{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IQSTKAOLKUZUNS4KFKDZ4GKV44","short_pith_number":"pith:IQSTKAOL","canonical_record":{"source":{"id":"2506.17305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-18T01:25:16Z","cross_cats_sorted":[],"title_canon_sha256":"6551ae7fa6642c69200487146abd05b7bff60d67f4292330729aac0607421b76","abstract_canon_sha256":"ee70f33a20faa6b9308234bb289bb91c77db206a05007e71dc8151777981a629"},"schema_version":"1.0"},"canonical_sha256":"44253501cb553346cb8a2a879e1955e701005b7e931c6b21274ce9537c2c07c9","source":{"kind":"arxiv","id":"2506.17305","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17305","created_at":"2026-07-05T11:25:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17305v1","created_at":"2026-07-05T11:25:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17305","created_at":"2026-07-05T11:25:15Z"},{"alias_kind":"pith_short_12","alias_value":"IQSTKAOLKUZU","created_at":"2026-07-05T11:25:15Z"},{"alias_kind":"pith_short_16","alias_value":"IQSTKAOLKUZUNS4K","created_at":"2026-07-05T11:25:15Z"},{"alias_kind":"pith_short_8","alias_value":"IQSTKAOL","created_at":"2026-07-05T11:25:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IQSTKAOLKUZUNS4KFKDZ4GKV44","target":"record","payload":{"canonical_record":{"source":{"id":"2506.17305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-18T01:25:16Z","cross_cats_sorted":[],"title_canon_sha256":"6551ae7fa6642c69200487146abd05b7bff60d67f4292330729aac0607421b76","abstract_canon_sha256":"ee70f33a20faa6b9308234bb289bb91c77db206a05007e71dc8151777981a629"},"schema_version":"1.0"},"canonical_sha256":"44253501cb553346cb8a2a879e1955e701005b7e931c6b21274ce9537c2c07c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:15.355903Z","signature_b64":"Y3desWcqUuj62rdNUNYkZzzfD1rEM2DFplx4d7mhaOUSCjVK2z+5cbZyvOlJBay5qqy9o7D5q/fDsRNqBrUFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44253501cb553346cb8a2a879e1955e701005b7e931c6b21274ce9537c2c07c9","last_reissued_at":"2026-07-05T11:25:15.355396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:15.355396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.17305","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:25:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/UPtbhx8I/4RKg1lIUxfjF3BLj8GLtEIRAuJGto149guZ56nvRuXmU40RKjRnNHr8lTu4tRizEX6pKR0qHDUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:43:15.784903Z"},"content_sha256":"1dee113e61b0dd59f173094008c378a37a0d1b063996025dc2d30bf3c888e7fa","schema_version":"1.0","event_id":"sha256:1dee113e61b0dd59f173094008c378a37a0d1b063996025dc2d30bf3c888e7fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IQSTKAOLKUZUNS4KFKDZ4GKV44","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KKT-based optimality conditions for neural network approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Julien Ugon, Nadezda Sukhorukova, Vinesha Peiris","submitted_at":"2025-06-18T01:25:16Z","abstract_excerpt":"In this paper, we obtain necessary optimality conditions for neural network approximation. We consider neural networks in Manhattan ($l_1$ norm) and Chebyshev ($\\max$ norm). The optimality conditions are based on neural networks with at most one hidden layer. We reformulate nonsmooth unconstrained optimisation problems as larger dimension constrained problems with smooth objective functions and constraints. Then we use KKT conditions to develop the necessary conditions and present the optimality conditions in terms of convex analysis and convex sets."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17305","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/2506.17305/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:25:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AJS9FoPdVq+rRv1JKCzaZYBHre3RLXURmm4qRYpiOYcAwNEwDfo3whSzB4PJnBkSFF0naLstnHdylEC9N4XYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:43:15.785397Z"},"content_sha256":"19301b00798b80b1cff8db652014b093cb629603b48dd67475d27c04ef25d73c","schema_version":"1.0","event_id":"sha256:19301b00798b80b1cff8db652014b093cb629603b48dd67475d27c04ef25d73c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQSTKAOLKUZUNS4KFKDZ4GKV44/bundle.json","state_url":"https://pith.science/pith/IQSTKAOLKUZUNS4KFKDZ4GKV44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQSTKAOLKUZUNS4KFKDZ4GKV44/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T19:43:15Z","links":{"resolver":"https://pith.science/pith/IQSTKAOLKUZUNS4KFKDZ4GKV44","bundle":"https://pith.science/pith/IQSTKAOLKUZUNS4KFKDZ4GKV44/bundle.json","state":"https://pith.science/pith/IQSTKAOLKUZUNS4KFKDZ4GKV44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQSTKAOLKUZUNS4KFKDZ4GKV44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IQSTKAOLKUZUNS4KFKDZ4GKV44","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":"ee70f33a20faa6b9308234bb289bb91c77db206a05007e71dc8151777981a629","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-18T01:25:16Z","title_canon_sha256":"6551ae7fa6642c69200487146abd05b7bff60d67f4292330729aac0607421b76"},"schema_version":"1.0","source":{"id":"2506.17305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17305","created_at":"2026-07-05T11:25:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17305v1","created_at":"2026-07-05T11:25:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17305","created_at":"2026-07-05T11:25:15Z"},{"alias_kind":"pith_short_12","alias_value":"IQSTKAOLKUZU","created_at":"2026-07-05T11:25:15Z"},{"alias_kind":"pith_short_16","alias_value":"IQSTKAOLKUZUNS4K","created_at":"2026-07-05T11:25:15Z"},{"alias_kind":"pith_short_8","alias_value":"IQSTKAOL","created_at":"2026-07-05T11:25:15Z"}],"graph_snapshots":[{"event_id":"sha256:19301b00798b80b1cff8db652014b093cb629603b48dd67475d27c04ef25d73c","target":"graph","created_at":"2026-07-05T11:25:15Z","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/2506.17305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we obtain necessary optimality conditions for neural network approximation. We consider neural networks in Manhattan ($l_1$ norm) and Chebyshev ($\\max$ norm). The optimality conditions are based on neural networks with at most one hidden layer. We reformulate nonsmooth unconstrained optimisation problems as larger dimension constrained problems with smooth objective functions and constraints. Then we use KKT conditions to develop the necessary conditions and present the optimality conditions in terms of convex analysis and convex sets.","authors_text":"Julien Ugon, Nadezda Sukhorukova, Vinesha Peiris","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-18T01:25:16Z","title":"KKT-based optimality conditions for neural network approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17305","kind":"arxiv","version":1},"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":"sha256:1dee113e61b0dd59f173094008c378a37a0d1b063996025dc2d30bf3c888e7fa","target":"record","created_at":"2026-07-05T11:25:15Z","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":"ee70f33a20faa6b9308234bb289bb91c77db206a05007e71dc8151777981a629","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-18T01:25:16Z","title_canon_sha256":"6551ae7fa6642c69200487146abd05b7bff60d67f4292330729aac0607421b76"},"schema_version":"1.0","source":{"id":"2506.17305","kind":"arxiv","version":1}},"canonical_sha256":"44253501cb553346cb8a2a879e1955e701005b7e931c6b21274ce9537c2c07c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44253501cb553346cb8a2a879e1955e701005b7e931c6b21274ce9537c2c07c9","first_computed_at":"2026-07-05T11:25:15.355396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:15.355396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y3desWcqUuj62rdNUNYkZzzfD1rEM2DFplx4d7mhaOUSCjVK2z+5cbZyvOlJBay5qqy9o7D5q/fDsRNqBrUFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:15.355903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dee113e61b0dd59f173094008c378a37a0d1b063996025dc2d30bf3c888e7fa","sha256:19301b00798b80b1cff8db652014b093cb629603b48dd67475d27c04ef25d73c"],"state_sha256":"d824f738e77926ddff79cf343fe1d10562c481f2ee08534f2b3221af9793faa1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w7bu39K5tTQRmAz/9MDwWKGxWyqWJKuP5q/XC9154pBucs1yxcVAxP3O0FLhTG4Nk4hNFJ9ue3/Ig0wNuHVLAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:43:15.790469Z","bundle_sha256":"b87d02b9ef999e7ffb1f724604509e5a76d09eba83fe128ecbca3f5bb648e83f"}}