{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2HU35VW4O77MOHFOXD76L66MRQ","short_pith_number":"pith:2HU35VW4","schema_version":"1.0","canonical_sha256":"d1e9bed6dc77fec71caeb8ffe5fbcc8c089414b8bf4ab5bb7490a8bbd23ed420","source":{"kind":"arxiv","id":"2606.01081","version":1},"attestation_state":"computed","paper":{"title":"Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Pascal Van Hentenryck, Paul Grigas, Tinghan Ye, Wyame Benslimane","submitted_at":"2026-05-31T07:58:28Z","abstract_excerpt":"Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy. For contextual linear optimization, most existing DFL methods assume offline data and full observations of the objective cost vector. We develop an on-policy learning method for sequential contextual linear optimization under partial feedback, generalizing the standard bandit feedback setting. Our method learns a stochastic predict-then-optimize policy that samples a cost-vector prediction from a conditional distribution and solves the resulting downstr"},"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":"2606.01081","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T07:58:28Z","cross_cats_sorted":[],"title_canon_sha256":"06f1d0c706a5aa29331299b91026b042ffd3fd38089d9b95f1272c19335df7e8","abstract_canon_sha256":"9e1f0f1b765aec670e5090b66aeea7ba61e0b313538da01561d60c9f38634541"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:20.734906Z","signature_b64":"tqGY4GOpJxf0xabBovbSQoZwIgNA2tWpx09A1hr4hCB8nBn0G84mFGOjD1U9NUP89K/fDBWCoB7j+LHms4SGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1e9bed6dc77fec71caeb8ffe5fbcc8c089414b8bf4ab5bb7490a8bbd23ed420","last_reissued_at":"2026-06-02T01:04:20.734530Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:20.734530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Pascal Van Hentenryck, Paul Grigas, Tinghan Ye, Wyame Benslimane","submitted_at":"2026-05-31T07:58:28Z","abstract_excerpt":"Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy. For contextual linear optimization, most existing DFL methods assume offline data and full observations of the objective cost vector. We develop an on-policy learning method for sequential contextual linear optimization under partial feedback, generalizing the standard bandit feedback setting. Our method learns a stochastic predict-then-optimize policy that samples a cost-vector prediction from a conditional distribution and solves the resulting downstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01081","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/2606.01081/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":"2606.01081","created_at":"2026-06-02T01:04:20.734588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01081v1","created_at":"2026-06-02T01:04:20.734588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01081","created_at":"2026-06-02T01:04:20.734588+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HU35VW4O77M","created_at":"2026-06-02T01:04:20.734588+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HU35VW4O77MOHFO","created_at":"2026-06-02T01:04:20.734588+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HU35VW4","created_at":"2026-06-02T01:04:20.734588+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/2HU35VW4O77MOHFOXD76L66MRQ","json":"https://pith.science/pith/2HU35VW4O77MOHFOXD76L66MRQ.json","graph_json":"https://pith.science/api/pith-number/2HU35VW4O77MOHFOXD76L66MRQ/graph.json","events_json":"https://pith.science/api/pith-number/2HU35VW4O77MOHFOXD76L66MRQ/events.json","paper":"https://pith.science/paper/2HU35VW4"},"agent_actions":{"view_html":"https://pith.science/pith/2HU35VW4O77MOHFOXD76L66MRQ","download_json":"https://pith.science/pith/2HU35VW4O77MOHFOXD76L66MRQ.json","view_paper":"https://pith.science/paper/2HU35VW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01081&json=true","fetch_graph":"https://pith.science/api/pith-number/2HU35VW4O77MOHFOXD76L66MRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2HU35VW4O77MOHFOXD76L66MRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HU35VW4O77MOHFOXD76L66MRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HU35VW4O77MOHFOXD76L66MRQ/action/storage_attestation","attest_author":"https://pith.science/pith/2HU35VW4O77MOHFOXD76L66MRQ/action/author_attestation","sign_citation":"https://pith.science/pith/2HU35VW4O77MOHFOXD76L66MRQ/action/citation_signature","submit_replication":"https://pith.science/pith/2HU35VW4O77MOHFOXD76L66MRQ/action/replication_record"}},"created_at":"2026-06-02T01:04:20.734588+00:00","updated_at":"2026-06-02T01:04:20.734588+00:00"}