{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UWKERGVLOISRV6ZCGJMUEX6L64","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":"e26bbb17f1d45ba5b99a42ba68eb2757597bbe74a8df728f6bd0e2c85d3e2dc6","cross_cats_sorted":["cond-mat.dis-nn","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2023-10-03T17:50:40Z","title_canon_sha256":"1bf0801aeb08ca9b7bf36c467d6476d0898f073d41b8512aa385c63271c64d36"},"schema_version":"1.0","source":{"id":"2310.02244","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02244","created_at":"2026-07-05T07:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02244v5","created_at":"2026-07-05T07:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02244","created_at":"2026-07-05T07:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"UWKERGVLOISR","created_at":"2026-07-05T07:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"UWKERGVLOISRV6ZC","created_at":"2026-07-05T07:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"UWKERGVL","created_at":"2026-07-05T07:00:09Z"}],"graph_snapshots":[{"event_id":"sha256:347fe11e2121826d7c830183e2a2c6aca6136ee24bdac9a4a88db7cd76709a3b","target":"graph","created_at":"2026-07-05T07:00:09Z","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/2310.02244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By classifying infinite-width neural networks and identifying the *optimal* limit, Tensor Programs IV and V demonstrated a universal way, called $\\mu$P, for *widthwise hyperparameter transfer*, i.e., predicting optimal hyperparameters of wide neural networks from narrow ones. Here we investigate the analogous classification for *depthwise parametrizations* of deep residual networks (resnets). We classify depthwise parametrizations of block multiplier and learning rate by their infinite-width-then-depth limits. In resnets where each block has only one layer, we identify a unique optimal paramet","authors_text":"Chen Zhu, Dingli Yu, Greg Yang, Soufiane Hayou","cross_cats":["cond-mat.dis-nn","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2023-10-03T17:50:40Z","title":"Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02244","kind":"arxiv","version":5},"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":"sha256:7afcb5374e718df4fed7980f4927941ff7276730cfa576ca7e3fc0f4d2fc8363","target":"record","created_at":"2026-07-05T07:00:09Z","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":"e26bbb17f1d45ba5b99a42ba68eb2757597bbe74a8df728f6bd0e2c85d3e2dc6","cross_cats_sorted":["cond-mat.dis-nn","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2023-10-03T17:50:40Z","title_canon_sha256":"1bf0801aeb08ca9b7bf36c467d6476d0898f073d41b8512aa385c63271c64d36"},"schema_version":"1.0","source":{"id":"2310.02244","kind":"arxiv","version":5}},"canonical_sha256":"a594489aab72251afb223259425fcbf73f1397a0fa30b0fb625c18c086c3265f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a594489aab72251afb223259425fcbf73f1397a0fa30b0fb625c18c086c3265f","first_computed_at":"2026-07-05T07:00:09.711295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:09.711295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wRvLnbpOVAU0oe7bbH7jQgbZM1ikYHGBzfi4+97u9m4SYBAcC/fssJ63EynFR5KBml4G1GlJQ6Chk1rYuOzyBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:09.711796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02244","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7afcb5374e718df4fed7980f4927941ff7276730cfa576ca7e3fc0f4d2fc8363","sha256:347fe11e2121826d7c830183e2a2c6aca6136ee24bdac9a4a88db7cd76709a3b"],"state_sha256":"2656f6cac89bf323f432441ad205c3fee3628c4b8e1f2e50ad2c30276e9477e8"}