{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SSWST7SUA24LOWMN4DKSQXIMTA","short_pith_number":"pith:SSWST7SU","canonical_record":{"source":{"id":"2502.02531","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:50:55Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"4db3ed34b4531256c106b3d6ee26126d7310ca90227fd4c26af2edcd45a1f367","abstract_canon_sha256":"d4079893b02044da9ffc4369c42c96839850ea664bf929935a3fb8ce17d1c328"},"schema_version":"1.0"},"canonical_sha256":"94ad29fe5406b8b7598de0d5285d0c982769b9028f4e34bbd6e9afbf0136277a","source":{"kind":"arxiv","id":"2502.02531","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02531","created_at":"2026-07-05T11:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02531v3","created_at":"2026-07-05T11:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02531","created_at":"2026-07-05T11:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"SSWST7SUA24L","created_at":"2026-07-05T11:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"SSWST7SUA24LOWMN","created_at":"2026-07-05T11:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"SSWST7SU","created_at":"2026-07-05T11:22:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SSWST7SUA24LOWMN4DKSQXIMTA","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02531","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:50:55Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"4db3ed34b4531256c106b3d6ee26126d7310ca90227fd4c26af2edcd45a1f367","abstract_canon_sha256":"d4079893b02044da9ffc4369c42c96839850ea664bf929935a3fb8ce17d1c328"},"schema_version":"1.0"},"canonical_sha256":"94ad29fe5406b8b7598de0d5285d0c982769b9028f4e34bbd6e9afbf0136277a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:17.599420Z","signature_b64":"yR0iJl/VIEHsgSSH3IPpwK+YDi6C77jqb2WXogGr483XC1l8hJKi/Z6wLmOOL2DI4IJkL/vkgGbvdGEq3i6DCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94ad29fe5406b8b7598de0d5285d0c982769b9028f4e34bbd6e9afbf0136277a","last_reissued_at":"2026-07-05T11:22:17.598713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:17.598713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02531","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mlpEwGI1OJkXS/9wbduslVneRc3Wm7foAmyRdB3IVagD3+db+2Cf5ufD/g9DcQW7zeZMIJDQxvN8BlPuMwPHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:39:25.177822Z"},"content_sha256":"decc5932fae5d7a1cb8ae8404d5be8dafc60856d629fbce2ac9f9924c3cd0b50","schema_version":"1.0","event_id":"sha256:decc5932fae5d7a1cb8ae8404d5be8dafc60856d629fbce2ac9f9924c3cd0b50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SSWST7SUA24LOWMN4DKSQXIMTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Blake Bordelon, Cengiz Pehlevan","submitted_at":"2025-02-04T17:50:55Z","abstract_excerpt":"We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better\" effect of mean-field/maximum-update parameterized networks as well as hyperparameter transfer effects, which can be contrasted with the neural-tangent parameterization where optimal learning rates shift with model width. We provide asymptotic descriptions of both non-residual and residual neural networks, the latter of which enables an infinite depth limit when branches are scaled as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02531","kind":"arxiv","version":3},"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/2502.02531/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T11:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pwR5g8ZPh1P+3JZMbBjuNv6VN9h6HO8jjnUSchroSp/BwGyyMpkCr3YLOwxd0E+GNe8kmS1rbia13g3XlTWqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:39:25.178393Z"},"content_sha256":"a610949914b21b5030570609f9d61c459f867dc000f8816aceb1d803b4b8455c","schema_version":"1.0","event_id":"sha256:a610949914b21b5030570609f9d61c459f867dc000f8816aceb1d803b4b8455c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SSWST7SUA24LOWMN4DKSQXIMTA/bundle.json","state_url":"https://pith.science/pith/SSWST7SUA24LOWMN4DKSQXIMTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SSWST7SUA24LOWMN4DKSQXIMTA/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":"2026-08-09T20:39:25Z","links":{"resolver":"https://pith.science/pith/SSWST7SUA24LOWMN4DKSQXIMTA","bundle":"https://pith.science/pith/SSWST7SUA24LOWMN4DKSQXIMTA/bundle.json","state":"https://pith.science/pith/SSWST7SUA24LOWMN4DKSQXIMTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SSWST7SUA24LOWMN4DKSQXIMTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SSWST7SUA24LOWMN4DKSQXIMTA","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":"d4079893b02044da9ffc4369c42c96839850ea664bf929935a3fb8ce17d1c328","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:50:55Z","title_canon_sha256":"4db3ed34b4531256c106b3d6ee26126d7310ca90227fd4c26af2edcd45a1f367"},"schema_version":"1.0","source":{"id":"2502.02531","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02531","created_at":"2026-07-05T11:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02531v3","created_at":"2026-07-05T11:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02531","created_at":"2026-07-05T11:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"SSWST7SUA24L","created_at":"2026-07-05T11:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"SSWST7SUA24LOWMN","created_at":"2026-07-05T11:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"SSWST7SU","created_at":"2026-07-05T11:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:a610949914b21b5030570609f9d61c459f867dc000f8816aceb1d803b4b8455c","target":"graph","created_at":"2026-07-05T11:22:17Z","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":[],"endpoint":"/pith/2502.02531/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better\" effect of mean-field/maximum-update parameterized networks as well as hyperparameter transfer effects, which can be contrasted with the neural-tangent parameterization where optimal learning rates shift with model width. We provide asymptotic descriptions of both non-residual and residual neural networks, the latter of which enables an infinite depth limit when branches are scaled as ","authors_text":"Blake Bordelon, Cengiz Pehlevan","cross_cats":["cond-mat.dis-nn","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:50:55Z","title":"Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02531","kind":"arxiv","version":3},"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:decc5932fae5d7a1cb8ae8404d5be8dafc60856d629fbce2ac9f9924c3cd0b50","target":"record","created_at":"2026-07-05T11:22:17Z","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":"d4079893b02044da9ffc4369c42c96839850ea664bf929935a3fb8ce17d1c328","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:50:55Z","title_canon_sha256":"4db3ed34b4531256c106b3d6ee26126d7310ca90227fd4c26af2edcd45a1f367"},"schema_version":"1.0","source":{"id":"2502.02531","kind":"arxiv","version":3}},"canonical_sha256":"94ad29fe5406b8b7598de0d5285d0c982769b9028f4e34bbd6e9afbf0136277a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94ad29fe5406b8b7598de0d5285d0c982769b9028f4e34bbd6e9afbf0136277a","first_computed_at":"2026-07-05T11:22:17.598713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:17.598713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yR0iJl/VIEHsgSSH3IPpwK+YDi6C77jqb2WXogGr483XC1l8hJKi/Z6wLmOOL2DI4IJkL/vkgGbvdGEq3i6DCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:17.599420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02531","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:decc5932fae5d7a1cb8ae8404d5be8dafc60856d629fbce2ac9f9924c3cd0b50","sha256:a610949914b21b5030570609f9d61c459f867dc000f8816aceb1d803b4b8455c"],"state_sha256":"d36ebb7f1e73410255f1db8b8e2103a51c6677ee9cfa72145146e8b0e4c05566"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KMVAE67fPwzyNt9xSrubgdtL9ZjGTg/usE0SPTqulMazbISvvO6wnska7k8omGet9jsbkry6/Ie3DMh55yUyDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:39:25.184493Z","bundle_sha256":"6e5839dd083c376a7f5079fefb50ca02d29ed3efafe3676d4e63a88d034cb866"}}