{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IPC57PUD3BWRM57Q2YTQRZN5EC","short_pith_number":"pith:IPC57PUD","schema_version":"1.0","canonical_sha256":"43c5dfbe83d86d1677f0d62708e5bd20ae47189147cab48cb28d8b0c8aee6747","source":{"kind":"arxiv","id":"2210.00973","version":2},"attestation_state":"computed","paper":{"title":"NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MS","eess.SP","math.OC"],"primary_cat":"cs.LG","authors_text":"Buyun Liang, Ju Sun, Tim Mitchell","submitted_at":"2022-10-03T14:41:26Z","abstract_excerpt":"Imposing explicit constraints is relatively new but increasingly pressing in deep learning, stimulated by, e.g., trustworthy AI that performs robust optimization over complicated perturbation sets and scientific applications that need to respect physical laws and constraints. However, it can be hard to reliably solve constrained deep learning problems without optimization expertise. The existing deep learning frameworks do not admit constraints. General-purpose optimization packages can handle constraints but do not perform auto-differentiation and have trouble dealing with nonsmoothness. In t"},"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":"2210.00973","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T14:41:26Z","cross_cats_sorted":["cs.CV","cs.MS","eess.SP","math.OC"],"title_canon_sha256":"03934e4b9431c22ea8344d322e56300aef94fc9f792a9752014b9e2ee1c6c2dc","abstract_canon_sha256":"7d591e3daef9e1643fe60eec2fe1ea464e03926e6cbaf7da70e8145bfa790213"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:42.944297Z","signature_b64":"nsAH9+Oevstp+8T0ZEV9nCJqyUMUdhPhsSTzlRwSrMd1XAfYS2NOqWjve38GEOTQvThoIJv6rv+nzAvIRHHiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43c5dfbe83d86d1677f0d62708e5bd20ae47189147cab48cb28d8b0c8aee6747","last_reissued_at":"2026-07-05T05:15:42.943783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:42.943783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MS","eess.SP","math.OC"],"primary_cat":"cs.LG","authors_text":"Buyun Liang, Ju Sun, Tim Mitchell","submitted_at":"2022-10-03T14:41:26Z","abstract_excerpt":"Imposing explicit constraints is relatively new but increasingly pressing in deep learning, stimulated by, e.g., trustworthy AI that performs robust optimization over complicated perturbation sets and scientific applications that need to respect physical laws and constraints. However, it can be hard to reliably solve constrained deep learning problems without optimization expertise. The existing deep learning frameworks do not admit constraints. General-purpose optimization packages can handle constraints but do not perform auto-differentiation and have trouble dealing with nonsmoothness. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00973","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/2210.00973/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":"2210.00973","created_at":"2026-07-05T05:15:42.943839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00973v2","created_at":"2026-07-05T05:15:42.943839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00973","created_at":"2026-07-05T05:15:42.943839+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPC57PUD3BWR","created_at":"2026-07-05T05:15:42.943839+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPC57PUD3BWRM57Q","created_at":"2026-07-05T05:15:42.943839+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPC57PUD","created_at":"2026-07-05T05:15:42.943839+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02896","citing_title":"Disciplined Nonlinear Programming","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12813","citing_title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","ref_index":168,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPC57PUD3BWRM57Q2YTQRZN5EC","json":"https://pith.science/pith/IPC57PUD3BWRM57Q2YTQRZN5EC.json","graph_json":"https://pith.science/api/pith-number/IPC57PUD3BWRM57Q2YTQRZN5EC/graph.json","events_json":"https://pith.science/api/pith-number/IPC57PUD3BWRM57Q2YTQRZN5EC/events.json","paper":"https://pith.science/paper/IPC57PUD"},"agent_actions":{"view_html":"https://pith.science/pith/IPC57PUD3BWRM57Q2YTQRZN5EC","download_json":"https://pith.science/pith/IPC57PUD3BWRM57Q2YTQRZN5EC.json","view_paper":"https://pith.science/paper/IPC57PUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00973&json=true","fetch_graph":"https://pith.science/api/pith-number/IPC57PUD3BWRM57Q2YTQRZN5EC/graph.json","fetch_events":"https://pith.science/api/pith-number/IPC57PUD3BWRM57Q2YTQRZN5EC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPC57PUD3BWRM57Q2YTQRZN5EC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPC57PUD3BWRM57Q2YTQRZN5EC/action/storage_attestation","attest_author":"https://pith.science/pith/IPC57PUD3BWRM57Q2YTQRZN5EC/action/author_attestation","sign_citation":"https://pith.science/pith/IPC57PUD3BWRM57Q2YTQRZN5EC/action/citation_signature","submit_replication":"https://pith.science/pith/IPC57PUD3BWRM57Q2YTQRZN5EC/action/replication_record"}},"created_at":"2026-07-05T05:15:42.943839+00:00","updated_at":"2026-07-05T05:15:42.943839+00:00"}