graph_json":"https://pith.science/api/pith-number/TTM445TAUS7PN64TAMOA6XI6UK/graph.json","events_json":"https://pith.science/api/pith-number/TTM445TAUS7PN64TAMOA6XI6UK/events.json","paper":"https://pith.science/paper/TTM445TA"},"agent_actions":{"view_html":"https://pith.science/pith/TTM445TAUS7PN64TAMOA6XI6UK","download_json":"https://pith.science/pith/TTM445TAUS7PN64TAMOA6XI6UK.json","view_paper":"https://pith.science/paper/TTM445TA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.05354&json=true","fetch_graph":"https://pith.science/api/pith-number/TTM445TAUS7PN64TAMOA6XI6UK/graph.json","fetch_events":"https://pith.science/api/pith-number/TTM445TAUS7PN64TAMOA6XI6UK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTM445TAUS7PN64TAMOA6XI6UK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTM445TAUS7PN64TAMOA6XI6UK/action/storage_attestation","attest_author":"https://pith.science/pith/TTM445TAUS7PN64TAMOA6XI6UK/action/author_attestation","sign_citation":"https://pith.science/pith/TTM445TAUS7PN64TAMOA6XI6UK/action/citation_signature","submit_replication":"https://pith.science/pith/TTM445TAUS7PN64TAMOA6XI6UK/action/replication_record"}},"created_at":"2026-07-05T02:55:08.644395+00:00","updated_at":"2026-07-05T02:55:08.644395+00:00"}