{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QFL5WGKFZ6IETJCPQVTH6BCKS5","short_pith_number":"pith:QFL5WGKF","canonical_record":{"source":{"id":"2305.15141","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T13:36:06Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"0c25dbe71a5f9b66cb2481089b011c5c3900b0fe901c01b6fbde0341714a8dc5","abstract_canon_sha256":"19cf863ed3cce17faaf67730fe7ac552a9c25aede4d5673da53fe49d2dc4aa98"},"schema_version":"1.0"},"canonical_sha256":"8157db1945cf9049a44f85667f044a974df7ceda9b7f15668ec62ecb961a01c3","source":{"kind":"arxiv","id":"2305.15141","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15141","created_at":"2026-07-05T07:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15141v3","created_at":"2026-07-05T07:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15141","created_at":"2026-07-05T07:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"QFL5WGKFZ6IE","created_at":"2026-07-05T07:59:02Z"},{"alias_kind":"pith_short_16","alias_value":"QFL5WGKFZ6IETJCP","created_at":"2026-07-05T07:59:02Z"},{"alias_kind":"pith_short_8","alias_value":"QFL5WGKF","created_at":"2026-07-05T07:59:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QFL5WGKFZ6IETJCPQVTH6BCKS5","target":"record","payload":{"canonical_record":{"source":{"id":"2305.15141","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T13:36:06Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"0c25dbe71a5f9b66cb2481089b011c5c3900b0fe901c01b6fbde0341714a8dc5","abstract_canon_sha256":"19cf863ed3cce17faaf67730fe7ac552a9c25aede4d5673da53fe49d2dc4aa98"},"schema_version":"1.0"},"canonical_sha256":"8157db1945cf9049a44f85667f044a974df7ceda9b7f15668ec62ecb961a01c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:02.522805Z","signature_b64":"lp3WvE066SObQCxQSl0e/mAfuxGkkGVV833gz+wqRu2UqefVNqTUm8lcD7awGqFO1dV8EMM0V7f7kI9CR/TFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8157db1945cf9049a44f85667f044a974df7ceda9b7f15668ec62ecb961a01c3","last_reissued_at":"2026-07-05T07:59:02.522349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:02.522349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.15141","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":"2026-07-05T07:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wtzMPx2DsdB7wsKxtFlAts9Zsf7bPoDR66J6qMsLWP26vQOz5NnyE1CPDLYtX9soaYW1Gq8mFdQd6RmXABIrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:25:02.831937Z"},"content_sha256":"870439f83023ec0ddaed7d3bca10889a0aa6f5d20872b5c3c6708816e2374217","schema_version":"1.0","event_id":"sha256:870439f83023ec0ddaed7d3bca10889a0aa6f5d20872b5c3c6708816e2374217"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QFL5WGKFZ6IETJCPQVTH6BCKS5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Tempered to Benign Overfitting in ReLU Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gilad Yehudai, Guy Kornowski, Ohad Shamir","submitted_at":"2023-05-24T13:36:06Z","abstract_excerpt":"Overparameterized neural networks (NNs) are observed to generalize well even when trained to perfectly fit noisy data. This phenomenon motivated a large body of work on \"benign overfitting\", where interpolating predictors achieve near-optimal performance. Recently, it was conjectured and empirically observed that the behavior of NNs is often better described as \"tempered overfitting\", where the performance is non-optimal yet also non-trivial, and degrades as a function of the noise level. However, a theoretical justification of this claim for non-linear NNs has been lacking so far. In this wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15141","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/2305.15141/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":"2026-07-05T07:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4wbf0Nu41/181IA85av5eGtbQwvbxrcNCpYJjDhJpzuGOGZGzICqsrfOkBuLVM3c6Xw2wB8U2EjDvyYuybhrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:25:02.832450Z"},"content_sha256":"cb4224d581d0119313dbdca0ea3922f31ac1c73bdc35bb9cd0eaaf1fac0ec9d9","schema_version":"1.0","event_id":"sha256:cb4224d581d0119313dbdca0ea3922f31ac1c73bdc35bb9cd0eaaf1fac0ec9d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QFL5WGKFZ6IETJCPQVTH6BCKS5/bundle.json","state_url":"https://pith.science/pith/QFL5WGKFZ6IETJCPQVTH6BCKS5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QFL5WGKFZ6IETJCPQVTH6BCKS5/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":"2026-08-05T13:25:02Z","links":{"resolver":"https://pith.science/pith/QFL5WGKFZ6IETJCPQVTH6BCKS5","bundle":"https://pith.science/pith/QFL5WGKFZ6IETJCPQVTH6BCKS5/bundle.json","state":"https://pith.science/pith/QFL5WGKFZ6IETJCPQVTH6BCKS5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QFL5WGKFZ6IETJCPQVTH6BCKS5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QFL5WGKFZ6IETJCPQVTH6BCKS5","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":"19cf863ed3cce17faaf67730fe7ac552a9c25aede4d5673da53fe49d2dc4aa98","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T13:36:06Z","title_canon_sha256":"0c25dbe71a5f9b66cb2481089b011c5c3900b0fe901c01b6fbde0341714a8dc5"},"schema_version":"1.0","source":{"id":"2305.15141","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15141","created_at":"2026-07-05T07:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15141v3","created_at":"2026-07-05T07:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15141","created_at":"2026-07-05T07:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"QFL5WGKFZ6IE","created_at":"2026-07-05T07:59:02Z"},{"alias_kind":"pith_short_16","alias_value":"QFL5WGKFZ6IETJCP","created_at":"2026-07-05T07:59:02Z"},{"alias_kind":"pith_short_8","alias_value":"QFL5WGKF","created_at":"2026-07-05T07:59:02Z"}],"graph_snapshots":[{"event_id":"sha256:cb4224d581d0119313dbdca0ea3922f31ac1c73bdc35bb9cd0eaaf1fac0ec9d9","target":"graph","created_at":"2026-07-05T07:59:02Z","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/2305.15141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Overparameterized neural networks (NNs) are observed to generalize well even when trained to perfectly fit noisy data. This phenomenon motivated a large body of work on \"benign overfitting\", where interpolating predictors achieve near-optimal performance. Recently, it was conjectured and empirically observed that the behavior of NNs is often better described as \"tempered overfitting\", where the performance is non-optimal yet also non-trivial, and degrades as a function of the noise level. However, a theoretical justification of this claim for non-linear NNs has been lacking so far. In this wor","authors_text":"Gilad Yehudai, Guy Kornowski, Ohad Shamir","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T13:36:06Z","title":"From Tempered to Benign Overfitting in ReLU Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15141","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":"sha256:870439f83023ec0ddaed7d3bca10889a0aa6f5d20872b5c3c6708816e2374217","target":"record","created_at":"2026-07-05T07:59:02Z","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":"19cf863ed3cce17faaf67730fe7ac552a9c25aede4d5673da53fe49d2dc4aa98","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T13:36:06Z","title_canon_sha256":"0c25dbe71a5f9b66cb2481089b011c5c3900b0fe901c01b6fbde0341714a8dc5"},"schema_version":"1.0","source":{"id":"2305.15141","kind":"arxiv","version":3}},"canonical_sha256":"8157db1945cf9049a44f85667f044a974df7ceda9b7f15668ec62ecb961a01c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8157db1945cf9049a44f85667f044a974df7ceda9b7f15668ec62ecb961a01c3","first_computed_at":"2026-07-05T07:59:02.522349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:02.522349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lp3WvE066SObQCxQSl0e/mAfuxGkkGVV833gz+wqRu2UqefVNqTUm8lcD7awGqFO1dV8EMM0V7f7kI9CR/TFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:02.522805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15141","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:870439f83023ec0ddaed7d3bca10889a0aa6f5d20872b5c3c6708816e2374217","sha256:cb4224d581d0119313dbdca0ea3922f31ac1c73bdc35bb9cd0eaaf1fac0ec9d9"],"state_sha256":"82dd2dd272facb12ee8b93a09d2e1cb7d0abb66478ef46bc677371439b08a0d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qAIuHcX5JrlWx5GfZj+NXgmmLv8bPV7Kan6q1Yfrb3kvXpfU4LIM/dUR4CxP1u5M/wlJLl0MO9NykjFu2vPuDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:25:02.843267Z","bundle_sha256":"87c315f9fec433a5749bddb784e1b9d37d2e7efa16ca30c8a946714b39fa4153"}}