{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BGWQND4G4JV33FDONTCIS62YKB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fe7accb77c0b8908dde9f780d809e6a42370269fd4914dec6524b6792bdb455a","cross_cats_sorted":["cs.CV","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-08T17:39:05Z","title_canon_sha256":"8250a8650f5c08e12cd48a7f8b2b531f5f343294bd328515b570c877c0edeaac"},"schema_version":"1.0","source":{"id":"2211.04395","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04395","created_at":"2026-07-05T05:31:18Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04395v2","created_at":"2026-07-05T05:31:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04395","created_at":"2026-07-05T05:31:18Z"},{"alias_kind":"pith_short_12","alias_value":"BGWQND4G4JV3","created_at":"2026-07-05T05:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"BGWQND4G4JV33FDO","created_at":"2026-07-05T05:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"BGWQND4G","created_at":"2026-07-05T05:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:9bedc97e65b2664951ab17e554164b87d965cca1d050e487a91934b7be780502","target":"graph","created_at":"2026-07-05T05:31:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.04395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We seek to impose linear, equality constraints in feedforward neural networks. As top layer predictors are usually nonlinear, this is a difficult task if we seek to deploy standard convex optimization methods and strong duality. To overcome this, we introduce a new saddle-point Lagrangian with auxiliary predictor variables on which constraints are imposed. Elimination of the auxiliary variables leads to a dual minimization problem on the Lagrange multipliers introduced to satisfy the linear constraints. This minimization problem is combined with the standard learning problem on the weight matr","authors_text":"Anand Rangarajan, Jaemoon Lee, Pan He, Sanjay Ranka, Tania Banerjee","cross_cats":["cs.CV","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-08T17:39:05Z","title":"Expressing linear equality constraints in feedforward neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04395","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b2202404800e57151c9962516057f512f50c8f0a932a14404094936c5860152a","target":"record","created_at":"2026-07-05T05:31:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fe7accb77c0b8908dde9f780d809e6a42370269fd4914dec6524b6792bdb455a","cross_cats_sorted":["cs.CV","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-08T17:39:05Z","title_canon_sha256":"8250a8650f5c08e12cd48a7f8b2b531f5f343294bd328515b570c877c0edeaac"},"schema_version":"1.0","source":{"id":"2211.04395","kind":"arxiv","version":2}},"canonical_sha256":"09ad068f86e26bbd946e6cc4897b5850600fe536e3a79c82c30e51cf818ac1dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09ad068f86e26bbd946e6cc4897b5850600fe536e3a79c82c30e51cf818ac1dd","first_computed_at":"2026-07-05T05:31:18.325571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:18.325571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"23x+qQtzV2mQJlq/GWTQssksKtwVmS6nvBeMLgDKTLkpoutrj+v8XrdF6TVkJgJFhMkuB/ijHPVj+08BG55CDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:18.326100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.04395","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2202404800e57151c9962516057f512f50c8f0a932a14404094936c5860152a","sha256:9bedc97e65b2664951ab17e554164b87d965cca1d050e487a91934b7be780502"],"state_sha256":"5fa393fdba564e600d4201a46e67fe2342bde33c99cf6e97fe8886b0e8baf51a"}