{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TY237Y62UMAQ7BYN55XYCTV3XZ","short_pith_number":"pith:TY237Y62","schema_version":"1.0","canonical_sha256":"9e35bfe3daa3010f870def6f814ebbbe430fc3d11e47c15b94e7ce553cf34d72","source":{"kind":"arxiv","id":"2505.15025","version":1},"attestation_state":"computed","paper":{"title":"Inverse Optimization via Learning Feasible Regions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Angelos Georghiou, Ke Ren, Peyman Mohajerin Esfahani","submitted_at":"2025-05-21T02:17:03Z","abstract_excerpt":"We study inverse optimization (IO), where the goal is to use a parametric optimization program as the hypothesis class to infer relationships between input-decision pairs. Most of the literature focuses on learning only the objective function, as learning the constraint function (i.e., feasible regions) leads to nonconvex training programs. Motivated by this, we focus on learning feasible regions for known linear objectives and introduce two training losses along with a hypothesis class to parameterize the constraint function. Our hypothesis class surpasses the previous objective-only method b"},"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":"2505.15025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-05-21T02:17:03Z","cross_cats_sorted":[],"title_canon_sha256":"ff4da8f38faecdc9823b541be27ca6fca7ce393bddc7e66df8239df76c9adb89","abstract_canon_sha256":"2e84caa9224488fe70d14d52121ce1e9a1e771b2cc8be4e4542a4e91a16826a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:39.421083Z","signature_b64":"HzijEt4DqcNRV08BYFRO3qPsupjNSLz6/xhxN9kKXj1yq+ZC2ljvI56TJ/VV+YE+6Sugq1l9eCH1/SmRc6xbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e35bfe3daa3010f870def6f814ebbbe430fc3d11e47c15b94e7ce553cf34d72","last_reissued_at":"2026-07-05T11:06:39.420628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:39.420628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverse Optimization via Learning Feasible Regions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Angelos Georghiou, Ke Ren, Peyman Mohajerin Esfahani","submitted_at":"2025-05-21T02:17:03Z","abstract_excerpt":"We study inverse optimization (IO), where the goal is to use a parametric optimization program as the hypothesis class to infer relationships between input-decision pairs. Most of the literature focuses on learning only the objective function, as learning the constraint function (i.e., feasible regions) leads to nonconvex training programs. Motivated by this, we focus on learning feasible regions for known linear objectives and introduce two training losses along with a hypothesis class to parameterize the constraint function. Our hypothesis class surpasses the previous objective-only method b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15025","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/2505.15025/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":"2505.15025","created_at":"2026-07-05T11:06:39.420686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15025v1","created_at":"2026-07-05T11:06:39.420686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15025","created_at":"2026-07-05T11:06:39.420686+00:00"},{"alias_kind":"pith_short_12","alias_value":"TY237Y62UMAQ","created_at":"2026-07-05T11:06:39.420686+00:00"},{"alias_kind":"pith_short_16","alias_value":"TY237Y62UMAQ7BYN","created_at":"2026-07-05T11:06:39.420686+00:00"},{"alias_kind":"pith_short_8","alias_value":"TY237Y62","created_at":"2026-07-05T11:06:39.420686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25288","citing_title":"Uncertainty Quantification in Data-Driven Inverse Optimization via Bayesian Inference","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08866","citing_title":"Tight Generalization Bounds for Noiseless Inverse Optimization","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TY237Y62UMAQ7BYN55XYCTV3XZ","json":"https://pith.science/pith/TY237Y62UMAQ7BYN55XYCTV3XZ.json","graph_json":"https://pith.science/api/pith-number/TY237Y62UMAQ7BYN55XYCTV3XZ/graph.json","events_json":"https://pith.science/api/pith-number/TY237Y62UMAQ7BYN55XYCTV3XZ/events.json","paper":"https://pith.science/paper/TY237Y62"},"agent_actions":{"view_html":"https://pith.science/pith/TY237Y62UMAQ7BYN55XYCTV3XZ","download_json":"https://pith.science/pith/TY237Y62UMAQ7BYN55XYCTV3XZ.json","view_paper":"https://pith.science/paper/TY237Y62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15025&json=true","fetch_graph":"https://pith.science/api/pith-number/TY237Y62UMAQ7BYN55XYCTV3XZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TY237Y62UMAQ7BYN55XYCTV3XZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TY237Y62UMAQ7BYN55XYCTV3XZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TY237Y62UMAQ7BYN55XYCTV3XZ/action/storage_attestation","attest_author":"https://pith.science/pith/TY237Y62UMAQ7BYN55XYCTV3XZ/action/author_attestation","sign_citation":"https://pith.science/pith/TY237Y62UMAQ7BYN55XYCTV3XZ/action/citation_signature","submit_replication":"https://pith.science/pith/TY237Y62UMAQ7BYN55XYCTV3XZ/action/replication_record"}},"created_at":"2026-07-05T11:06:39.420686+00:00","updated_at":"2026-07-05T11:06:39.420686+00:00"}