{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:B54UWSXA6N55FU2SE65CKZPUHT","short_pith_number":"pith:B54UWSXA","canonical_record":{"source":{"id":"1901.08276","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:20:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"81e8226b24d614f04ad78b83629842294736040678978382d80d79080478db76","abstract_canon_sha256":"8494be1dc4b6bddd235c9bf7af83760bc2296a7b1095c96374dfc5e131120872"},"schema_version":"1.0"},"canonical_sha256":"0f794b4ae0f37bd2d35227ba2565f43cdfcaeab3c791720faa3c383189b789dd","source":{"kind":"arxiv","id":"1901.08276","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08276","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08276v1","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08276","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"B54UWSXA6N55","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"B54UWSXA6N55FU2S","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"B54UWSXA","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:B54UWSXA6N55FU2SE65CKZPUHT","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08276","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:20:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"81e8226b24d614f04ad78b83629842294736040678978382d80d79080478db76","abstract_canon_sha256":"8494be1dc4b6bddd235c9bf7af83760bc2296a7b1095c96374dfc5e131120872"},"schema_version":"1.0"},"canonical_sha256":"0f794b4ae0f37bd2d35227ba2565f43cdfcaeab3c791720faa3c383189b789dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:37.466802Z","signature_b64":"tET+visdhFSn1JDSNSBNtV83AxbhV9E1szGXYRE4XXPnT/eGAeOqvnGQJGTeqpvRfOR7o1gW0YsiaBVg943HAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f794b4ae0f37bd2d35227ba2565f43cdfcaeab3c791720faa3c383189b789dd","last_reissued_at":"2026-05-17T23:55:37.466293Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:37.466293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08276","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":"2026-05-17T23:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zTW6XUlmB/URbhgNClqhp7L7fatQdLMAyB9d+Duv/beJDT7hP+CuVQGciLzmMWMkDYQpIPfUTK6Q+ivuteQkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T19:42:39.723307Z"},"content_sha256":"7454dcbe4a6d9717befdf4eb0030423b26ffffb37fea5ea5cfd7e7dcbbd4a5ed","schema_version":"1.0","event_id":"sha256:7454dcbe4a6d9717befdf4eb0030423b26ffffb37fea5ea5cfd7e7dcbbd4a5ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:B54UWSXA6N55FU2SE65CKZPUHT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Traditional and Heavy-Tailed Self Regularization in Neural Network Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles H. Martin, Michael W. Mahoney","submitted_at":"2019-01-24T08:20:42Z","abstract_excerpt":"Random Matrix Theory (RMT) is applied to analyze the weight matrices of Deep Neural Networks (DNNs), including both production quality, pre-trained models such as AlexNet and Inception, and smaller models trained from scratch, such as LeNet5 and a miniature-AlexNet. Empirical and theoretical results clearly indicate that the empirical spectral density (ESD) of DNN layer matrices displays signatures of traditionally-regularized statistical models, even in the absence of exogenously specifying traditional forms of regularization, such as Dropout or Weight Norm constraints. Building on recent res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08276","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":"2026-05-17T23:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0vmUl/0+a8lukzTHzr2hKzJfttr0YY2zERDtAyoTpyPfdX3ZluFnpz47ds0TSCeVwk4FrJucbaqnOR+BnSAiCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T19:42:39.723668Z"},"content_sha256":"4704b0fd2e2644212ce66c88643035d1e5423cb698da78eeacbdb8b1ac42d251","schema_version":"1.0","event_id":"sha256:4704b0fd2e2644212ce66c88643035d1e5423cb698da78eeacbdb8b1ac42d251"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B54UWSXA6N55FU2SE65CKZPUHT/bundle.json","state_url":"https://pith.science/pith/B54UWSXA6N55FU2SE65CKZPUHT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B54UWSXA6N55FU2SE65CKZPUHT/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":"2026-07-04T19:42:39Z","links":{"resolver":"https://pith.science/pith/B54UWSXA6N55FU2SE65CKZPUHT","bundle":"https://pith.science/pith/B54UWSXA6N55FU2SE65CKZPUHT/bundle.json","state":"https://pith.science/pith/B54UWSXA6N55FU2SE65CKZPUHT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B54UWSXA6N55FU2SE65CKZPUHT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:B54UWSXA6N55FU2SE65CKZPUHT","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":"8494be1dc4b6bddd235c9bf7af83760bc2296a7b1095c96374dfc5e131120872","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:20:42Z","title_canon_sha256":"81e8226b24d614f04ad78b83629842294736040678978382d80d79080478db76"},"schema_version":"1.0","source":{"id":"1901.08276","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08276","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08276v1","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08276","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"B54UWSXA6N55","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"B54UWSXA6N55FU2S","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"B54UWSXA","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:4704b0fd2e2644212ce66c88643035d1e5423cb698da78eeacbdb8b1ac42d251","target":"graph","created_at":"2026-05-17T23:55:37Z","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":"Random Matrix Theory (RMT) is applied to analyze the weight matrices of Deep Neural Networks (DNNs), including both production quality, pre-trained models such as AlexNet and Inception, and smaller models trained from scratch, such as LeNet5 and a miniature-AlexNet. Empirical and theoretical results clearly indicate that the empirical spectral density (ESD) of DNN layer matrices displays signatures of traditionally-regularized statistical models, even in the absence of exogenously specifying traditional forms of regularization, such as Dropout or Weight Norm constraints. Building on recent res","authors_text":"Charles H. Martin, Michael W. Mahoney","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:20:42Z","title":"Traditional and Heavy-Tailed Self Regularization in Neural Network Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08276","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":"sha256:7454dcbe4a6d9717befdf4eb0030423b26ffffb37fea5ea5cfd7e7dcbbd4a5ed","target":"record","created_at":"2026-05-17T23:55:37Z","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":"8494be1dc4b6bddd235c9bf7af83760bc2296a7b1095c96374dfc5e131120872","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:20:42Z","title_canon_sha256":"81e8226b24d614f04ad78b83629842294736040678978382d80d79080478db76"},"schema_version":"1.0","source":{"id":"1901.08276","kind":"arxiv","version":1}},"canonical_sha256":"0f794b4ae0f37bd2d35227ba2565f43cdfcaeab3c791720faa3c383189b789dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f794b4ae0f37bd2d35227ba2565f43cdfcaeab3c791720faa3c383189b789dd","first_computed_at":"2026-05-17T23:55:37.466293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:37.466293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tET+visdhFSn1JDSNSBNtV83AxbhV9E1szGXYRE4XXPnT/eGAeOqvnGQJGTeqpvRfOR7o1gW0YsiaBVg943HAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:37.466802Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08276","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7454dcbe4a6d9717befdf4eb0030423b26ffffb37fea5ea5cfd7e7dcbbd4a5ed","sha256:4704b0fd2e2644212ce66c88643035d1e5423cb698da78eeacbdb8b1ac42d251"],"state_sha256":"b5bb9bb330c5a297edc1b37bad8992c87c3d405c235715b74253154e26ea3f01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmXS7u3S9xGgpz/Hel/segdVPYn6G9QtXSZByAkBHlK5wJR8xOnDIxiquntYEpfl/bliF3gBtzl/trlzIFyPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T19:42:39.725615Z","bundle_sha256":"acdca7e85212f9c4da0906d21fabcc7ae5333dfdf8f8720b379d0ed96155acc3"}}