{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JNDJNSY2M3X2EWARHSVFP6RLHT","short_pith_number":"pith:JNDJNSY2","schema_version":"1.0","canonical_sha256":"4b4696cb1a66efa258113caa57fa2b3ccdee5477d5b46c39d30dc05eb2cbf598","source":{"kind":"arxiv","id":"2106.10349","version":2},"attestation_state":"computed","paper":{"title":"The Perils of Learning Before Optimizing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Chris Cameron, Jason Hartford, Kevin Leyton-Brown, Taylor Lundy","submitted_at":"2021-06-18T20:43:47Z","abstract_excerpt":"Formulating real-world optimization problems often begins with making predictions from historical data (e.g., an optimizer that aims to recommend fast routes relies upon travel-time predictions). Typically, learning the prediction model used to generate the optimization problem and solving that problem are performed in two separate stages. Recent work has showed how such prediction models can be learned end-to-end by differentiating through the optimization task. Such methods often yield empirical improvements, which are typically attributed to end-to-end making better error tradeoffs than the"},"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":"2106.10349","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T20:43:47Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"b4457ce57050f36f4c0fc9df89224bfe1096ba7be5e0340476bc44b7e53dc069","abstract_canon_sha256":"905afbecd1ceda7562a133204b9149fb05dc394c7dc37a98d7a6fa54f9d9ad0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:39.755840Z","signature_b64":"LtDQ7fyGnO0UNq9MvONM8v6rXnDCmnJGC4sbsS1poZAOe+57+Kd5cVhVg6rYq7on0frh7aS94HzvpTC95W5BBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b4696cb1a66efa258113caa57fa2b3ccdee5477d5b46c39d30dc05eb2cbf598","last_reissued_at":"2026-07-05T03:41:39.755429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:39.755429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Perils of Learning Before Optimizing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Chris Cameron, Jason Hartford, Kevin Leyton-Brown, Taylor Lundy","submitted_at":"2021-06-18T20:43:47Z","abstract_excerpt":"Formulating real-world optimization problems often begins with making predictions from historical data (e.g., an optimizer that aims to recommend fast routes relies upon travel-time predictions). Typically, learning the prediction model used to generate the optimization problem and solving that problem are performed in two separate stages. Recent work has showed how such prediction models can be learned end-to-end by differentiating through the optimization task. Such methods often yield empirical improvements, which are typically attributed to end-to-end making better error tradeoffs than the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10349","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/2106.10349/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":"2106.10349","created_at":"2026-07-05T03:41:39.755485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.10349v2","created_at":"2026-07-05T03:41:39.755485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10349","created_at":"2026-07-05T03:41:39.755485+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNDJNSY2M3X2","created_at":"2026-07-05T03:41:39.755485+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNDJNSY2M3X2EWAR","created_at":"2026-07-05T03:41:39.755485+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNDJNSY2","created_at":"2026-07-05T03:41:39.755485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11360","citing_title":"Efficient End-to-End Learning for Decision-Making: A Meta-Optimization Approach","ref_index":2004,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNDJNSY2M3X2EWARHSVFP6RLHT","json":"https://pith.science/pith/JNDJNSY2M3X2EWARHSVFP6RLHT.json","graph_json":"https://pith.science/api/pith-number/JNDJNSY2M3X2EWARHSVFP6RLHT/graph.json","events_json":"https://pith.science/api/pith-number/JNDJNSY2M3X2EWARHSVFP6RLHT/events.json","paper":"https://pith.science/paper/JNDJNSY2"},"agent_actions":{"view_html":"https://pith.science/pith/JNDJNSY2M3X2EWARHSVFP6RLHT","download_json":"https://pith.science/pith/JNDJNSY2M3X2EWARHSVFP6RLHT.json","view_paper":"https://pith.science/paper/JNDJNSY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.10349&json=true","fetch_graph":"https://pith.science/api/pith-number/JNDJNSY2M3X2EWARHSVFP6RLHT/graph.json","fetch_events":"https://pith.science/api/pith-number/JNDJNSY2M3X2EWARHSVFP6RLHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNDJNSY2M3X2EWARHSVFP6RLHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNDJNSY2M3X2EWARHSVFP6RLHT/action/storage_attestation","attest_author":"https://pith.science/pith/JNDJNSY2M3X2EWARHSVFP6RLHT/action/author_attestation","sign_citation":"https://pith.science/pith/JNDJNSY2M3X2EWARHSVFP6RLHT/action/citation_signature","submit_replication":"https://pith.science/pith/JNDJNSY2M3X2EWARHSVFP6RLHT/action/replication_record"}},"created_at":"2026-07-05T03:41:39.755485+00:00","updated_at":"2026-07-05T03:41:39.755485+00:00"}