{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SCPXQNZDIYK4OUPKFWSRB6ZCEH","short_pith_number":"pith:SCPXQNZD","canonical_record":{"source":{"id":"2605.17692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T23:20:50Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"c94c17483410ed45c17de441485cdaea5d93ec8d10e9e4577231d5c1dcaf5785","abstract_canon_sha256":"0b8e60ffff7be021e08fdb30197104a6468b9a4cb8e5e3ba99edcadb6c9b4963"},"schema_version":"1.0"},"canonical_sha256":"909f7837234615c751ea2da510fb2221cdbe0f79fc9c8effbf228216e28c56c5","source":{"kind":"arxiv","id":"2605.17692","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17692","created_at":"2026-05-20T00:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17692v1","created_at":"2026-05-20T00:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17692","created_at":"2026-05-20T00:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"SCPXQNZDIYK4","created_at":"2026-05-20T00:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"SCPXQNZDIYK4OUPK","created_at":"2026-05-20T00:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"SCPXQNZD","created_at":"2026-05-20T00:04:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SCPXQNZDIYK4OUPKFWSRB6ZCEH","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T23:20:50Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"c94c17483410ed45c17de441485cdaea5d93ec8d10e9e4577231d5c1dcaf5785","abstract_canon_sha256":"0b8e60ffff7be021e08fdb30197104a6468b9a4cb8e5e3ba99edcadb6c9b4963"},"schema_version":"1.0"},"canonical_sha256":"909f7837234615c751ea2da510fb2221cdbe0f79fc9c8effbf228216e28c56c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:53.067666Z","signature_b64":"EQyQcZ36Qp8PekKxrtfNWqoSbcgluA0H3DHWSusfXUrP/vvO+kCdBuMbttg+277J5RNOxHvlIPbFcR7aMmA3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"909f7837234615c751ea2da510fb2221cdbe0f79fc9c8effbf228216e28c56c5","last_reissued_at":"2026-05-20T00:04:53.066795Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:53.066795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17692","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":"2026-05-20T00:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6oJ1iWxXsMC6QCT4GToLDsldN7LJs25aTBNcAB/0+F7MbkAyatGjowpKBBXGI7KkB7yGe7NV4p7Zk+hVT1vaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:01:29.675893Z"},"content_sha256":"6398de7eb28dbcb3a787c8967e819781768a7fcdd22ec1ca9ed3ee34d25899a1","schema_version":"1.0","event_id":"sha256:6398de7eb28dbcb3a787c8967e819781768a7fcdd22ec1ca9ed3ee34d25899a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SCPXQNZDIYK4OUPKFWSRB6ZCEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exact Convex Reformulations of Linear Neural Networks via Completely Positive Lifting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Alp Yurtsever, Karthik Prakhya","submitted_at":"2026-05-17T23:20:50Z","abstract_excerpt":"We show that the training problem of a deep linear neural network under the squared loss admits an exact convex reformulation in a lifted space over a generalized completely positive cone. The reformulation has the same optimal value as the original nonconvex problem and is linear in the lifted variables, with all nonconvexity encoded in the cone constraint. Its ambient lifted dimension depends only on the input and output dimensions, independent of the network depth and the number of data points, and the bottleneck width enters only through scalar constraints. The construction proceeds by red"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17692","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/2605.17692/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T21:51:57.526512Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T21:49:43.948874Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:43.747761Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.520955Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.430894Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"43f472827ed5c93d4e3d2263b9da1ef5c859337d9d7c4552a7b6b597c1d6de73"},"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":"2026-05-20T00:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6xMTpw83Oy6PIAAe8+HzAdoKMkXA7qInfU6dod35Rx6B6yXOR5dHdL5V1NSn4El8nSqpTva+pMIGUa0DSGoHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:01:29.676410Z"},"content_sha256":"9263f7e1461119fa39f0bc3fdacec83ea87243ea1f4b9a7524ac65cce3e0f569","schema_version":"1.0","event_id":"sha256:9263f7e1461119fa39f0bc3fdacec83ea87243ea1f4b9a7524ac65cce3e0f569"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SCPXQNZDIYK4OUPKFWSRB6ZCEH/bundle.json","state_url":"https://pith.science/pith/SCPXQNZDIYK4OUPKFWSRB6ZCEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SCPXQNZDIYK4OUPKFWSRB6ZCEH/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":"2026-05-27T13:01:29Z","links":{"resolver":"https://pith.science/pith/SCPXQNZDIYK4OUPKFWSRB6ZCEH","bundle":"https://pith.science/pith/SCPXQNZDIYK4OUPKFWSRB6ZCEH/bundle.json","state":"https://pith.science/pith/SCPXQNZDIYK4OUPKFWSRB6ZCEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SCPXQNZDIYK4OUPKFWSRB6ZCEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SCPXQNZDIYK4OUPKFWSRB6ZCEH","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":"0b8e60ffff7be021e08fdb30197104a6468b9a4cb8e5e3ba99edcadb6c9b4963","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T23:20:50Z","title_canon_sha256":"c94c17483410ed45c17de441485cdaea5d93ec8d10e9e4577231d5c1dcaf5785"},"schema_version":"1.0","source":{"id":"2605.17692","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17692","created_at":"2026-05-20T00:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17692v1","created_at":"2026-05-20T00:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17692","created_at":"2026-05-20T00:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"SCPXQNZDIYK4","created_at":"2026-05-20T00:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"SCPXQNZDIYK4OUPK","created_at":"2026-05-20T00:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"SCPXQNZD","created_at":"2026-05-20T00:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:9263f7e1461119fa39f0bc3fdacec83ea87243ea1f4b9a7524ac65cce3e0f569","target":"graph","created_at":"2026-05-20T00:04:53Z","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":[{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T21:51:57.526512Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"shingle_duplication","ran_at":"2026-05-19T21:49:43.948874Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:43.747761Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.520955Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.430894Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17692/integrity.json","findings":[],"snapshot_sha256":"43f472827ed5c93d4e3d2263b9da1ef5c859337d9d7c4552a7b6b597c1d6de73","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show that the training problem of a deep linear neural network under the squared loss admits an exact convex reformulation in a lifted space over a generalized completely positive cone. The reformulation has the same optimal value as the original nonconvex problem and is linear in the lifted variables, with all nonconvexity encoded in the cone constraint. Its ambient lifted dimension depends only on the input and output dimensions, independent of the network depth and the number of data points, and the bottleneck width enters only through scalar constraints. The construction proceeds by red","authors_text":"Alp Yurtsever, Karthik Prakhya","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T23:20:50Z","title":"Exact Convex Reformulations of Linear Neural Networks via Completely Positive Lifting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17692","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":"sha256:6398de7eb28dbcb3a787c8967e819781768a7fcdd22ec1ca9ed3ee34d25899a1","target":"record","created_at":"2026-05-20T00:04:53Z","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":"0b8e60ffff7be021e08fdb30197104a6468b9a4cb8e5e3ba99edcadb6c9b4963","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T23:20:50Z","title_canon_sha256":"c94c17483410ed45c17de441485cdaea5d93ec8d10e9e4577231d5c1dcaf5785"},"schema_version":"1.0","source":{"id":"2605.17692","kind":"arxiv","version":1}},"canonical_sha256":"909f7837234615c751ea2da510fb2221cdbe0f79fc9c8effbf228216e28c56c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"909f7837234615c751ea2da510fb2221cdbe0f79fc9c8effbf228216e28c56c5","first_computed_at":"2026-05-20T00:04:53.066795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:53.066795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EQyQcZ36Qp8PekKxrtfNWqoSbcgluA0H3DHWSusfXUrP/vvO+kCdBuMbttg+277J5RNOxHvlIPbFcR7aMmA3Ag==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:53.067666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17692","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6398de7eb28dbcb3a787c8967e819781768a7fcdd22ec1ca9ed3ee34d25899a1","sha256:9263f7e1461119fa39f0bc3fdacec83ea87243ea1f4b9a7524ac65cce3e0f569"],"state_sha256":"7b5f87caa690767767eaf8b4622e9ad2151e9ca40ede7246374ebbb397df1b7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BMVNjWPENSBIT8zUYX9BqGLPdz/rPHoTt9rGBb366iOwggXPhpHfX7HT3BOeASnHMmiSw0Yg5X8gr4SGyosZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:01:29.680227Z","bundle_sha256":"5609825eb29026143c26486adfcfb90729762848c02a9f31e0571b9edb220844"}}