{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:34OEFIVQLE4M2SWNXAQJQAZE4F","short_pith_number":"pith:34OEFIVQ","canonical_record":{"source":{"id":"1702.03380","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-11T04:02:40Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"8e41b8b3b855c352ad73239abd96f698288eef1f09e2bbf21967f0c0f1bcee81","abstract_canon_sha256":"c3c8d2f3da3820b198ff0623940f67a8219a0e29e6e1811f7e4d91381d28288e"},"schema_version":"1.0"},"canonical_sha256":"df1c42a2b05938cd4acdb820980324e169b1fc01b09241967e7923d8cda58236","source":{"kind":"arxiv","id":"1702.03380","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.03380","created_at":"2026-05-18T00:42:12Z"},{"alias_kind":"arxiv_version","alias_value":"1702.03380v2","created_at":"2026-05-18T00:42:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03380","created_at":"2026-05-18T00:42:12Z"},{"alias_kind":"pith_short_12","alias_value":"34OEFIVQLE4M","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"34OEFIVQLE4M2SWN","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"34OEFIVQ","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:34OEFIVQLE4M2SWNXAQJQAZE4F","target":"record","payload":{"canonical_record":{"source":{"id":"1702.03380","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-11T04:02:40Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"8e41b8b3b855c352ad73239abd96f698288eef1f09e2bbf21967f0c0f1bcee81","abstract_canon_sha256":"c3c8d2f3da3820b198ff0623940f67a8219a0e29e6e1811f7e4d91381d28288e"},"schema_version":"1.0"},"canonical_sha256":"df1c42a2b05938cd4acdb820980324e169b1fc01b09241967e7923d8cda58236","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:12.388302Z","signature_b64":"yHWPtrESSkWJVPKGqGcP8Xvr46AxndpdtcmGuBab/bceH53LQwd8WrJlUs3wySDwhTsUhaqh91W37uBZAM2FAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df1c42a2b05938cd4acdb820980324e169b1fc01b09241967e7923d8cda58236","last_reissued_at":"2026-05-18T00:42:12.387844Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:12.387844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.03380","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:42:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W3Oe5FXV0ycOieypDTq3w6WDnSfzIuOcH0CkgT00vb78SqFzwIYeUsLR79UnIUmOoD+/ZFKnMGY38viY0uteCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T16:36:39.524495Z"},"content_sha256":"1f26c82dba402b6b093641eb7b0eae4b2153b4418f26043caf0ad8887f84fdae","schema_version":"1.0","event_id":"sha256:1f26c82dba402b6b093641eb7b0eae4b2153b4418f26043caf0ad8887f84fdae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:34OEFIVQLE4M2SWNXAQJQAZE4F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Deep Neural Networks via Optimization Over Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Guoqiang Zhang, W. Bastiaan Kleijn","submitted_at":"2017-02-11T04:02:40Z","abstract_excerpt":"In this work, we propose to train a deep neural network by distributed optimization over a graph. Two nonlinear functions are considered: the rectified linear unit (ReLU) and a linear unit with both lower and upper cutoffs (DCutLU). The problem reformulation over a graph is realized by explicitly representing ReLU or DCutLU using a set of slack variables. We then apply the alternating direction method of multipliers (ADMM) to update the weights of the network layerwise by solving subproblems of the reformulated problem. Empirical results suggest that the ADMM-based method is less sensitive to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03380","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":""},"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":"2026-05-18T00:42:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cNxfgx+Y+tC/0QRJzr8hA5GRw6OSnNQOpcPAtDi7tIIj16cBVbd9klxNY1lPaMv31CtHzt5Pc8Dr0igh3Q5TDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T16:36:39.524862Z"},"content_sha256":"ad9c431223eff580479875859e7faa7c586c3abbd770bffc48619451a8017a21","schema_version":"1.0","event_id":"sha256:ad9c431223eff580479875859e7faa7c586c3abbd770bffc48619451a8017a21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/34OEFIVQLE4M2SWNXAQJQAZE4F/bundle.json","state_url":"https://pith.science/pith/34OEFIVQLE4M2SWNXAQJQAZE4F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/34OEFIVQLE4M2SWNXAQJQAZE4F/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":"2026-05-20T16:36:39Z","links":{"resolver":"https://pith.science/pith/34OEFIVQLE4M2SWNXAQJQAZE4F","bundle":"https://pith.science/pith/34OEFIVQLE4M2SWNXAQJQAZE4F/bundle.json","state":"https://pith.science/pith/34OEFIVQLE4M2SWNXAQJQAZE4F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/34OEFIVQLE4M2SWNXAQJQAZE4F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:34OEFIVQLE4M2SWNXAQJQAZE4F","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":"c3c8d2f3da3820b198ff0623940f67a8219a0e29e6e1811f7e4d91381d28288e","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-11T04:02:40Z","title_canon_sha256":"8e41b8b3b855c352ad73239abd96f698288eef1f09e2bbf21967f0c0f1bcee81"},"schema_version":"1.0","source":{"id":"1702.03380","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.03380","created_at":"2026-05-18T00:42:12Z"},{"alias_kind":"arxiv_version","alias_value":"1702.03380v2","created_at":"2026-05-18T00:42:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03380","created_at":"2026-05-18T00:42:12Z"},{"alias_kind":"pith_short_12","alias_value":"34OEFIVQLE4M","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"34OEFIVQLE4M2SWN","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"34OEFIVQ","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:ad9c431223eff580479875859e7faa7c586c3abbd770bffc48619451a8017a21","target":"graph","created_at":"2026-05-18T00:42:12Z","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"},"paper":{"abstract_excerpt":"In this work, we propose to train a deep neural network by distributed optimization over a graph. Two nonlinear functions are considered: the rectified linear unit (ReLU) and a linear unit with both lower and upper cutoffs (DCutLU). The problem reformulation over a graph is realized by explicitly representing ReLU or DCutLU using a set of slack variables. We then apply the alternating direction method of multipliers (ADMM) to update the weights of the network layerwise by solving subproblems of the reformulated problem. Empirical results suggest that the ADMM-based method is less sensitive to ","authors_text":"Guoqiang Zhang, W. Bastiaan Kleijn","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-11T04:02:40Z","title":"Training Deep Neural Networks via Optimization Over Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03380","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":"sha256:1f26c82dba402b6b093641eb7b0eae4b2153b4418f26043caf0ad8887f84fdae","target":"record","created_at":"2026-05-18T00:42:12Z","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":"c3c8d2f3da3820b198ff0623940f67a8219a0e29e6e1811f7e4d91381d28288e","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-11T04:02:40Z","title_canon_sha256":"8e41b8b3b855c352ad73239abd96f698288eef1f09e2bbf21967f0c0f1bcee81"},"schema_version":"1.0","source":{"id":"1702.03380","kind":"arxiv","version":2}},"canonical_sha256":"df1c42a2b05938cd4acdb820980324e169b1fc01b09241967e7923d8cda58236","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df1c42a2b05938cd4acdb820980324e169b1fc01b09241967e7923d8cda58236","first_computed_at":"2026-05-18T00:42:12.387844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:12.387844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yHWPtrESSkWJVPKGqGcP8Xvr46AxndpdtcmGuBab/bceH53LQwd8WrJlUs3wySDwhTsUhaqh91W37uBZAM2FAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:12.388302Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.03380","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f26c82dba402b6b093641eb7b0eae4b2153b4418f26043caf0ad8887f84fdae","sha256:ad9c431223eff580479875859e7faa7c586c3abbd770bffc48619451a8017a21"],"state_sha256":"2ddebb20049ab8492fee487670bc46d9e64770ce79d85bb4e4c8e110e36fc5b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DgZxhUlpUqj4T83677oQuKk86BghhyDSRVJhlW+AtoB4ObPKle/NKRsI/n8HJ54T9r+mH7fRvDQgItiVKiM1DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T16:36:39.526851Z","bundle_sha256":"30f97f4a416af9252e566b85dd85cb0f49c41ad2221444ba1c2ca50f79dc2c19"}}