{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3QCCLOPQ4TYR7QBSOB3U4K7J6X","short_pith_number":"pith:3QCCLOPQ","canonical_record":{"source":{"id":"2201.13383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-01-31T17:44:58Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"title_canon_sha256":"a386afe53e473c271d193ae6a03aeb3dd8b67e714b0acaa99ab058564363e703","abstract_canon_sha256":"46a59bd6c213cb6ede50575eb12a0af0f3344b1ad2c87f2cbdc20608285731ba"},"schema_version":"1.0"},"canonical_sha256":"dc0425b9f0e4f11fc03270774e2be9f5e0bcae603b47e2680a1929d1da48ea2c","source":{"kind":"arxiv","id":"2201.13383","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.13383","created_at":"2026-07-05T05:02:10Z"},{"alias_kind":"arxiv_version","alias_value":"2201.13383v1","created_at":"2026-07-05T05:02:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13383","created_at":"2026-07-05T05:02:10Z"},{"alias_kind":"pith_short_12","alias_value":"3QCCLOPQ4TYR","created_at":"2026-07-05T05:02:10Z"},{"alias_kind":"pith_short_16","alias_value":"3QCCLOPQ4TYR7QBS","created_at":"2026-07-05T05:02:10Z"},{"alias_kind":"pith_short_8","alias_value":"3QCCLOPQ","created_at":"2026-07-05T05:02:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3QCCLOPQ4TYR7QBSOB3U4K7J6X","target":"record","payload":{"canonical_record":{"source":{"id":"2201.13383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-01-31T17:44:58Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"title_canon_sha256":"a386afe53e473c271d193ae6a03aeb3dd8b67e714b0acaa99ab058564363e703","abstract_canon_sha256":"46a59bd6c213cb6ede50575eb12a0af0f3344b1ad2c87f2cbdc20608285731ba"},"schema_version":"1.0"},"canonical_sha256":"dc0425b9f0e4f11fc03270774e2be9f5e0bcae603b47e2680a1929d1da48ea2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:10.550522Z","signature_b64":"SextLOdMxSq8Rz9DxiqTiw5V6i2OQjWyO5lxB7lolquh9Za9fBTUFSB6OvnmL3QakB+Owdflq73GvkDclI8hAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc0425b9f0e4f11fc03270774e2be9f5e0bcae603b47e2680a1929d1da48ea2c","last_reissued_at":"2026-07-05T05:02:10.550131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:10.550131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.13383","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":"2026-07-05T05:02:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ZcjFnRurMJsN3FIN0hdo1QqL8i9qC+OpmIwc2bFjm03/OjEldwpps/4QWBYSTwgOuboXE6NZTHLd/sgfSIFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T08:33:36.804177Z"},"content_sha256":"8b13baf533903572162ffae48219329f8555dc54a3ff1e3947116be6da6bf35d","schema_version":"1.0","event_id":"sha256:8b13baf533903572162ffae48219329f8555dc54a3ff1e3947116be6da6bf35d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3QCCLOPQ4TYR7QBSOB3U4K7J6X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bruno Loureiro, C\\'edric Gerbelot, Florent Krzakala, Gabriele Sicuro, Maria Refinetti","submitted_at":"2022-01-31T17:44:58Z","abstract_excerpt":"From the sampling of data to the initialisation of parameters, randomness is ubiquitous in modern Machine Learning practice. Understanding the statistical fluctuations engendered by the different sources of randomness in prediction is therefore key to understanding robust generalisation. In this manuscript we develop a quantitative and rigorous theory for the study of fluctuations in an ensemble of generalised linear models trained on different, but correlated, features in high-dimensions. In particular, we provide a complete description of the asymptotic joint distribution of the empirical ri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13383","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/2201.13383/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":"2026-07-05T05:02:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MZ3hWLMpIWLZtyGUv4pPyTUZHc74s7Nv1A729lLIGInaZy0x3Tr0pHSQSpiipJOjBQGNlA/zkljv6vjYXodrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T08:33:36.804744Z"},"content_sha256":"ef80842173755016584de28e53c1780ae99d636eacfc4bc0a5b4cbef2d3c6b01","schema_version":"1.0","event_id":"sha256:ef80842173755016584de28e53c1780ae99d636eacfc4bc0a5b4cbef2d3c6b01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3QCCLOPQ4TYR7QBSOB3U4K7J6X/bundle.json","state_url":"https://pith.science/pith/3QCCLOPQ4TYR7QBSOB3U4K7J6X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3QCCLOPQ4TYR7QBSOB3U4K7J6X/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":"2026-07-28T08:33:36Z","links":{"resolver":"https://pith.science/pith/3QCCLOPQ4TYR7QBSOB3U4K7J6X","bundle":"https://pith.science/pith/3QCCLOPQ4TYR7QBSOB3U4K7J6X/bundle.json","state":"https://pith.science/pith/3QCCLOPQ4TYR7QBSOB3U4K7J6X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3QCCLOPQ4TYR7QBSOB3U4K7J6X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3QCCLOPQ4TYR7QBSOB3U4K7J6X","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":"46a59bd6c213cb6ede50575eb12a0af0f3344b1ad2c87f2cbdc20608285731ba","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-01-31T17:44:58Z","title_canon_sha256":"a386afe53e473c271d193ae6a03aeb3dd8b67e714b0acaa99ab058564363e703"},"schema_version":"1.0","source":{"id":"2201.13383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.13383","created_at":"2026-07-05T05:02:10Z"},{"alias_kind":"arxiv_version","alias_value":"2201.13383v1","created_at":"2026-07-05T05:02:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13383","created_at":"2026-07-05T05:02:10Z"},{"alias_kind":"pith_short_12","alias_value":"3QCCLOPQ4TYR","created_at":"2026-07-05T05:02:10Z"},{"alias_kind":"pith_short_16","alias_value":"3QCCLOPQ4TYR7QBS","created_at":"2026-07-05T05:02:10Z"},{"alias_kind":"pith_short_8","alias_value":"3QCCLOPQ","created_at":"2026-07-05T05:02:10Z"}],"graph_snapshots":[{"event_id":"sha256:ef80842173755016584de28e53c1780ae99d636eacfc4bc0a5b4cbef2d3c6b01","target":"graph","created_at":"2026-07-05T05:02:10Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.13383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"From the sampling of data to the initialisation of parameters, randomness is ubiquitous in modern Machine Learning practice. Understanding the statistical fluctuations engendered by the different sources of randomness in prediction is therefore key to understanding robust generalisation. In this manuscript we develop a quantitative and rigorous theory for the study of fluctuations in an ensemble of generalised linear models trained on different, but correlated, features in high-dimensions. In particular, we provide a complete description of the asymptotic joint distribution of the empirical ri","authors_text":"Bruno Loureiro, C\\'edric Gerbelot, Florent Krzakala, Gabriele Sicuro, Maria Refinetti","cross_cats":["cond-mat.dis-nn","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-01-31T17:44:58Z","title":"Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13383","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":"sha256:8b13baf533903572162ffae48219329f8555dc54a3ff1e3947116be6da6bf35d","target":"record","created_at":"2026-07-05T05:02:10Z","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":"46a59bd6c213cb6ede50575eb12a0af0f3344b1ad2c87f2cbdc20608285731ba","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-01-31T17:44:58Z","title_canon_sha256":"a386afe53e473c271d193ae6a03aeb3dd8b67e714b0acaa99ab058564363e703"},"schema_version":"1.0","source":{"id":"2201.13383","kind":"arxiv","version":1}},"canonical_sha256":"dc0425b9f0e4f11fc03270774e2be9f5e0bcae603b47e2680a1929d1da48ea2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc0425b9f0e4f11fc03270774e2be9f5e0bcae603b47e2680a1929d1da48ea2c","first_computed_at":"2026-07-05T05:02:10.550131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:10.550131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SextLOdMxSq8Rz9DxiqTiw5V6i2OQjWyO5lxB7lolquh9Za9fBTUFSB6OvnmL3QakB+Owdflq73GvkDclI8hAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:10.550522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.13383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b13baf533903572162ffae48219329f8555dc54a3ff1e3947116be6da6bf35d","sha256:ef80842173755016584de28e53c1780ae99d636eacfc4bc0a5b4cbef2d3c6b01"],"state_sha256":"e353a793f33fff313000105d2e1ad41c3e867ab58fa4c223900fd8b88cc9a01f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HTL1hRS9zootQNTXmsWjfzvg+fsyur5kDkks/c9vSFTTFluIMsCXN+YrdfDUa05NalG17rf0cbk/ziTqIHpnBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T08:33:36.809017Z","bundle_sha256":"889f026e7372b20e51fc49330ed952be95c652fe84782dc0e60ebadc9d069732"}}