{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LXDJX42ESHRIHBPBTYBAMS4JYS","short_pith_number":"pith:LXDJX42E","canonical_record":{"source":{"id":"1710.03667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-10T15:48:12Z","cross_cats_sorted":["cs.LG","physics.data-an","q-bio.NC"],"title_canon_sha256":"9132b369ab609f4616f9456a43bcfc470fcd00760914e727dce70b8417d7b6cb","abstract_canon_sha256":"03ace6ed005f5e187a07f610c3a6b68274cf99f1afb4d0f754b5f846c63911d8"},"schema_version":"1.0"},"canonical_sha256":"5dc69bf34491e28385e19e02064b89c49518fd5f6c42b8351b75cba088a330a6","source":{"kind":"arxiv","id":"1710.03667","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.03667","created_at":"2026-05-18T00:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"1710.03667v1","created_at":"2026-05-18T00:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.03667","created_at":"2026-05-18T00:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"LXDJX42ESHRI","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LXDJX42ESHRIHBPB","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LXDJX42E","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LXDJX42ESHRIHBPBTYBAMS4JYS","target":"record","payload":{"canonical_record":{"source":{"id":"1710.03667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-10T15:48:12Z","cross_cats_sorted":["cs.LG","physics.data-an","q-bio.NC"],"title_canon_sha256":"9132b369ab609f4616f9456a43bcfc470fcd00760914e727dce70b8417d7b6cb","abstract_canon_sha256":"03ace6ed005f5e187a07f610c3a6b68274cf99f1afb4d0f754b5f846c63911d8"},"schema_version":"1.0"},"canonical_sha256":"5dc69bf34491e28385e19e02064b89c49518fd5f6c42b8351b75cba088a330a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:11.044206Z","signature_b64":"F/RRvpgzpz33zfUKpm5D3rZw9iH7Nrqy5cVo0zfFh/GRNh2PIIBsOk7wIidkPbqi30JCREjAIY7oYpkHOEfgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dc69bf34491e28385e19e02064b89c49518fd5f6c42b8351b75cba088a330a6","last_reissued_at":"2026-05-18T00:33:11.043659Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:11.043659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.03667","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":"2026-05-18T00:33:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lurm59x9c/+HGgxyfSajmKlYot/TpLmD04zcb1/I46IXb30ybqBj2mRNKZfYCPY8WMrhesgjBu8orx7kNX9RCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:29:11.442747Z"},"content_sha256":"af4bed3452aa1f890cd0ec76ecc67ee89a080396f30ff8ba0cb9e950e1c4ee39","schema_version":"1.0","event_id":"sha256:af4bed3452aa1f890cd0ec76ecc67ee89a080396f30ff8ba0cb9e950e1c4ee39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LXDJX42ESHRIHBPBTYBAMS4JYS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"High-dimensional dynamics of generalization error in neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.data-an","q-bio.NC"],"primary_cat":"stat.ML","authors_text":"Andrew M. Saxe, Madhu S. Advani","submitted_at":"2017-10-10T15:48:12Z","abstract_excerpt":"We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant \"high-dimensional\" regime where the number of free parameters in the network is on the order of or even larger than the number of examples in the dataset. Using random matrix theory and exact solutions in linear models, we derive the generalization error and training error dynamics of learning and analyze how they depend on the dimensionality of data and signal to noise ratio of the learning problem. We find that the dynamics of gradient "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.03667","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":""},"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":"2026-05-18T00:33:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O47tB3PpRZhKpWeLPPZv+GO4MHjxaG7ZR9INSLF2IvasfuV8g22/pB3dhl7lNbIcRozLTfvnJ6spu1C0xGfSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:29:11.443106Z"},"content_sha256":"7446b5cbdd732dfee06f29484dd1f4e00d31efd0d3ca9af9551c6af4e334bdf2","schema_version":"1.0","event_id":"sha256:7446b5cbdd732dfee06f29484dd1f4e00d31efd0d3ca9af9551c6af4e334bdf2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LXDJX42ESHRIHBPBTYBAMS4JYS/bundle.json","state_url":"https://pith.science/pith/LXDJX42ESHRIHBPBTYBAMS4JYS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LXDJX42ESHRIHBPBTYBAMS4JYS/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":"2026-05-28T01:29:11Z","links":{"resolver":"https://pith.science/pith/LXDJX42ESHRIHBPBTYBAMS4JYS","bundle":"https://pith.science/pith/LXDJX42ESHRIHBPBTYBAMS4JYS/bundle.json","state":"https://pith.science/pith/LXDJX42ESHRIHBPBTYBAMS4JYS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LXDJX42ESHRIHBPBTYBAMS4JYS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LXDJX42ESHRIHBPBTYBAMS4JYS","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":"03ace6ed005f5e187a07f610c3a6b68274cf99f1afb4d0f754b5f846c63911d8","cross_cats_sorted":["cs.LG","physics.data-an","q-bio.NC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-10T15:48:12Z","title_canon_sha256":"9132b369ab609f4616f9456a43bcfc470fcd00760914e727dce70b8417d7b6cb"},"schema_version":"1.0","source":{"id":"1710.03667","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.03667","created_at":"2026-05-18T00:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"1710.03667v1","created_at":"2026-05-18T00:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.03667","created_at":"2026-05-18T00:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"LXDJX42ESHRI","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LXDJX42ESHRIHBPB","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LXDJX42E","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:7446b5cbdd732dfee06f29484dd1f4e00d31efd0d3ca9af9551c6af4e334bdf2","target":"graph","created_at":"2026-05-18T00:33:11Z","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":"We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant \"high-dimensional\" regime where the number of free parameters in the network is on the order of or even larger than the number of examples in the dataset. Using random matrix theory and exact solutions in linear models, we derive the generalization error and training error dynamics of learning and analyze how they depend on the dimensionality of data and signal to noise ratio of the learning problem. We find that the dynamics of gradient ","authors_text":"Andrew M. Saxe, Madhu S. Advani","cross_cats":["cs.LG","physics.data-an","q-bio.NC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-10T15:48:12Z","title":"High-dimensional dynamics of generalization error in neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.03667","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:af4bed3452aa1f890cd0ec76ecc67ee89a080396f30ff8ba0cb9e950e1c4ee39","target":"record","created_at":"2026-05-18T00:33:11Z","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":"03ace6ed005f5e187a07f610c3a6b68274cf99f1afb4d0f754b5f846c63911d8","cross_cats_sorted":["cs.LG","physics.data-an","q-bio.NC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-10T15:48:12Z","title_canon_sha256":"9132b369ab609f4616f9456a43bcfc470fcd00760914e727dce70b8417d7b6cb"},"schema_version":"1.0","source":{"id":"1710.03667","kind":"arxiv","version":1}},"canonical_sha256":"5dc69bf34491e28385e19e02064b89c49518fd5f6c42b8351b75cba088a330a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dc69bf34491e28385e19e02064b89c49518fd5f6c42b8351b75cba088a330a6","first_computed_at":"2026-05-18T00:33:11.043659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:11.043659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F/RRvpgzpz33zfUKpm5D3rZw9iH7Nrqy5cVo0zfFh/GRNh2PIIBsOk7wIidkPbqi30JCREjAIY7oYpkHOEfgBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:11.044206Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.03667","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af4bed3452aa1f890cd0ec76ecc67ee89a080396f30ff8ba0cb9e950e1c4ee39","sha256:7446b5cbdd732dfee06f29484dd1f4e00d31efd0d3ca9af9551c6af4e334bdf2"],"state_sha256":"71bafa1013d0df4e59773c5097d5d55b0bf67e95ff75acbdc6aaa4ab5e872d26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tflsqQuugO55yTCuEOCEwhHp/LAqPlFZ0V34ZTUiHLyl/ltM0HN86iDUH2xlGihXduRRzIqs93ZybuKGRlaZAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T01:29:11.445240Z","bundle_sha256":"76dfe18fefa59891495fb498a0df9d60147fa6c65c1621962324c270509bae80"}}