{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NAIME6TMY6ZJJ4FIMXN4RNNPWI","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":"9375d78a3563bd362b7ad4ae54f360aa4e435be2561d2edf60d89f5cce59ccc0","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-09-28T17:20:50Z","title_canon_sha256":"f5a5b124354b648bf3186e5b90638c776028418f1e242a976e04c9b1e5539330"},"schema_version":"1.0","source":{"id":"2309.16620","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16620","created_at":"2026-07-05T07:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16620v2","created_at":"2026-07-05T07:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16620","created_at":"2026-07-05T07:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"NAIME6TMY6ZJ","created_at":"2026-07-05T07:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"NAIME6TMY6ZJJ4FI","created_at":"2026-07-05T07:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"NAIME6TM","created_at":"2026-07-05T07:21:44Z"}],"graph_snapshots":[{"event_id":"sha256:1795f79cf11e24415b49cce26932a01ec508850dfee142aaeaad590b9730b9ac","target":"graph","created_at":"2026-07-05T07:21:44Z","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/2309.16620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The cost of hyperparameter tuning in deep learning has been rising with model sizes, prompting practitioners to find new tuning methods using a proxy of smaller networks. One such proposal uses $\\mu$P parameterized networks, where the optimal hyperparameters for small width networks transfer to networks with arbitrarily large width. However, in this scheme, hyperparameters do not transfer across depths. As a remedy, we study residual networks with a residual branch scale of $1/\\sqrt{\\text{depth}}$ in combination with the $\\mu$P parameterization. We provide experiments demonstrating that residu","authors_text":"Blake Bordelon, Boris Hanin, Cengiz Pehlevan, Lorenzo Noci, Mufan Bill Li","cross_cats":["cond-mat.dis-nn","cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-09-28T17:20:50Z","title":"Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16620","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":"sha256:0c196c6e7b875a9b11b013f0b0b3a2b074ee797272e3d59e39f5e89ac3db45ea","target":"record","created_at":"2026-07-05T07:21:44Z","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":"9375d78a3563bd362b7ad4ae54f360aa4e435be2561d2edf60d89f5cce59ccc0","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-09-28T17:20:50Z","title_canon_sha256":"f5a5b124354b648bf3186e5b90638c776028418f1e242a976e04c9b1e5539330"},"schema_version":"1.0","source":{"id":"2309.16620","kind":"arxiv","version":2}},"canonical_sha256":"6810c27a6cc7b294f0a865dbc8b5afb2322391b822a06ba0f0cf9c90ece40b18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6810c27a6cc7b294f0a865dbc8b5afb2322391b822a06ba0f0cf9c90ece40b18","first_computed_at":"2026-07-05T07:21:44.996784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:44.996784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KMi6bsgtFF7VfEeZPdVKi47kjdrRTWmB3RxgidTL5GmCCfADcoLOS6/MUhqcUEj3Gpg0AFvoBNH4Al9+Dd6IAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:44.997287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16620","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c196c6e7b875a9b11b013f0b0b3a2b074ee797272e3d59e39f5e89ac3db45ea","sha256:1795f79cf11e24415b49cce26932a01ec508850dfee142aaeaad590b9730b9ac"],"state_sha256":"b6dfb4d932d1080d666f13e29a7c3caab472f49fd29069e74b6c44883253bf58"}