{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:T2AQTJAY3E57XU5KLMZPGIIDSV","short_pith_number":"pith:T2AQTJAY","canonical_record":{"source":{"id":"2607.23397","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T00:11:54Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"8c2d5c1ec21fc4d15d789d64c2658d0782ff2f1bb146eb81ea3d8cf5f93ed919","abstract_canon_sha256":"d4e537a8993afddd1f17df01a4f345158e44111e2edfd54c461c1807d2d63d77"},"schema_version":"1.0"},"canonical_sha256":"9e8109a418d93bfbd3aa5b32f3210395665cf69c6323ffa37f0d8567dfd089e8","source":{"kind":"arxiv","id":"2607.23397","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23397","created_at":"2026-07-28T01:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23397v1","created_at":"2026-07-28T01:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23397","created_at":"2026-07-28T01:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"T2AQTJAY3E57","created_at":"2026-07-28T01:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"T2AQTJAY3E57XU5K","created_at":"2026-07-28T01:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"T2AQTJAY","created_at":"2026-07-28T01:22:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:T2AQTJAY3E57XU5KLMZPGIIDSV","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23397","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T00:11:54Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"8c2d5c1ec21fc4d15d789d64c2658d0782ff2f1bb146eb81ea3d8cf5f93ed919","abstract_canon_sha256":"d4e537a8993afddd1f17df01a4f345158e44111e2edfd54c461c1807d2d63d77"},"schema_version":"1.0"},"canonical_sha256":"9e8109a418d93bfbd3aa5b32f3210395665cf69c6323ffa37f0d8567dfd089e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:50.599615Z","signature_b64":"qYnksQNZGHRBzl3chIDip98UiQzlS7ZswLCMnHlP9KAE5YZ/cT7WoAg+hn/4E5sN648SKGnMKfwT+bewWNnnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e8109a418d93bfbd3aa5b32f3210395665cf69c6323ffa37f0d8567dfd089e8","last_reissued_at":"2026-07-28T01:22:50.598850Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:50.598850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23397","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-28T01:22:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5X+MwQUtsarUdnhgBtSymVwmUoolnLo/hjJVIcFByy4LjzFo6WvcBDA8KbBfM7ZRTrqzGVyJu//ZZe91KmAGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:03:39.923999Z"},"content_sha256":"42436e132254c16e2ea798c61d234dc5a276f0d75668f36064bf419093355cc9","schema_version":"1.0","event_id":"sha256:42436e132254c16e2ea798c61d234dc5a276f0d75668f36064bf419093355cc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:T2AQTJAY3E57XU5KLMZPGIIDSV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Statistical Difference between Single-Layer Learning and Hierarchical Learning in Wide Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Sumio Watanabe","submitted_at":"2026-07-26T00:11:54Z","abstract_excerpt":"Hierarchical neural networks are widely used in artificial intelligence, yet their mathematical properties remain incompletely understood. In the infinite-width limit, two different theoretical frameworks have been proposed. One reduces deep learning to kernel regression with a fixed kernel by assuming that the parameters remain close to their initialization, whereas the other allows the parameters to move away from their initialization, requiring the kernel itself to be optimized.\n  In this paper, we study a three-layer neural network with a finite but large number of hidden units. We show th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23397","kind":"arxiv","version":1},"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/2607.23397/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":"2026-07-28T01:22:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0bSneEi+ZZ9iuY6YbXHGpCjr456dX/ddR9ImNEJg2lsmpp2YgK/LbbClDds01eSZGzK/QoT/NbIP05/okzBYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:03:39.924559Z"},"content_sha256":"ced6b24b2b38fefb34a20a2407284cdf78ef4a6e10b68f769360f2697781d0d6","schema_version":"1.0","event_id":"sha256:ced6b24b2b38fefb34a20a2407284cdf78ef4a6e10b68f769360f2697781d0d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T2AQTJAY3E57XU5KLMZPGIIDSV/bundle.json","state_url":"https://pith.science/pith/T2AQTJAY3E57XU5KLMZPGIIDSV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T2AQTJAY3E57XU5KLMZPGIIDSV/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":"2026-08-04T02:03:39Z","links":{"resolver":"https://pith.science/pith/T2AQTJAY3E57XU5KLMZPGIIDSV","bundle":"https://pith.science/pith/T2AQTJAY3E57XU5KLMZPGIIDSV/bundle.json","state":"https://pith.science/pith/T2AQTJAY3E57XU5KLMZPGIIDSV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T2AQTJAY3E57XU5KLMZPGIIDSV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T2AQTJAY3E57XU5KLMZPGIIDSV","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":"d4e537a8993afddd1f17df01a4f345158e44111e2edfd54c461c1807d2d63d77","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T00:11:54Z","title_canon_sha256":"8c2d5c1ec21fc4d15d789d64c2658d0782ff2f1bb146eb81ea3d8cf5f93ed919"},"schema_version":"1.0","source":{"id":"2607.23397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23397","created_at":"2026-07-28T01:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23397v1","created_at":"2026-07-28T01:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23397","created_at":"2026-07-28T01:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"T2AQTJAY3E57","created_at":"2026-07-28T01:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"T2AQTJAY3E57XU5K","created_at":"2026-07-28T01:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"T2AQTJAY","created_at":"2026-07-28T01:22:50Z"}],"graph_snapshots":[{"event_id":"sha256:ced6b24b2b38fefb34a20a2407284cdf78ef4a6e10b68f769360f2697781d0d6","target":"graph","created_at":"2026-07-28T01:22:50Z","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/2607.23397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical neural networks are widely used in artificial intelligence, yet their mathematical properties remain incompletely understood. In the infinite-width limit, two different theoretical frameworks have been proposed. One reduces deep learning to kernel regression with a fixed kernel by assuming that the parameters remain close to their initialization, whereas the other allows the parameters to move away from their initialization, requiring the kernel itself to be optimized.\n  In this paper, we study a three-layer neural network with a finite but large number of hidden units. We show th","authors_text":"Sumio Watanabe","cross_cats":["math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T00:11:54Z","title":"A Statistical Difference between Single-Layer Learning and Hierarchical Learning in Wide Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23397","kind":"arxiv","version":1},"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":"sha256:42436e132254c16e2ea798c61d234dc5a276f0d75668f36064bf419093355cc9","target":"record","created_at":"2026-07-28T01:22:50Z","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":"d4e537a8993afddd1f17df01a4f345158e44111e2edfd54c461c1807d2d63d77","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T00:11:54Z","title_canon_sha256":"8c2d5c1ec21fc4d15d789d64c2658d0782ff2f1bb146eb81ea3d8cf5f93ed919"},"schema_version":"1.0","source":{"id":"2607.23397","kind":"arxiv","version":1}},"canonical_sha256":"9e8109a418d93bfbd3aa5b32f3210395665cf69c6323ffa37f0d8567dfd089e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e8109a418d93bfbd3aa5b32f3210395665cf69c6323ffa37f0d8567dfd089e8","first_computed_at":"2026-07-28T01:22:50.598850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:50.598850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qYnksQNZGHRBzl3chIDip98UiQzlS7ZswLCMnHlP9KAE5YZ/cT7WoAg+hn/4E5sN648SKGnMKfwT+bewWNnnCQ==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:50.599615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42436e132254c16e2ea798c61d234dc5a276f0d75668f36064bf419093355cc9","sha256:ced6b24b2b38fefb34a20a2407284cdf78ef4a6e10b68f769360f2697781d0d6"],"state_sha256":"2d26b1e7e020cfa13ededaa596d435f22570c142d2f6ed9b73bddf8982faf499"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EVC/WyyIkw8P5MnEoZPORPcBOfhvP/CuS46YUdFpetyCvDbztNJNSzZThxJoDV8Lm1paSUa1DDuxFFu3oNC5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T02:03:39.928407Z","bundle_sha256":"cfeb64e94afe4778fb023e4e290e80dc01e3b762f8af22770aad844b46c84e3a"}}