{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QBKKL7S2S2EFZ3VSP26TPP5MGC","short_pith_number":"pith:QBKKL7S2","canonical_record":{"source":{"id":"2011.03321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-11-04T21:04:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b3c511300e31e91599d4c72383f676ad85388cc4d8f83d1cf8b050c49406392c","abstract_canon_sha256":"b89c3c78f65d444f180707dda0a2ced40b2e57d24ed90e129fe988520c1a8928"},"schema_version":"1.0"},"canonical_sha256":"8054a5fe5a96885ceeb27ebd37bfac309b9f87b2a84555ddce3ab8512569cfff","source":{"kind":"arxiv","id":"2011.03321","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03321","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03321v1","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03321","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_12","alias_value":"QBKKL7S2S2EF","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_16","alias_value":"QBKKL7S2S2EFZ3VS","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_8","alias_value":"QBKKL7S2","created_at":"2026-07-05T01:49:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QBKKL7S2S2EFZ3VSP26TPP5MGC","target":"record","payload":{"canonical_record":{"source":{"id":"2011.03321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-11-04T21:04:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b3c511300e31e91599d4c72383f676ad85388cc4d8f83d1cf8b050c49406392c","abstract_canon_sha256":"b89c3c78f65d444f180707dda0a2ced40b2e57d24ed90e129fe988520c1a8928"},"schema_version":"1.0"},"canonical_sha256":"8054a5fe5a96885ceeb27ebd37bfac309b9f87b2a84555ddce3ab8512569cfff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:42.010042Z","signature_b64":"NQG5UWxFQACbYZkvKqMvTgv36XsYETa19pJYSU0R4abquMJQLsbUxtk5c3RAlhUi4NPfYv2ESoCtmSXEqSJZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8054a5fe5a96885ceeb27ebd37bfac309b9f87b2a84555ddce3ab8512569cfff","last_reissued_at":"2026-07-05T01:49:42.009577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:42.009577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.03321","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":"2026-07-05T01:49:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HJY4p79lWMYE4uJ9IIEHcq7ZC2vqpgGRf1Y+ZxmmHPsr/qptxD+fcwMqrbRzYtp+6gYfTTLnXBZCwGW3EbbvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:44:12.047441Z"},"content_sha256":"393cc33e4c7997c570a92bed80533ce975bd367db494c8482c3277f459ee7902","schema_version":"1.0","event_id":"sha256:393cc33e4c7997c570a92bed80533ce975bd367db494c8482c3277f459ee7902"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QBKKL7S2S2EFZ3VSP26TPP5MGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ben Adlam, Jeffrey Pennington","submitted_at":"2020-11-04T21:04:02Z","abstract_excerpt":"Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high variance of the predictive function. However, such a simple trade-off does not adequately describe deep learning models that simultaneously attain low bias and variance in the heavily overparameterized regime. A primary obstacle in explaining this behavior is that deep learning algorithms typically involve multiple sources of randomness whose individual contri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03321","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/2011.03321/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":"2026-07-05T01:49:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Fz6b/L0nRC4ylrSpuUOWpj/yDHd/akCNecmjsGr7dSGWCqHo0ta2i6vIwaWdcn6ThYejvLw/X7Qa5h8SxKKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:44:12.047934Z"},"content_sha256":"bf8a7f0228fd1a5bb983efcc317c6a548b38709a76e863bd12fde5bd548de9e1","schema_version":"1.0","event_id":"sha256:bf8a7f0228fd1a5bb983efcc317c6a548b38709a76e863bd12fde5bd548de9e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QBKKL7S2S2EFZ3VSP26TPP5MGC/bundle.json","state_url":"https://pith.science/pith/QBKKL7S2S2EFZ3VSP26TPP5MGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QBKKL7S2S2EFZ3VSP26TPP5MGC/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":"2026-08-07T15:44:12Z","links":{"resolver":"https://pith.science/pith/QBKKL7S2S2EFZ3VSP26TPP5MGC","bundle":"https://pith.science/pith/QBKKL7S2S2EFZ3VSP26TPP5MGC/bundle.json","state":"https://pith.science/pith/QBKKL7S2S2EFZ3VSP26TPP5MGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QBKKL7S2S2EFZ3VSP26TPP5MGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QBKKL7S2S2EFZ3VSP26TPP5MGC","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":"b89c3c78f65d444f180707dda0a2ced40b2e57d24ed90e129fe988520c1a8928","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-11-04T21:04:02Z","title_canon_sha256":"b3c511300e31e91599d4c72383f676ad85388cc4d8f83d1cf8b050c49406392c"},"schema_version":"1.0","source":{"id":"2011.03321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03321","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03321v1","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03321","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_12","alias_value":"QBKKL7S2S2EF","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_16","alias_value":"QBKKL7S2S2EFZ3VS","created_at":"2026-07-05T01:49:42Z"},{"alias_kind":"pith_short_8","alias_value":"QBKKL7S2","created_at":"2026-07-05T01:49:42Z"}],"graph_snapshots":[{"event_id":"sha256:bf8a7f0228fd1a5bb983efcc317c6a548b38709a76e863bd12fde5bd548de9e1","target":"graph","created_at":"2026-07-05T01:49:42Z","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/2011.03321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high variance of the predictive function. However, such a simple trade-off does not adequately describe deep learning models that simultaneously attain low bias and variance in the heavily overparameterized regime. A primary obstacle in explaining this behavior is that deep learning algorithms typically involve multiple sources of randomness whose individual contri","authors_text":"Ben Adlam, Jeffrey Pennington","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-11-04T21:04:02Z","title":"Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03321","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":"sha256:393cc33e4c7997c570a92bed80533ce975bd367db494c8482c3277f459ee7902","target":"record","created_at":"2026-07-05T01:49:42Z","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":"b89c3c78f65d444f180707dda0a2ced40b2e57d24ed90e129fe988520c1a8928","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-11-04T21:04:02Z","title_canon_sha256":"b3c511300e31e91599d4c72383f676ad85388cc4d8f83d1cf8b050c49406392c"},"schema_version":"1.0","source":{"id":"2011.03321","kind":"arxiv","version":1}},"canonical_sha256":"8054a5fe5a96885ceeb27ebd37bfac309b9f87b2a84555ddce3ab8512569cfff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8054a5fe5a96885ceeb27ebd37bfac309b9f87b2a84555ddce3ab8512569cfff","first_computed_at":"2026-07-05T01:49:42.009577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:42.009577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NQG5UWxFQACbYZkvKqMvTgv36XsYETa19pJYSU0R4abquMJQLsbUxtk5c3RAlhUi4NPfYv2ESoCtmSXEqSJZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:42.010042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.03321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:393cc33e4c7997c570a92bed80533ce975bd367db494c8482c3277f459ee7902","sha256:bf8a7f0228fd1a5bb983efcc317c6a548b38709a76e863bd12fde5bd548de9e1"],"state_sha256":"28b60ca243d723d390f33e15aabffcf5d2a16d2182c35ae15db44f44424e8bcb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eV4JiTHOm3zTAO4hmMwa6Nej4aMSUPCaSvaF/CVH8gtXRTVdOx0TvGidGqwX0qwng/3rOIPcNOunZE5cWphtCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:44:12.052251Z","bundle_sha256":"09b86c700916c1dd298409457e17a38c598705d064dfe59de52f2223fd85a866"}}