{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DDOHM55XD3TDYLCGDF7ALJVKGC","short_pith_number":"pith:DDOHM55X","schema_version":"1.0","canonical_sha256":"18dc7677b71ee63c2c46197e05a6aa3083a527de363a428cd20c6f07c5d45bae","source":{"kind":"arxiv","id":"2504.01212","version":1},"attestation_state":"computed","paper":{"title":"Cooper: A Library for Constrained Optimization in Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MS"],"primary_cat":"cs.LG","authors_text":"Jose Gallego-Posada, Juan Ramirez, Meraj Hashemizadeh, Simon Lacoste-Julien","submitted_at":"2025-04-01T21:52:53Z","abstract_excerpt":"Cooper is an open-source package for solving constrained optimization problems involving deep learning models. Cooper implements several Lagrangian-based first-order update schemes, making it easy to combine constrained optimization algorithms with high-level features of PyTorch such as automatic differentiation, and specialized deep learning architectures and optimizers. Although Cooper is specifically designed for deep learning applications where gradients are estimated based on mini-batches, it is suitable for general non-convex continuous constrained optimization. Cooper's source code is a"},"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":"2504.01212","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-01T21:52:53Z","cross_cats_sorted":["cs.MS"],"title_canon_sha256":"66dc329b1e6cf41605d7320a140789c342c85700929986e7719154b2df37c960","abstract_canon_sha256":"377677c97d9fa88e88079e18a77b44276a60a664647bfe523542ef61e424446b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:11.008009Z","signature_b64":"qivRTCCG2rj3F7WjDih3VHgZn7lr7EtI+3bOmwmcYXJMqHl2yGghbIorxybfe4iGSlbGriLhHO7mh/AZrvT7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18dc7677b71ee63c2c46197e05a6aa3083a527de363a428cd20c6f07c5d45bae","last_reissued_at":"2026-07-05T10:43:11.007522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:11.007522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cooper: A Library for Constrained Optimization in Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MS"],"primary_cat":"cs.LG","authors_text":"Jose Gallego-Posada, Juan Ramirez, Meraj Hashemizadeh, Simon Lacoste-Julien","submitted_at":"2025-04-01T21:52:53Z","abstract_excerpt":"Cooper is an open-source package for solving constrained optimization problems involving deep learning models. Cooper implements several Lagrangian-based first-order update schemes, making it easy to combine constrained optimization algorithms with high-level features of PyTorch such as automatic differentiation, and specialized deep learning architectures and optimizers. Although Cooper is specifically designed for deep learning applications where gradients are estimated based on mini-batches, it is suitable for general non-convex continuous constrained optimization. Cooper's source code is a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01212","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/2504.01212/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":"2504.01212","created_at":"2026-07-05T10:43:11.007583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01212v1","created_at":"2026-07-05T10:43:11.007583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01212","created_at":"2026-07-05T10:43:11.007583+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDOHM55XD3TD","created_at":"2026-07-05T10:43:11.007583+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDOHM55XD3TDYLCG","created_at":"2026-07-05T10:43:11.007583+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDOHM55X","created_at":"2026-07-05T10:43:11.007583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19594","citing_title":"Unsupervised Causal Abstractions Discovery","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29521","citing_title":"Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20628","citing_title":"Position: Adopt Constraints Over Fixed Penalties in Deep Learning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02981","citing_title":"How pore-scale disorder controls fluid stretching in porous media","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DDOHM55XD3TDYLCGDF7ALJVKGC","json":"https://pith.science/pith/DDOHM55XD3TDYLCGDF7ALJVKGC.json","graph_json":"https://pith.science/api/pith-number/DDOHM55XD3TDYLCGDF7ALJVKGC/graph.json","events_json":"https://pith.science/api/pith-number/DDOHM55XD3TDYLCGDF7ALJVKGC/events.json","paper":"https://pith.science/paper/DDOHM55X"},"agent_actions":{"view_html":"https://pith.science/pith/DDOHM55XD3TDYLCGDF7ALJVKGC","download_json":"https://pith.science/pith/DDOHM55XD3TDYLCGDF7ALJVKGC.json","view_paper":"https://pith.science/paper/DDOHM55X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01212&json=true","fetch_graph":"https://pith.science/api/pith-number/DDOHM55XD3TDYLCGDF7ALJVKGC/graph.json","fetch_events":"https://pith.science/api/pith-number/DDOHM55XD3TDYLCGDF7ALJVKGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDOHM55XD3TDYLCGDF7ALJVKGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDOHM55XD3TDYLCGDF7ALJVKGC/action/storage_attestation","attest_author":"https://pith.science/pith/DDOHM55XD3TDYLCGDF7ALJVKGC/action/author_attestation","sign_citation":"https://pith.science/pith/DDOHM55XD3TDYLCGDF7ALJVKGC/action/citation_signature","submit_replication":"https://pith.science/pith/DDOHM55XD3TDYLCGDF7ALJVKGC/action/replication_record"}},"created_at":"2026-07-05T10:43:11.007583+00:00","updated_at":"2026-07-05T10:43:11.007583+00:00"}