{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3J3RGAG546BFN7MMJEV5SAUWXQ","short_pith_number":"pith:3J3RGAG5","schema_version":"1.0","canonical_sha256":"da771300dde78256fd8c492bd90296bc3ec52c62c2ee667edce5818a2a411e6d","source":{"kind":"arxiv","id":"1703.00443","version":5},"attestation_state":"computed","paper":{"title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Brandon Amos, J. Zico Kolter","submitted_at":"2017-03-01T18:58:48Z","abstract_excerpt":"This paper presents OptNet, a network architecture that integrates optimization problems (here, specifically in the form of quadratic programs) as individual layers in larger end-to-end trainable deep networks. These layers encode constraints and complex dependencies between the hidden states that traditional convolutional and fully-connected layers often cannot capture. We explore the foundations for such an architecture: we show how techniques from sensitivity analysis, bilevel optimization, and implicit differentiation can be used to exactly differentiate through these layers and with respe"},"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":"1703.00443","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-01T18:58:48Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"69d818083b7c8be10c4de778034eb8883cb92ae738e68098da99a5d454a3a636","abstract_canon_sha256":"839e6b60c83b3e408b3bd95de32c75a27c278fbb04b67bad4d6c4409fecef6a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:50.147797Z","signature_b64":"ozDBts8CC7A1K/H0cZo4guOYuY6w4VsFKB16ss7VW4GpuTpKSzlYesN4QahMr/g8UgBzsMXBSO0r4VEB8/XSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da771300dde78256fd8c492bd90296bc3ec52c62c2ee667edce5818a2a411e6d","last_reissued_at":"2026-07-05T03:36:50.147301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:50.147301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Brandon Amos, J. Zico Kolter","submitted_at":"2017-03-01T18:58:48Z","abstract_excerpt":"This paper presents OptNet, a network architecture that integrates optimization problems (here, specifically in the form of quadratic programs) as individual layers in larger end-to-end trainable deep networks. These layers encode constraints and complex dependencies between the hidden states that traditional convolutional and fully-connected layers often cannot capture. We explore the foundations for such an architecture: we show how techniques from sensitivity analysis, bilevel optimization, and implicit differentiation can be used to exactly differentiate through these layers and with respe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00443","kind":"arxiv","version":5},"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/1703.00443/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":"1703.00443","created_at":"2026-07-05T03:36:50.147365+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00443v5","created_at":"2026-07-05T03:36:50.147365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00443","created_at":"2026-07-05T03:36:50.147365+00:00"},{"alias_kind":"pith_short_12","alias_value":"3J3RGAG546BF","created_at":"2026-07-05T03:36:50.147365+00:00"},{"alias_kind":"pith_short_16","alias_value":"3J3RGAG546BFN7MM","created_at":"2026-07-05T03:36:50.147365+00:00"},{"alias_kind":"pith_short_8","alias_value":"3J3RGAG5","created_at":"2026-07-05T03:36:50.147365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26341","citing_title":"Scaling Nonlinear Optimization: Many Problems One GPU","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05687","citing_title":"Accelerating and Scaling MPC-Guided Reinforcement Learning for Humanoid Locomotion and Manipulation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06100","citing_title":"CredibleDFGO: Differentiable Factor Graph Optimization with Credibility Supervision","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02294","citing_title":"Regularized Large Neighborhood Search","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09471","citing_title":"The Statistical Cost of Adaptation in Multi-Source Transfer Learning","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11507","citing_title":"Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25848","citing_title":"A Distributionally Robust Reinforcement Learning Framework for Constrained Urban EV Dispatch","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3J3RGAG546BFN7MMJEV5SAUWXQ","json":"https://pith.science/pith/3J3RGAG546BFN7MMJEV5SAUWXQ.json","graph_json":"https://pith.science/api/pith-number/3J3RGAG546BFN7MMJEV5SAUWXQ/graph.json","events_json":"https://pith.science/api/pith-number/3J3RGAG546BFN7MMJEV5SAUWXQ/events.json","paper":"https://pith.science/paper/3J3RGAG5"},"agent_actions":{"view_html":"https://pith.science/pith/3J3RGAG546BFN7MMJEV5SAUWXQ","download_json":"https://pith.science/pith/3J3RGAG546BFN7MMJEV5SAUWXQ.json","view_paper":"https://pith.science/paper/3J3RGAG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00443&json=true","fetch_graph":"https://pith.science/api/pith-number/3J3RGAG546BFN7MMJEV5SAUWXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3J3RGAG546BFN7MMJEV5SAUWXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3J3RGAG546BFN7MMJEV5SAUWXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3J3RGAG546BFN7MMJEV5SAUWXQ/action/storage_attestation","attest_author":"https://pith.science/pith/3J3RGAG546BFN7MMJEV5SAUWXQ/action/author_attestation","sign_citation":"https://pith.science/pith/3J3RGAG546BFN7MMJEV5SAUWXQ/action/citation_signature","submit_replication":"https://pith.science/pith/3J3RGAG546BFN7MMJEV5SAUWXQ/action/replication_record"}},"created_at":"2026-07-05T03:36:50.147365+00:00","updated_at":"2026-07-05T03:36:50.147365+00:00"}