{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HIF4C7TWEL65JWXMJXKBC4EMUR","short_pith_number":"pith:HIF4C7TW","canonical_record":{"source":{"id":"2203.03466","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-07T15:37:35Z","cross_cats_sorted":["cond-mat.dis-nn","cs.NE"],"title_canon_sha256":"12995e605f7d0abd4b8ec3c27657173aae1dba22b09a0aef0400a4eb703b8e0c","abstract_canon_sha256":"642a7193797b5c515beaaf6ad4a036c12ecdcbc285899beceb0f1a8869583132"},"schema_version":"1.0"},"canonical_sha256":"3a0bc17e7622fdd4daec4dd411708ca4647e9e14ae2082342fe80e16546c8aaa","source":{"kind":"arxiv","id":"2203.03466","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.03466","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2203.03466v2","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03466","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"HIF4C7TWEL65","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"HIF4C7TWEL65JWXM","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"HIF4C7TW","created_at":"2026-07-05T04:09:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HIF4C7TWEL65JWXMJXKBC4EMUR","target":"record","payload":{"canonical_record":{"source":{"id":"2203.03466","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-07T15:37:35Z","cross_cats_sorted":["cond-mat.dis-nn","cs.NE"],"title_canon_sha256":"12995e605f7d0abd4b8ec3c27657173aae1dba22b09a0aef0400a4eb703b8e0c","abstract_canon_sha256":"642a7193797b5c515beaaf6ad4a036c12ecdcbc285899beceb0f1a8869583132"},"schema_version":"1.0"},"canonical_sha256":"3a0bc17e7622fdd4daec4dd411708ca4647e9e14ae2082342fe80e16546c8aaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:02.576710Z","signature_b64":"87hD/Yp1rj5CEmssR7vOf1KvVwAiW/Ro0u+RBDna+8dufQvUU0cYygYBXdR5XuMCi6O2VOMusTHWo97w8G8rBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a0bc17e7622fdd4daec4dd411708ca4647e9e14ae2082342fe80e16546c8aaa","last_reissued_at":"2026-07-05T04:09:02.576236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:02.576236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.03466","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v9h6pCY37M3NASHmbK6a5UlyFMxPo6dSw8yHc5aIxRyEtNClHGSyLNpfizoI6UwVBrTS3eOVIQb4idc+NE8KAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:51:49.959653Z"},"content_sha256":"59c8435a3a58bf4653e8345b675cf56b497ea66f0e35970906a5acb0f4c2963d","schema_version":"1.0","event_id":"sha256:59c8435a3a58bf4653e8345b675cf56b497ea66f0e35970906a5acb0f4c2963d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HIF4C7TWEL65JWXMJXKBC4EMUR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.NE"],"primary_cat":"cs.LG","authors_text":"David Farhi, Edward J. Hu, Greg Yang, Igor Babuschkin, Jakub Pachocki, Jianfeng Gao, Nick Ryder, Szymon Sidor, Weizhu Chen, XiaoDong Liu","submitted_at":"2022-03-07T15:37:35Z","abstract_excerpt":"Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovered Maximal Update Parametrization (muP), many optimal HPs remain stable even as model size changes. This leads to a new HP tuning paradigm we call muTransfer: parametrize the target model in muP, tune the HP indirectly on a smaller model, and zero-shot transfer them to the full-sized model, i.e., without directly tuning the latter at all. We verify muTransfer on Transformer and ResNet. For example, 1) by transferring "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03466","kind":"arxiv","version":2},"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/2203.03466/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":"2026-07-05T04:09:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sJwNPmzkmTa/EGg+yV9kx03L7SBZBDNL2RAuLoNG8JWul7xMCBXqos2og8u124hVtbpYKkfyuSDmjz5/uEpDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:51:49.960646Z"},"content_sha256":"663af4dcdfe6deeca60a81efd7af6f59d5a07b9d0c0df7d0ecef7b3072ed71db","schema_version":"1.0","event_id":"sha256:663af4dcdfe6deeca60a81efd7af6f59d5a07b9d0c0df7d0ecef7b3072ed71db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HIF4C7TWEL65JWXMJXKBC4EMUR/bundle.json","state_url":"https://pith.science/pith/HIF4C7TWEL65JWXMJXKBC4EMUR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HIF4C7TWEL65JWXMJXKBC4EMUR/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":"2026-08-03T16:51:49Z","links":{"resolver":"https://pith.science/pith/HIF4C7TWEL65JWXMJXKBC4EMUR","bundle":"https://pith.science/pith/HIF4C7TWEL65JWXMJXKBC4EMUR/bundle.json","state":"https://pith.science/pith/HIF4C7TWEL65JWXMJXKBC4EMUR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HIF4C7TWEL65JWXMJXKBC4EMUR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HIF4C7TWEL65JWXMJXKBC4EMUR","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":"642a7193797b5c515beaaf6ad4a036c12ecdcbc285899beceb0f1a8869583132","cross_cats_sorted":["cond-mat.dis-nn","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-07T15:37:35Z","title_canon_sha256":"12995e605f7d0abd4b8ec3c27657173aae1dba22b09a0aef0400a4eb703b8e0c"},"schema_version":"1.0","source":{"id":"2203.03466","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.03466","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2203.03466v2","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03466","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"HIF4C7TWEL65","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"HIF4C7TWEL65JWXM","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"HIF4C7TW","created_at":"2026-07-05T04:09:02Z"}],"graph_snapshots":[{"event_id":"sha256:663af4dcdfe6deeca60a81efd7af6f59d5a07b9d0c0df7d0ecef7b3072ed71db","target":"graph","created_at":"2026-07-05T04:09:02Z","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/2203.03466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovered Maximal Update Parametrization (muP), many optimal HPs remain stable even as model size changes. This leads to a new HP tuning paradigm we call muTransfer: parametrize the target model in muP, tune the HP indirectly on a smaller model, and zero-shot transfer them to the full-sized model, i.e., without directly tuning the latter at all. We verify muTransfer on Transformer and ResNet. For example, 1) by transferring ","authors_text":"David Farhi, Edward J. Hu, Greg Yang, Igor Babuschkin, Jakub Pachocki, Jianfeng Gao, Nick Ryder, Szymon Sidor, Weizhu Chen, XiaoDong Liu","cross_cats":["cond-mat.dis-nn","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-07T15:37:35Z","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03466","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":"sha256:59c8435a3a58bf4653e8345b675cf56b497ea66f0e35970906a5acb0f4c2963d","target":"record","created_at":"2026-07-05T04:09:02Z","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":"642a7193797b5c515beaaf6ad4a036c12ecdcbc285899beceb0f1a8869583132","cross_cats_sorted":["cond-mat.dis-nn","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-07T15:37:35Z","title_canon_sha256":"12995e605f7d0abd4b8ec3c27657173aae1dba22b09a0aef0400a4eb703b8e0c"},"schema_version":"1.0","source":{"id":"2203.03466","kind":"arxiv","version":2}},"canonical_sha256":"3a0bc17e7622fdd4daec4dd411708ca4647e9e14ae2082342fe80e16546c8aaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a0bc17e7622fdd4daec4dd411708ca4647e9e14ae2082342fe80e16546c8aaa","first_computed_at":"2026-07-05T04:09:02.576236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:02.576236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"87hD/Yp1rj5CEmssR7vOf1KvVwAiW/Ro0u+RBDna+8dufQvUU0cYygYBXdR5XuMCi6O2VOMusTHWo97w8G8rBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:02.576710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.03466","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59c8435a3a58bf4653e8345b675cf56b497ea66f0e35970906a5acb0f4c2963d","sha256:663af4dcdfe6deeca60a81efd7af6f59d5a07b9d0c0df7d0ecef7b3072ed71db"],"state_sha256":"e2480bd49418d82f2a5a06ba3afae5714df936f4d0d68c0430f75caa3b116d97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8kaYleQ2pw9qP3CklI5S3f3lrt9NIreA9q7Z04U0myMf6RzzUOhUmHbwNXq1ARqsoGdD4xZRjWMGHxNh4bVcCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:51:49.985044Z","bundle_sha256":"bc4a924729d52776c83754f561aec9de9bd8af1c28ca8c5465feb146e7ddebb4"}}