{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OTNSWV7XT5ONYO3FM5TV5FBXDJ","short_pith_number":"pith:OTNSWV7X","schema_version":"1.0","canonical_sha256":"74db2b57f79f5cdc3b6567675e94371a7870c533e4d0dd8c37868288af39a31a","source":{"kind":"arxiv","id":"2409.06997","version":2},"attestation_state":"computed","paper":{"title":"What is the Right Notion of Distance between Predict-then-Optimize Tasks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Alvarez-Melis, Kai Wang, Lingkai Kong, Milind Tambe, Paula Rodriguez-Diaz","submitted_at":"2024-09-11T04:13:17Z","abstract_excerpt":"Comparing datasets is a fundamental task in machine learning, essential for various learning paradigms-from evaluating train and test datasets for model generalization to using dataset similarity for detecting data drift. While traditional notions of dataset distances offer principled measures of similarity, their utility has largely been assessed through prediction error minimization. However, in Predict-then-Optimize (PtO) frameworks, where predictions serve as inputs for downstream optimization tasks, model performance is measured through decision regret rather than prediction error. In thi"},"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":"2409.06997","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T04:13:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"987f45381b947147f2dfa9ce3a42afc8d75aa7f2c5ee2b4939043a05aa5f623a","abstract_canon_sha256":"f8d01603022163125ea521fa03f0c293490cbf00f85e14069e975b4df9f2782f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:32.188966Z","signature_b64":"cjOUnRtejaikjpDH8xM3hhKYaJA+CZmA282YvAy/K3P9ykIDr/WxirboLxjFNhwnuTGrS7uJWtds7kVdiySWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74db2b57f79f5cdc3b6567675e94371a7870c533e4d0dd8c37868288af39a31a","last_reissued_at":"2026-07-05T11:22:32.188478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:32.188478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What is the Right Notion of Distance between Predict-then-Optimize Tasks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Alvarez-Melis, Kai Wang, Lingkai Kong, Milind Tambe, Paula Rodriguez-Diaz","submitted_at":"2024-09-11T04:13:17Z","abstract_excerpt":"Comparing datasets is a fundamental task in machine learning, essential for various learning paradigms-from evaluating train and test datasets for model generalization to using dataset similarity for detecting data drift. While traditional notions of dataset distances offer principled measures of similarity, their utility has largely been assessed through prediction error minimization. However, in Predict-then-Optimize (PtO) frameworks, where predictions serve as inputs for downstream optimization tasks, model performance is measured through decision regret rather than prediction error. In thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06997","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/2409.06997/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":"2409.06997","created_at":"2026-07-05T11:22:32.188537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06997v2","created_at":"2026-07-05T11:22:32.188537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06997","created_at":"2026-07-05T11:22:32.188537+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTNSWV7XT5ON","created_at":"2026-07-05T11:22:32.188537+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTNSWV7XT5ONYO3F","created_at":"2026-07-05T11:22:32.188537+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTNSWV7X","created_at":"2026-07-05T11:22:32.188537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21773","citing_title":"Decision-Focused Learning: When and Why Traditional Prediction Models Fail","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02081","citing_title":"ASSS: A Differentiable Adversarial Framework for Task-Aware Data Reduction","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTNSWV7XT5ONYO3FM5TV5FBXDJ","json":"https://pith.science/pith/OTNSWV7XT5ONYO3FM5TV5FBXDJ.json","graph_json":"https://pith.science/api/pith-number/OTNSWV7XT5ONYO3FM5TV5FBXDJ/graph.json","events_json":"https://pith.science/api/pith-number/OTNSWV7XT5ONYO3FM5TV5FBXDJ/events.json","paper":"https://pith.science/paper/OTNSWV7X"},"agent_actions":{"view_html":"https://pith.science/pith/OTNSWV7XT5ONYO3FM5TV5FBXDJ","download_json":"https://pith.science/pith/OTNSWV7XT5ONYO3FM5TV5FBXDJ.json","view_paper":"https://pith.science/paper/OTNSWV7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06997&json=true","fetch_graph":"https://pith.science/api/pith-number/OTNSWV7XT5ONYO3FM5TV5FBXDJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OTNSWV7XT5ONYO3FM5TV5FBXDJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTNSWV7XT5ONYO3FM5TV5FBXDJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTNSWV7XT5ONYO3FM5TV5FBXDJ/action/storage_attestation","attest_author":"https://pith.science/pith/OTNSWV7XT5ONYO3FM5TV5FBXDJ/action/author_attestation","sign_citation":"https://pith.science/pith/OTNSWV7XT5ONYO3FM5TV5FBXDJ/action/citation_signature","submit_replication":"https://pith.science/pith/OTNSWV7XT5ONYO3FM5TV5FBXDJ/action/replication_record"}},"created_at":"2026-07-05T11:22:32.188537+00:00","updated_at":"2026-07-05T11:22:32.188537+00:00"}