{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RW3GNK2SZY4QKJNSF6DAGWQBGR","short_pith_number":"pith:RW3GNK2S","canonical_record":{"source":{"id":"2111.00034","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T18:22:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8580e7ea2356319b4cc6a1558fc0d0c837c90911f534debf0f3206ac61cf5b2c","abstract_canon_sha256":"1ca4e3f8d6d5126412f3029d616a6ad14a20a63c1b3fd73c5a1c66606c3d99f5"},"schema_version":"1.0"},"canonical_sha256":"8db666ab52ce390525b22f86035a01345aa201668c7736539c3d8d89da268d3d","source":{"kind":"arxiv","id":"2111.00034","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00034","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00034v2","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00034","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_12","alias_value":"RW3GNK2SZY4Q","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_16","alias_value":"RW3GNK2SZY4QKJNS","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_8","alias_value":"RW3GNK2S","created_at":"2026-07-05T03:54:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RW3GNK2SZY4QKJNSF6DAGWQBGR","target":"record","payload":{"canonical_record":{"source":{"id":"2111.00034","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T18:22:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8580e7ea2356319b4cc6a1558fc0d0c837c90911f534debf0f3206ac61cf5b2c","abstract_canon_sha256":"1ca4e3f8d6d5126412f3029d616a6ad14a20a63c1b3fd73c5a1c66606c3d99f5"},"schema_version":"1.0"},"canonical_sha256":"8db666ab52ce390525b22f86035a01345aa201668c7736539c3d8d89da268d3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:03.320566Z","signature_b64":"5H/ywjq99/6Jbn2g8plx90c2spDfnjuGMgNrhFv9NXncwJpRyhnW28GNXEZJjz/eFxwT8ioR/PY2oOySPyfRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8db666ab52ce390525b22f86035a01345aa201668c7736539c3d8d89da268d3d","last_reissued_at":"2026-07-05T03:54:03.320129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:03.320129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.00034","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":"2026-07-05T03:54:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eZIpZS/BzGPzvBOTI4dr6bQ1xG7MCRgS0GGMpn/A/QdAOapD0Nkvs7LGkZRl+ftTGxWfjGo2ISjDt3dDht5sDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:42:56.739234Z"},"content_sha256":"66d8194be4aebe2381179e22933790bf9c31a1d5198b2e08e00683c82fc73391","schema_version":"1.0","event_id":"sha256:66d8194be4aebe2381179e22933790bf9c31a1d5198b2e08e00683c82fc73391"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RW3GNK2SZY4QKJNSF6DAGWQBGR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Networks as Kernel Learners: The Silent Alignment Effect","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Atanasov, Blake Bordelon, Cengiz Pehlevan","submitted_at":"2021-10-29T18:22:46Z","abstract_excerpt":"Neural networks in the lazy training regime converge to kernel machines. Can neural networks in the rich feature learning regime learn a kernel machine with a data-dependent kernel? We demonstrate that this can indeed happen due to a phenomenon we term silent alignment, which requires that the tangent kernel of a network evolves in eigenstructure while small and before the loss appreciably decreases, and grows only in overall scale afterwards. We show that such an effect takes place in homogenous neural networks with small initialization and whitened data. We provide an analytical treatment of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00034","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/2111.00034/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":"2026-07-05T03:54:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r6GLPq98xz48nMfSYaUvV62NdPG301fWNKgEbcBm5aO01PJFfmHUWKKc3tHkDP4GvdywWZFkGQxAj5LwQhDNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:42:56.739746Z"},"content_sha256":"8d24da3584b65440375adb0322c583594b5dc216376eb29284b9bb30a2a9f511","schema_version":"1.0","event_id":"sha256:8d24da3584b65440375adb0322c583594b5dc216376eb29284b9bb30a2a9f511"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RW3GNK2SZY4QKJNSF6DAGWQBGR/bundle.json","state_url":"https://pith.science/pith/RW3GNK2SZY4QKJNSF6DAGWQBGR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RW3GNK2SZY4QKJNSF6DAGWQBGR/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":"2026-08-15T17:42:56Z","links":{"resolver":"https://pith.science/pith/RW3GNK2SZY4QKJNSF6DAGWQBGR","bundle":"https://pith.science/pith/RW3GNK2SZY4QKJNSF6DAGWQBGR/bundle.json","state":"https://pith.science/pith/RW3GNK2SZY4QKJNSF6DAGWQBGR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RW3GNK2SZY4QKJNSF6DAGWQBGR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RW3GNK2SZY4QKJNSF6DAGWQBGR","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":"1ca4e3f8d6d5126412f3029d616a6ad14a20a63c1b3fd73c5a1c66606c3d99f5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T18:22:46Z","title_canon_sha256":"8580e7ea2356319b4cc6a1558fc0d0c837c90911f534debf0f3206ac61cf5b2c"},"schema_version":"1.0","source":{"id":"2111.00034","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00034","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00034v2","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00034","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_12","alias_value":"RW3GNK2SZY4Q","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_16","alias_value":"RW3GNK2SZY4QKJNS","created_at":"2026-07-05T03:54:03Z"},{"alias_kind":"pith_short_8","alias_value":"RW3GNK2S","created_at":"2026-07-05T03:54:03Z"}],"graph_snapshots":[{"event_id":"sha256:8d24da3584b65440375adb0322c583594b5dc216376eb29284b9bb30a2a9f511","target":"graph","created_at":"2026-07-05T03:54:03Z","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/2111.00034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks in the lazy training regime converge to kernel machines. Can neural networks in the rich feature learning regime learn a kernel machine with a data-dependent kernel? We demonstrate that this can indeed happen due to a phenomenon we term silent alignment, which requires that the tangent kernel of a network evolves in eigenstructure while small and before the loss appreciably decreases, and grows only in overall scale afterwards. We show that such an effect takes place in homogenous neural networks with small initialization and whitened data. We provide an analytical treatment of","authors_text":"Alexander Atanasov, Blake Bordelon, Cengiz Pehlevan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T18:22:46Z","title":"Neural Networks as Kernel Learners: The Silent Alignment Effect"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00034","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":"sha256:66d8194be4aebe2381179e22933790bf9c31a1d5198b2e08e00683c82fc73391","target":"record","created_at":"2026-07-05T03:54:03Z","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":"1ca4e3f8d6d5126412f3029d616a6ad14a20a63c1b3fd73c5a1c66606c3d99f5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-29T18:22:46Z","title_canon_sha256":"8580e7ea2356319b4cc6a1558fc0d0c837c90911f534debf0f3206ac61cf5b2c"},"schema_version":"1.0","source":{"id":"2111.00034","kind":"arxiv","version":2}},"canonical_sha256":"8db666ab52ce390525b22f86035a01345aa201668c7736539c3d8d89da268d3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8db666ab52ce390525b22f86035a01345aa201668c7736539c3d8d89da268d3d","first_computed_at":"2026-07-05T03:54:03.320129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:03.320129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5H/ywjq99/6Jbn2g8plx90c2spDfnjuGMgNrhFv9NXncwJpRyhnW28GNXEZJjz/eFxwT8ioR/PY2oOySPyfRAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:03.320566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.00034","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66d8194be4aebe2381179e22933790bf9c31a1d5198b2e08e00683c82fc73391","sha256:8d24da3584b65440375adb0322c583594b5dc216376eb29284b9bb30a2a9f511"],"state_sha256":"4514b1bd05adcaae5a51ee09fb4a4f62884be5e8c983d7c2a626fbe2cc1b6468"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRFZ3Z1nAMv47WS5Yv1CsR7289Di7m6RGCA+WSDwwOKMKEK732JybTAkO1NZ9XZdib//t2/RxN04R+xfeYtRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:42:56.744749Z","bundle_sha256":"764897693cc859b0cc7c43f8d7908bdb660813116fa8a250124e45fbf6ddb635"}}