{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:F5MZPQI3QHCSLJZBNEVNM5BCT4","short_pith_number":"pith:F5MZPQI3","canonical_record":{"source":{"id":"1808.04685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-08-14T13:45:34Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC"],"title_canon_sha256":"7f1a061854713bd34bcefcc5dcca71d6cdc7c9edc11d01f63415e6013f08a097","abstract_canon_sha256":"c0383f01ed465aa44f74bfd9273d17c15d25dfeb4169d35b8e12b26731902560"},"schema_version":"1.0"},"canonical_sha256":"2f5997c11b81c525a721692ad674229f1975cc25b59c15e1547ec4eb3b43dd39","source":{"kind":"arxiv","id":"1808.04685","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04685","created_at":"2026-05-17T23:47:30Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04685v2","created_at":"2026-05-17T23:47:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04685","created_at":"2026-05-17T23:47:30Z"},{"alias_kind":"pith_short_12","alias_value":"F5MZPQI3QHCS","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"F5MZPQI3QHCSLJZB","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"F5MZPQI3","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:F5MZPQI3QHCSLJZBNEVNM5BCT4","target":"record","payload":{"canonical_record":{"source":{"id":"1808.04685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-08-14T13:45:34Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC"],"title_canon_sha256":"7f1a061854713bd34bcefcc5dcca71d6cdc7c9edc11d01f63415e6013f08a097","abstract_canon_sha256":"c0383f01ed465aa44f74bfd9273d17c15d25dfeb4169d35b8e12b26731902560"},"schema_version":"1.0"},"canonical_sha256":"2f5997c11b81c525a721692ad674229f1975cc25b59c15e1547ec4eb3b43dd39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:30.552161Z","signature_b64":"O0gMEX6UqCrYQsO9ruBLb6mnyH278eUWtFVwGCF70uoinmlOQjeJ3QmDEnAxLgT7RbdD78q6+BbMODkUPiwUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f5997c11b81c525a721692ad674229f1975cc25b59c15e1547ec4eb3b43dd39","last_reissued_at":"2026-05-17T23:47:30.551770Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:30.551770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.04685","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":"2026-05-17T23:47:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jtfrup6Qnuyc60LlmO8ruXjRuh+OgoMyVlLXUOEPhagKlbIFLOKmhkCXRyr49kOZcrcJAgzAaJ+GshhWMAUDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T05:51:22.237878Z"},"content_sha256":"8a6c08d3a8dfb52f4ee9e70e351202a3fb707a213341d67d1069fdfb30c96537","schema_version":"1.0","event_id":"sha256:8a6c08d3a8dfb52f4ee9e70e351202a3fb707a213341d67d1069fdfb30c96537"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:F5MZPQI3QHCSLJZBNEVNM5BCT4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.OC"],"primary_cat":"stat.ML","authors_text":"Gang Wang, Georgios B. Giannakis, Jie Chen","submitted_at":"2018-08-14T13:45:34Z","abstract_excerpt":"Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the underlying data distribution being e.g. Gaussian, or require the network size and/or training size to be sufficiently large. In this context, the problem of learning a two-layer ReLU network is approached in a binary classification setting, where the data are linearly separable and a hinge loss criterion is adopted. Leveraging the power of random noise pertu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04685","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":"2026-05-17T23:47:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I6EXP3KkTcpxJvbq/Nmwf2Fes9vWRTlZUjLzYbIrXg32ERMjuVs6dLp8d6X4LzTzYWTbCnbmardDa//NDOfnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T05:51:22.238222Z"},"content_sha256":"47317469a2365f21819b613f370d3ddbbc018539413b9c81dd52f2027dcaf299","schema_version":"1.0","event_id":"sha256:47317469a2365f21819b613f370d3ddbbc018539413b9c81dd52f2027dcaf299"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5MZPQI3QHCSLJZBNEVNM5BCT4/bundle.json","state_url":"https://pith.science/pith/F5MZPQI3QHCSLJZBNEVNM5BCT4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5MZPQI3QHCSLJZBNEVNM5BCT4/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":"2026-05-20T05:51:22Z","links":{"resolver":"https://pith.science/pith/F5MZPQI3QHCSLJZBNEVNM5BCT4","bundle":"https://pith.science/pith/F5MZPQI3QHCSLJZBNEVNM5BCT4/bundle.json","state":"https://pith.science/pith/F5MZPQI3QHCSLJZBNEVNM5BCT4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5MZPQI3QHCSLJZBNEVNM5BCT4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:F5MZPQI3QHCSLJZBNEVNM5BCT4","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":"c0383f01ed465aa44f74bfd9273d17c15d25dfeb4169d35b8e12b26731902560","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-08-14T13:45:34Z","title_canon_sha256":"7f1a061854713bd34bcefcc5dcca71d6cdc7c9edc11d01f63415e6013f08a097"},"schema_version":"1.0","source":{"id":"1808.04685","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04685","created_at":"2026-05-17T23:47:30Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04685v2","created_at":"2026-05-17T23:47:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04685","created_at":"2026-05-17T23:47:30Z"},{"alias_kind":"pith_short_12","alias_value":"F5MZPQI3QHCS","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"F5MZPQI3QHCSLJZB","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"F5MZPQI3","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:47317469a2365f21819b613f370d3ddbbc018539413b9c81dd52f2027dcaf299","target":"graph","created_at":"2026-05-17T23:47:30Z","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":"Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the underlying data distribution being e.g. Gaussian, or require the network size and/or training size to be sufficiently large. In this context, the problem of learning a two-layer ReLU network is approached in a binary classification setting, where the data are linearly separable and a hinge loss criterion is adopted. Leveraging the power of random noise pertu","authors_text":"Gang Wang, Georgios B. Giannakis, Jie Chen","cross_cats":["cs.IT","cs.LG","math.IT","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-08-14T13:45:34Z","title":"Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04685","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":"sha256:8a6c08d3a8dfb52f4ee9e70e351202a3fb707a213341d67d1069fdfb30c96537","target":"record","created_at":"2026-05-17T23:47:30Z","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":"c0383f01ed465aa44f74bfd9273d17c15d25dfeb4169d35b8e12b26731902560","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-08-14T13:45:34Z","title_canon_sha256":"7f1a061854713bd34bcefcc5dcca71d6cdc7c9edc11d01f63415e6013f08a097"},"schema_version":"1.0","source":{"id":"1808.04685","kind":"arxiv","version":2}},"canonical_sha256":"2f5997c11b81c525a721692ad674229f1975cc25b59c15e1547ec4eb3b43dd39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f5997c11b81c525a721692ad674229f1975cc25b59c15e1547ec4eb3b43dd39","first_computed_at":"2026-05-17T23:47:30.551770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:30.551770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O0gMEX6UqCrYQsO9ruBLb6mnyH278eUWtFVwGCF70uoinmlOQjeJ3QmDEnAxLgT7RbdD78q6+BbMODkUPiwUCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:30.552161Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.04685","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a6c08d3a8dfb52f4ee9e70e351202a3fb707a213341d67d1069fdfb30c96537","sha256:47317469a2365f21819b613f370d3ddbbc018539413b9c81dd52f2027dcaf299"],"state_sha256":"9452bbe6fb0fa4a3945eb61ed7bb5c304ba137d52c1c343d151e2325b8bfe69e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lm+6OxFmYOrCMDm6ySfjjshbLbYk0WX/lX1jDuQETtd3Xfcmk/fpZc98CxSi2fR3XMydW23X7EiXgUJc1TkLCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T05:51:22.240149Z","bundle_sha256":"d9e80ab50e79da2bf60c0aca62de9d1aacc8f7d999be11f4c3fb020517939086"}}