{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AVDJDLWRAYXZYGQKBOWUJHNUIO","short_pith_number":"pith:AVDJDLWR","canonical_record":{"source":{"id":"2106.03212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-06T19:08:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9928e2f85885be1cdb3c1951cdcee878bd485e9fa5eab304c855cc21fc495b22","abstract_canon_sha256":"5ddfd741c82ed22d4dc87ca02232816979d36d6a91bc60aea2cde33de9ff453e"},"schema_version":"1.0"},"canonical_sha256":"054691aed1062f9c1a0a0bad449db443b54abf52347d15d3295149ed4b38718f","source":{"kind":"arxiv","id":"2106.03212","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03212","created_at":"2026-07-05T02:46:47Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03212v1","created_at":"2026-07-05T02:46:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03212","created_at":"2026-07-05T02:46:47Z"},{"alias_kind":"pith_short_12","alias_value":"AVDJDLWRAYXZ","created_at":"2026-07-05T02:46:47Z"},{"alias_kind":"pith_short_16","alias_value":"AVDJDLWRAYXZYGQK","created_at":"2026-07-05T02:46:47Z"},{"alias_kind":"pith_short_8","alias_value":"AVDJDLWR","created_at":"2026-07-05T02:46:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AVDJDLWRAYXZYGQKBOWUJHNUIO","target":"record","payload":{"canonical_record":{"source":{"id":"2106.03212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-06T19:08:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9928e2f85885be1cdb3c1951cdcee878bd485e9fa5eab304c855cc21fc495b22","abstract_canon_sha256":"5ddfd741c82ed22d4dc87ca02232816979d36d6a91bc60aea2cde33de9ff453e"},"schema_version":"1.0"},"canonical_sha256":"054691aed1062f9c1a0a0bad449db443b54abf52347d15d3295149ed4b38718f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:47.403738Z","signature_b64":"g3UsJ/B4tdlofOk1Cdne2E4vFWvUcFSc+wX7Avhf7edFORt7VC4/NG+hievIiQr4NzP9aaIC9ecC4HoYKRpODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"054691aed1062f9c1a0a0bad449db443b54abf52347d15d3295149ed4b38718f","last_reissued_at":"2026-07-05T02:46:47.403219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:47.403219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.03212","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":"2026-07-05T02:46:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nQbUVoGVLmCBvtYhp49ekdKTHFQpT0ZFU9atujj7vtjWJugGtgeLb7aoc7ZXMDFhMRVPFECZ9pGmw8jhJ1wMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T18:11:44.500559Z"},"content_sha256":"c781b63161682c1d6f51a14baa2dbc5b2fb0b7b2227e468ebbc8a27a2511df6e","schema_version":"1.0","event_id":"sha256:c781b63161682c1d6f51a14baa2dbc5b2fb0b7b2227e468ebbc8a27a2511df6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AVDJDLWRAYXZYGQKBOWUJHNUIO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards an Understanding of Benign Overfitting in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arthur Gretton, Zhi-Hua Zhou, Zhu Li","submitted_at":"2021-06-06T19:08:53Z","abstract_excerpt":"Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss; yet surprisingly, they possess near-optimal prediction performance, contradicting classical learning theory. We examine how these benign overfitting phenomena occur in a two-layer neural network setting where sample covariates are corrupted with noise. We address the high dimensional regime, where the data dimension $d$ grows with the number $n$ of data points. Our analysis combines an upper bound on the bias with matching upper and lower bounds on the variance of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03212","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/2106.03212/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":"2026-07-05T02:46:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cerSCak12uJmgP+SS0rSPbit21n4Z7wmsqQCkQkzjTJv+zhUyc5EXs+qlP5qJxa6Qlh4yHTCCD9DPjqTX7aqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T18:11:44.501462Z"},"content_sha256":"5145ea45ea06d39e99d9a98ef2ff677592cd01ade72aeedc24b5c440629f9759","schema_version":"1.0","event_id":"sha256:5145ea45ea06d39e99d9a98ef2ff677592cd01ade72aeedc24b5c440629f9759"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AVDJDLWRAYXZYGQKBOWUJHNUIO/bundle.json","state_url":"https://pith.science/pith/AVDJDLWRAYXZYGQKBOWUJHNUIO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AVDJDLWRAYXZYGQKBOWUJHNUIO/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":"2026-08-16T18:11:44Z","links":{"resolver":"https://pith.science/pith/AVDJDLWRAYXZYGQKBOWUJHNUIO","bundle":"https://pith.science/pith/AVDJDLWRAYXZYGQKBOWUJHNUIO/bundle.json","state":"https://pith.science/pith/AVDJDLWRAYXZYGQKBOWUJHNUIO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AVDJDLWRAYXZYGQKBOWUJHNUIO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AVDJDLWRAYXZYGQKBOWUJHNUIO","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":"5ddfd741c82ed22d4dc87ca02232816979d36d6a91bc60aea2cde33de9ff453e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-06T19:08:53Z","title_canon_sha256":"9928e2f85885be1cdb3c1951cdcee878bd485e9fa5eab304c855cc21fc495b22"},"schema_version":"1.0","source":{"id":"2106.03212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03212","created_at":"2026-07-05T02:46:47Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03212v1","created_at":"2026-07-05T02:46:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03212","created_at":"2026-07-05T02:46:47Z"},{"alias_kind":"pith_short_12","alias_value":"AVDJDLWRAYXZ","created_at":"2026-07-05T02:46:47Z"},{"alias_kind":"pith_short_16","alias_value":"AVDJDLWRAYXZYGQK","created_at":"2026-07-05T02:46:47Z"},{"alias_kind":"pith_short_8","alias_value":"AVDJDLWR","created_at":"2026-07-05T02:46:47Z"}],"graph_snapshots":[{"event_id":"sha256:5145ea45ea06d39e99d9a98ef2ff677592cd01ade72aeedc24b5c440629f9759","target":"graph","created_at":"2026-07-05T02:46:47Z","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/2106.03212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss; yet surprisingly, they possess near-optimal prediction performance, contradicting classical learning theory. We examine how these benign overfitting phenomena occur in a two-layer neural network setting where sample covariates are corrupted with noise. We address the high dimensional regime, where the data dimension $d$ grows with the number $n$ of data points. Our analysis combines an upper bound on the bias with matching upper and lower bounds on the variance of the","authors_text":"Arthur Gretton, Zhi-Hua Zhou, Zhu Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-06T19:08:53Z","title":"Towards an Understanding of Benign Overfitting in Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03212","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:c781b63161682c1d6f51a14baa2dbc5b2fb0b7b2227e468ebbc8a27a2511df6e","target":"record","created_at":"2026-07-05T02:46:47Z","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":"5ddfd741c82ed22d4dc87ca02232816979d36d6a91bc60aea2cde33de9ff453e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-06T19:08:53Z","title_canon_sha256":"9928e2f85885be1cdb3c1951cdcee878bd485e9fa5eab304c855cc21fc495b22"},"schema_version":"1.0","source":{"id":"2106.03212","kind":"arxiv","version":1}},"canonical_sha256":"054691aed1062f9c1a0a0bad449db443b54abf52347d15d3295149ed4b38718f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"054691aed1062f9c1a0a0bad449db443b54abf52347d15d3295149ed4b38718f","first_computed_at":"2026-07-05T02:46:47.403219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:47.403219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g3UsJ/B4tdlofOk1Cdne2E4vFWvUcFSc+wX7Avhf7edFORt7VC4/NG+hievIiQr4NzP9aaIC9ecC4HoYKRpODw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:47.403738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.03212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c781b63161682c1d6f51a14baa2dbc5b2fb0b7b2227e468ebbc8a27a2511df6e","sha256:5145ea45ea06d39e99d9a98ef2ff677592cd01ade72aeedc24b5c440629f9759"],"state_sha256":"cd268f4e542edb43a7bbec4eecde92c7a98b1f7ea6c99a94ca9b83ebc34d9852"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vMoXQ7OebwPMjx9rHthZHqDmI/6o8Ii0YXeUtLH0zfhCAMEfrN+mcHUWHBC0COPvToJGTvaATOMyK3bkwRJVAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T18:11:44.508707Z","bundle_sha256":"a4b82affb15b41f6e5cf201c34c661231af371980789c15e593ca918df8f7599"}}