{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KM3XVFBLGQH4REMSH2PKSYAUYG","short_pith_number":"pith:KM3XVFBL","canonical_record":{"source":{"id":"2011.14522","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T03:21:05Z","cross_cats_sorted":["cond-mat.dis-nn","cs.NE"],"title_canon_sha256":"af3f63d420af4ec0ab564348dee3607a0fdc5a634a914b86481d94bf91f39afd","abstract_canon_sha256":"c45b348ed53c2cbef2c78c061c9521ea933eeb362fbecfc473e6a5d533064ee8"},"schema_version":"1.0"},"canonical_sha256":"53377a942b340fc891923e9ea96014c18b3e070c04d48404622a9fc0f5e4782a","source":{"kind":"arxiv","id":"2011.14522","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.14522","created_at":"2026-07-05T04:40:22Z"},{"alias_kind":"arxiv_version","alias_value":"2011.14522v3","created_at":"2026-07-05T04:40:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14522","created_at":"2026-07-05T04:40:22Z"},{"alias_kind":"pith_short_12","alias_value":"KM3XVFBLGQH4","created_at":"2026-07-05T04:40:22Z"},{"alias_kind":"pith_short_16","alias_value":"KM3XVFBLGQH4REMS","created_at":"2026-07-05T04:40:22Z"},{"alias_kind":"pith_short_8","alias_value":"KM3XVFBL","created_at":"2026-07-05T04:40:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KM3XVFBLGQH4REMSH2PKSYAUYG","target":"record","payload":{"canonical_record":{"source":{"id":"2011.14522","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T03:21:05Z","cross_cats_sorted":["cond-mat.dis-nn","cs.NE"],"title_canon_sha256":"af3f63d420af4ec0ab564348dee3607a0fdc5a634a914b86481d94bf91f39afd","abstract_canon_sha256":"c45b348ed53c2cbef2c78c061c9521ea933eeb362fbecfc473e6a5d533064ee8"},"schema_version":"1.0"},"canonical_sha256":"53377a942b340fc891923e9ea96014c18b3e070c04d48404622a9fc0f5e4782a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:22.744946Z","signature_b64":"TXHgPMy+OLg7hsdfGBXIcjfv7BGrIw9aX96wh19ZdzGaPpAfzFUfvhZTrIvcrtsDJzeICf1YD77fIQy8P5wwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53377a942b340fc891923e9ea96014c18b3e070c04d48404622a9fc0f5e4782a","last_reissued_at":"2026-07-05T04:40:22.744476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:22.744476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.14522","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":"2026-07-05T04:40:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7IAyAQ+tvPVCZ8OvKuP72JV7hkDIBgvL/0/eN0MyXPoDETDXsZ5pCfjc0Tyw61gnpgNC9Un7HMMAvttqV13kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:25:28.536129Z"},"content_sha256":"ad36a0fee09825241ae3d099c74b62174a2ad597dfcf520980b3cdff2091e711","schema_version":"1.0","event_id":"sha256:ad36a0fee09825241ae3d099c74b62174a2ad597dfcf520980b3cdff2091e711"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KM3XVFBLGQH4REMSH2PKSYAUYG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feature Learning in Infinite-Width Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.NE"],"primary_cat":"cs.LG","authors_text":"Edward J. Hu, Greg Yang","submitted_at":"2020-11-30T03:21:05Z","abstract_excerpt":"As its width tends to infinity, a deep neural network's behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the NTK parametrization). However, we show that the standard and NTK parametrizations of a neural network do not admit infinite-width limits that can learn features, which is crucial for pretraining and transfer learning such as with BERT. We propose simple modifications to the standard parametrization to allow for feature learning in the limit. Using the *Tensor Programs* techniq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14522","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/2011.14522/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":"2026-07-05T04:40:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YfGnM7eAh1WX0nA60GgE/mV2NdsHySR6fKJOZLIkC6PgqKW9zXbzwXJBRlxUBFDbhaSrI3wthKjulHkTJE3WDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:25:28.536646Z"},"content_sha256":"bdb50a39ffc843a1ad9b9dd41a37338d544fba65e0a87621dc62df1b515070e7","schema_version":"1.0","event_id":"sha256:bdb50a39ffc843a1ad9b9dd41a37338d544fba65e0a87621dc62df1b515070e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KM3XVFBLGQH4REMSH2PKSYAUYG/bundle.json","state_url":"https://pith.science/pith/KM3XVFBLGQH4REMSH2PKSYAUYG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KM3XVFBLGQH4REMSH2PKSYAUYG/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":"2026-08-05T01:25:28Z","links":{"resolver":"https://pith.science/pith/KM3XVFBLGQH4REMSH2PKSYAUYG","bundle":"https://pith.science/pith/KM3XVFBLGQH4REMSH2PKSYAUYG/bundle.json","state":"https://pith.science/pith/KM3XVFBLGQH4REMSH2PKSYAUYG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KM3XVFBLGQH4REMSH2PKSYAUYG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KM3XVFBLGQH4REMSH2PKSYAUYG","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":"c45b348ed53c2cbef2c78c061c9521ea933eeb362fbecfc473e6a5d533064ee8","cross_cats_sorted":["cond-mat.dis-nn","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T03:21:05Z","title_canon_sha256":"af3f63d420af4ec0ab564348dee3607a0fdc5a634a914b86481d94bf91f39afd"},"schema_version":"1.0","source":{"id":"2011.14522","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.14522","created_at":"2026-07-05T04:40:22Z"},{"alias_kind":"arxiv_version","alias_value":"2011.14522v3","created_at":"2026-07-05T04:40:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14522","created_at":"2026-07-05T04:40:22Z"},{"alias_kind":"pith_short_12","alias_value":"KM3XVFBLGQH4","created_at":"2026-07-05T04:40:22Z"},{"alias_kind":"pith_short_16","alias_value":"KM3XVFBLGQH4REMS","created_at":"2026-07-05T04:40:22Z"},{"alias_kind":"pith_short_8","alias_value":"KM3XVFBL","created_at":"2026-07-05T04:40:22Z"}],"graph_snapshots":[{"event_id":"sha256:bdb50a39ffc843a1ad9b9dd41a37338d544fba65e0a87621dc62df1b515070e7","target":"graph","created_at":"2026-07-05T04:40:22Z","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/2011.14522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As its width tends to infinity, a deep neural network's behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the NTK parametrization). However, we show that the standard and NTK parametrizations of a neural network do not admit infinite-width limits that can learn features, which is crucial for pretraining and transfer learning such as with BERT. We propose simple modifications to the standard parametrization to allow for feature learning in the limit. Using the *Tensor Programs* techniq","authors_text":"Edward J. Hu, Greg Yang","cross_cats":["cond-mat.dis-nn","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T03:21:05Z","title":"Feature Learning in Infinite-Width Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14522","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:ad36a0fee09825241ae3d099c74b62174a2ad597dfcf520980b3cdff2091e711","target":"record","created_at":"2026-07-05T04:40:22Z","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":"c45b348ed53c2cbef2c78c061c9521ea933eeb362fbecfc473e6a5d533064ee8","cross_cats_sorted":["cond-mat.dis-nn","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T03:21:05Z","title_canon_sha256":"af3f63d420af4ec0ab564348dee3607a0fdc5a634a914b86481d94bf91f39afd"},"schema_version":"1.0","source":{"id":"2011.14522","kind":"arxiv","version":3}},"canonical_sha256":"53377a942b340fc891923e9ea96014c18b3e070c04d48404622a9fc0f5e4782a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53377a942b340fc891923e9ea96014c18b3e070c04d48404622a9fc0f5e4782a","first_computed_at":"2026-07-05T04:40:22.744476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:22.744476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TXHgPMy+OLg7hsdfGBXIcjfv7BGrIw9aX96wh19ZdzGaPpAfzFUfvhZTrIvcrtsDJzeICf1YD77fIQy8P5wwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:22.744946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.14522","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad36a0fee09825241ae3d099c74b62174a2ad597dfcf520980b3cdff2091e711","sha256:bdb50a39ffc843a1ad9b9dd41a37338d544fba65e0a87621dc62df1b515070e7"],"state_sha256":"2c26cdd41d86af6aec1db70a78d8252dbb09e41960ba0e9cb11fe3add5109548"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"epVduHKfudJaI+6mdJsZVAsAiKtOE9j9T5jxeDf6FESfXt8Ce5R5akDb0+qzYtQCZ6D2Ada0PqG0b7Qtl47+Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:25:28.541636Z","bundle_sha256":"88f21121fdd0e05d8e567923d6ce320f599a4d22e9adee0b27ede0dfc6b6b1bb"}}