{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OG6JG3DQY3IBQJH6ILE7BLKFVZ","short_pith_number":"pith:OG6JG3DQ","canonical_record":{"source":{"id":"1905.10264","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T14:45:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6ce8403aac36f7a8603042068785f0deafd436bb133006338e2fb60a44203859","abstract_canon_sha256":"baf49aefcc091f059f505a9bd499d1c03fae7a9281b315b8dd6ca668a0b81781"},"schema_version":"1.0"},"canonical_sha256":"71bc936c70c6d01824fe42c9f0ad45ae7fd6eea1dadd3f6508aaccc6b9c7020a","source":{"kind":"arxiv","id":"1905.10264","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10264","created_at":"2026-05-17T23:45:10Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10264v1","created_at":"2026-05-17T23:45:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10264","created_at":"2026-05-17T23:45:10Z"},{"alias_kind":"pith_short_12","alias_value":"OG6JG3DQY3IB","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OG6JG3DQY3IBQJH6","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OG6JG3DQ","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OG6JG3DQY3IBQJH6ILE7BLKFVZ","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10264","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T14:45:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6ce8403aac36f7a8603042068785f0deafd436bb133006338e2fb60a44203859","abstract_canon_sha256":"baf49aefcc091f059f505a9bd499d1c03fae7a9281b315b8dd6ca668a0b81781"},"schema_version":"1.0"},"canonical_sha256":"71bc936c70c6d01824fe42c9f0ad45ae7fd6eea1dadd3f6508aaccc6b9c7020a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:10.776062Z","signature_b64":"OuLLJtK6l+eJQ263gahVVb7eswPYNoAhah1Df1hhwdvbhtbiwEJzAGlT5+8etSg4tApaKsUykEf0c0ONSUnOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71bc936c70c6d01824fe42c9f0ad45ae7fd6eea1dadd3f6508aaccc6b9c7020a","last_reissued_at":"2026-05-17T23:45:10.775235Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:10.775235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10264","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":"2026-05-17T23:45:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O3E8a/iaIErmCP/ZhHhL6zzacPP+FcPXJchjLHg70TZtcAEr2Iy9jFRnTm1muWSPnTqPwY9Ux7c3SQV6jt8EAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:37:33.377251Z"},"content_sha256":"5b37b52d5119e6894535fdcfac20f2f1b64571b92d79c7c0c63a6218fb17f411","schema_version":"1.0","event_id":"sha256:5b37b52d5119e6894535fdcfac20f2f1b64571b92d79c7c0c63a6218fb17f411"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OG6JG3DQY3IBQJH6ILE7BLKFVZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explicitizing an Implicit Bias of the Frequency Principle in Two-layer Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Tao Luo, Yaoyu Zhang, Zheng Ma, Zhi-Qin John Xu","submitted_at":"2019-05-24T14:45:37Z","abstract_excerpt":"It remains a puzzle that why deep neural networks (DNNs), with more parameters than samples, often generalize well. An attempt of understanding this puzzle is to discover implicit biases underlying the training process of DNNs, such as the Frequency Principle (F-Principle), i.e., DNNs often fit target functions from low to high frequencies. Inspired by the F-Principle, we propose an effective model of linear F-Principle (LFP) dynamics which accurately predicts the learning results of two-layer ReLU neural networks (NNs) of large widths. This LFP dynamics is rationalized by a linearized mean fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10264","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":""},"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":"2026-05-17T23:45:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wg4w+UncETL2u8Fm4ZmZMEWJAQpwaDLkMGLRbBKIwzfeRBfPzVkLkhPnLLL/9dAX/+4YBqXNwNSO78+Q5HjxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:37:33.377621Z"},"content_sha256":"436dbc0cb2f522455b7d4d2e7581dd685dffb9c75701f01bb17ba795c66722df","schema_version":"1.0","event_id":"sha256:436dbc0cb2f522455b7d4d2e7581dd685dffb9c75701f01bb17ba795c66722df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OG6JG3DQY3IBQJH6ILE7BLKFVZ/bundle.json","state_url":"https://pith.science/pith/OG6JG3DQY3IBQJH6ILE7BLKFVZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OG6JG3DQY3IBQJH6ILE7BLKFVZ/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":"2026-05-21T12:37:33Z","links":{"resolver":"https://pith.science/pith/OG6JG3DQY3IBQJH6ILE7BLKFVZ","bundle":"https://pith.science/pith/OG6JG3DQY3IBQJH6ILE7BLKFVZ/bundle.json","state":"https://pith.science/pith/OG6JG3DQY3IBQJH6ILE7BLKFVZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OG6JG3DQY3IBQJH6ILE7BLKFVZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OG6JG3DQY3IBQJH6ILE7BLKFVZ","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":"baf49aefcc091f059f505a9bd499d1c03fae7a9281b315b8dd6ca668a0b81781","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T14:45:37Z","title_canon_sha256":"6ce8403aac36f7a8603042068785f0deafd436bb133006338e2fb60a44203859"},"schema_version":"1.0","source":{"id":"1905.10264","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10264","created_at":"2026-05-17T23:45:10Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10264v1","created_at":"2026-05-17T23:45:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10264","created_at":"2026-05-17T23:45:10Z"},{"alias_kind":"pith_short_12","alias_value":"OG6JG3DQY3IB","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OG6JG3DQY3IBQJH6","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OG6JG3DQ","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:436dbc0cb2f522455b7d4d2e7581dd685dffb9c75701f01bb17ba795c66722df","target":"graph","created_at":"2026-05-17T23:45:10Z","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"},"paper":{"abstract_excerpt":"It remains a puzzle that why deep neural networks (DNNs), with more parameters than samples, often generalize well. An attempt of understanding this puzzle is to discover implicit biases underlying the training process of DNNs, such as the Frequency Principle (F-Principle), i.e., DNNs often fit target functions from low to high frequencies. Inspired by the F-Principle, we propose an effective model of linear F-Principle (LFP) dynamics which accurately predicts the learning results of two-layer ReLU neural networks (NNs) of large widths. This LFP dynamics is rationalized by a linearized mean fi","authors_text":"Tao Luo, Yaoyu Zhang, Zheng Ma, Zhi-Qin John Xu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T14:45:37Z","title":"Explicitizing an Implicit Bias of the Frequency Principle in Two-layer Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10264","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":"sha256:5b37b52d5119e6894535fdcfac20f2f1b64571b92d79c7c0c63a6218fb17f411","target":"record","created_at":"2026-05-17T23:45:10Z","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":"baf49aefcc091f059f505a9bd499d1c03fae7a9281b315b8dd6ca668a0b81781","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T14:45:37Z","title_canon_sha256":"6ce8403aac36f7a8603042068785f0deafd436bb133006338e2fb60a44203859"},"schema_version":"1.0","source":{"id":"1905.10264","kind":"arxiv","version":1}},"canonical_sha256":"71bc936c70c6d01824fe42c9f0ad45ae7fd6eea1dadd3f6508aaccc6b9c7020a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71bc936c70c6d01824fe42c9f0ad45ae7fd6eea1dadd3f6508aaccc6b9c7020a","first_computed_at":"2026-05-17T23:45:10.775235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:10.775235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OuLLJtK6l+eJQ263gahVVb7eswPYNoAhah1Df1hhwdvbhtbiwEJzAGlT5+8etSg4tApaKsUykEf0c0ONSUnOAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:10.776062Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10264","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b37b52d5119e6894535fdcfac20f2f1b64571b92d79c7c0c63a6218fb17f411","sha256:436dbc0cb2f522455b7d4d2e7581dd685dffb9c75701f01bb17ba795c66722df"],"state_sha256":"c6b01c1417e6f663417eea6e0a358e5907ae67f89142ea0dc70d393635aa6c04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AqkukLR+hUxY0SHdFQoSF67flRAX+OXRRjjKzHxPQvEfX7596kOXEG1Jq+wc5xBnhld3IbusMEhr0SOSESMmBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T12:37:33.379902Z","bundle_sha256":"d6f8b776bfd685292d8fb5255fa64ba3e9c75bab90330f436606b50f39302eab"}}