{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AON5HGFA4B6NFQWXPV6AXLADBH","short_pith_number":"pith:AON5HGFA","canonical_record":{"source":{"id":"2505.11621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T18:37:51Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e741ee6f7f78dd3b3f47a2879a758e7510e41c2e3acbffe5d3b80eee99dee1ec","abstract_canon_sha256":"bcf503cd87df8b4ec04b23999cf86790acec7056c58ac17bb92d0ba6f19c9bc1"},"schema_version":"1.0"},"canonical_sha256":"039bd398a0e07cd2c2d77d7c0bac0309e45d5f2269ebc6e9c1271900e6111e85","source":{"kind":"arxiv","id":"2505.11621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11621","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11621v1","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11621","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"AON5HGFA4B6N","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"AON5HGFA4B6NFQWX","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"AON5HGFA","created_at":"2026-07-05T11:04:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AON5HGFA4B6NFQWXPV6AXLADBH","target":"record","payload":{"canonical_record":{"source":{"id":"2505.11621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T18:37:51Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e741ee6f7f78dd3b3f47a2879a758e7510e41c2e3acbffe5d3b80eee99dee1ec","abstract_canon_sha256":"bcf503cd87df8b4ec04b23999cf86790acec7056c58ac17bb92d0ba6f19c9bc1"},"schema_version":"1.0"},"canonical_sha256":"039bd398a0e07cd2c2d77d7c0bac0309e45d5f2269ebc6e9c1271900e6111e85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:24.487895Z","signature_b64":"KXIMuTcCCQt4fOZmLdFBC7W2gQaydaz+K166i0vdt+n/10gk+R28J/TaVoCgSZXgGJo8xpD/p9Gd1v81sLqjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"039bd398a0e07cd2c2d77d7c0bac0309e45d5f2269ebc6e9c1271900e6111e85","last_reissued_at":"2026-07-05T11:04:24.487351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:24.487351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.11621","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":"2026-07-05T11:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vVHN2pCdpGmuM56bEYUZUlI6CyHnuOzjSy4j++LABKnFmAi5ut0JOT3aDNmdMKbLAlRsEKEAy05CroXOhRVHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T04:57:40.290415Z"},"content_sha256":"566dd63a570e6f5d045c71b2b7c3ef77e4e84fd984066aecf7ee89f117caec4b","schema_version":"1.0","event_id":"sha256:566dd63a570e6f5d045c71b2b7c3ef77e4e84fd984066aecf7ee89f117caec4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AON5HGFA4B6NFQWXPV6AXLADBH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Classical View on Benign Overfitting: The Role of Sample Size","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junhyung Park, Patrick Bloebaum, Shiva Prasad Kasiviswanathan","submitted_at":"2025-05-16T18:37:51Z","abstract_excerpt":"Benign overfitting is a phenomenon in machine learning where a model perfectly fits (interpolates) the training data, including noisy examples, yet still generalizes well to unseen data. Understanding this phenomenon has attracted considerable attention in recent years. In this work, we introduce a conceptual shift, by focusing on almost benign overfitting, where models simultaneously achieve both arbitrarily small training and test errors. This behavior is characteristic of neural networks, which often achieve low (but non-zero) training error while still generalizing well. We hypothesize tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11621","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/2505.11621/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":"2026-07-05T11:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y8Q8Dvq5B64Y98lEo/VAEQHrhg8ErW13oK4Vhb9RDRpd1HSK66WmWOTSCdxE/xGBu7waVcpmhilt2Wdz/Ru/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T04:57:40.290994Z"},"content_sha256":"71a4e3b5de03d676f48e614ddeaad26b239f8f9b3da5722c2f48199369246722","schema_version":"1.0","event_id":"sha256:71a4e3b5de03d676f48e614ddeaad26b239f8f9b3da5722c2f48199369246722"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AON5HGFA4B6NFQWXPV6AXLADBH/bundle.json","state_url":"https://pith.science/pith/AON5HGFA4B6NFQWXPV6AXLADBH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AON5HGFA4B6NFQWXPV6AXLADBH/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":"2026-08-16T04:57:40Z","links":{"resolver":"https://pith.science/pith/AON5HGFA4B6NFQWXPV6AXLADBH","bundle":"https://pith.science/pith/AON5HGFA4B6NFQWXPV6AXLADBH/bundle.json","state":"https://pith.science/pith/AON5HGFA4B6NFQWXPV6AXLADBH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AON5HGFA4B6NFQWXPV6AXLADBH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AON5HGFA4B6NFQWXPV6AXLADBH","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":"bcf503cd87df8b4ec04b23999cf86790acec7056c58ac17bb92d0ba6f19c9bc1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T18:37:51Z","title_canon_sha256":"e741ee6f7f78dd3b3f47a2879a758e7510e41c2e3acbffe5d3b80eee99dee1ec"},"schema_version":"1.0","source":{"id":"2505.11621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11621","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11621v1","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11621","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"AON5HGFA4B6N","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"AON5HGFA4B6NFQWX","created_at":"2026-07-05T11:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"AON5HGFA","created_at":"2026-07-05T11:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:71a4e3b5de03d676f48e614ddeaad26b239f8f9b3da5722c2f48199369246722","target":"graph","created_at":"2026-07-05T11:04:24Z","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/2505.11621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benign overfitting is a phenomenon in machine learning where a model perfectly fits (interpolates) the training data, including noisy examples, yet still generalizes well to unseen data. Understanding this phenomenon has attracted considerable attention in recent years. In this work, we introduce a conceptual shift, by focusing on almost benign overfitting, where models simultaneously achieve both arbitrarily small training and test errors. This behavior is characteristic of neural networks, which often achieve low (but non-zero) training error while still generalizing well. We hypothesize tha","authors_text":"Junhyung Park, Patrick Bloebaum, Shiva Prasad Kasiviswanathan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T18:37:51Z","title":"A Classical View on Benign Overfitting: The Role of Sample Size"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11621","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":"sha256:566dd63a570e6f5d045c71b2b7c3ef77e4e84fd984066aecf7ee89f117caec4b","target":"record","created_at":"2026-07-05T11:04:24Z","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":"bcf503cd87df8b4ec04b23999cf86790acec7056c58ac17bb92d0ba6f19c9bc1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T18:37:51Z","title_canon_sha256":"e741ee6f7f78dd3b3f47a2879a758e7510e41c2e3acbffe5d3b80eee99dee1ec"},"schema_version":"1.0","source":{"id":"2505.11621","kind":"arxiv","version":1}},"canonical_sha256":"039bd398a0e07cd2c2d77d7c0bac0309e45d5f2269ebc6e9c1271900e6111e85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"039bd398a0e07cd2c2d77d7c0bac0309e45d5f2269ebc6e9c1271900e6111e85","first_computed_at":"2026-07-05T11:04:24.487351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:24.487351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KXIMuTcCCQt4fOZmLdFBC7W2gQaydaz+K166i0vdt+n/10gk+R28J/TaVoCgSZXgGJo8xpD/p9Gd1v81sLqjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:24.487895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:566dd63a570e6f5d045c71b2b7c3ef77e4e84fd984066aecf7ee89f117caec4b","sha256:71a4e3b5de03d676f48e614ddeaad26b239f8f9b3da5722c2f48199369246722"],"state_sha256":"b663c98ea526284eeeee02d0911f535f80f1b614683c7c4ec48eabf9b4a026ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w98QXC9OJ8FxVGw+7uDZ98kmXlGs0alEGggV4jN1PGybp6geWe5WxhQpFKVHzSr/cGb16vj7mIspMtFDfJcpAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T04:57:40.298495Z","bundle_sha256":"06d338ae6d6611f2c71d0896eb3b678f280e39cde90329e3d64fffb6a48bed66"}}