{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UWXXOCHWLYXLCDMXPYPVDEXX6D","short_pith_number":"pith:UWXXOCHW","canonical_record":{"source":{"id":"2502.11323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-02-17T00:21:33Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"de776060e7c1c0ccec37a17017c039a3f14338eb16d1023516ed8f74b5a01edc","abstract_canon_sha256":"26f9f41c00f8cfcb5f715e86ccf4a955322d5ddf260258028d0d530a4d4d720e"},"schema_version":"1.0"},"canonical_sha256":"a5af7708f65e2eb10d977e1f5192f7f0e84cd2da89a4493f65f276ad66e38466","source":{"kind":"arxiv","id":"2502.11323","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11323","created_at":"2026-07-05T10:15:06Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11323v1","created_at":"2026-07-05T10:15:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11323","created_at":"2026-07-05T10:15:06Z"},{"alias_kind":"pith_short_12","alias_value":"UWXXOCHWLYXL","created_at":"2026-07-05T10:15:06Z"},{"alias_kind":"pith_short_16","alias_value":"UWXXOCHWLYXLCDMX","created_at":"2026-07-05T10:15:06Z"},{"alias_kind":"pith_short_8","alias_value":"UWXXOCHW","created_at":"2026-07-05T10:15:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UWXXOCHWLYXLCDMXPYPVDEXX6D","target":"record","payload":{"canonical_record":{"source":{"id":"2502.11323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-02-17T00:21:33Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"de776060e7c1c0ccec37a17017c039a3f14338eb16d1023516ed8f74b5a01edc","abstract_canon_sha256":"26f9f41c00f8cfcb5f715e86ccf4a955322d5ddf260258028d0d530a4d4d720e"},"schema_version":"1.0"},"canonical_sha256":"a5af7708f65e2eb10d977e1f5192f7f0e84cd2da89a4493f65f276ad66e38466","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:06.733949Z","signature_b64":"nsfXNri/Prz1JO8DMKHPp/jZz687r7t92OigvCmwPtdmgu3v2Rsxn1bhyFlx9XZNEfMWqExsKLaWn58pMZ1wBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5af7708f65e2eb10d977e1f5192f7f0e84cd2da89a4493f65f276ad66e38466","last_reissued_at":"2026-07-05T10:15:06.733453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:06.733453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.11323","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":"2026-07-05T10:15:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6B6QMR5QodLMyHs1AB/iE2CxK3fsEWVGdR2CcxSPMpc1+yi2iMVGFwWVyy3Qoy+dxgpTaFfQhshqWDfAWr9pAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:19:22.518231Z"},"content_sha256":"4b2fb953baecc20c51beebce91e1315a5ee09a2ebaf9764edb4ba6f8bc36659b","schema_version":"1.0","event_id":"sha256:4b2fb953baecc20c51beebce91e1315a5ee09a2ebaf9764edb4ba6f8bc36659b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UWXXOCHWLYXLCDMXPYPVDEXX6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A statistical theory of overfitting for imbalanced classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jingyang Lyu, Kangjie Zhou, Yiqiao Zhong","submitted_at":"2025-02-17T00:21:33Z","abstract_excerpt":"Classification with imbalanced data is a common challenge in data analysis, where certain classes (minority classes) account for a small fraction of the training data compared with other classes (majority classes). Classical statistical theory based on large-sample asymptotics and finite-sample corrections is often ineffective for high-dimensional data, leaving many overfitting phenomena in empirical machine learning unexplained.\n  In this paper, we develop a statistical theory for high-dimensional imbalanced classification by investigating support vector machines and logistic regression. We f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11323","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/2502.11323/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":"2026-07-05T10:15:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ex5q8kux+eAD3c7ypdE5JNHxWWYc1HNxOQe1E0zjym6AVvX6PDnvICoPwJnESh+Mz5GbaX6wXEZoC/Ln1pVPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:19:22.519064Z"},"content_sha256":"2d4c6808900e905cd058fc8f6685b05884de770c352239d147cd93f8a8cd5c30","schema_version":"1.0","event_id":"sha256:2d4c6808900e905cd058fc8f6685b05884de770c352239d147cd93f8a8cd5c30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UWXXOCHWLYXLCDMXPYPVDEXX6D/bundle.json","state_url":"https://pith.science/pith/UWXXOCHWLYXLCDMXPYPVDEXX6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UWXXOCHWLYXLCDMXPYPVDEXX6D/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":"2026-08-22T03:19:22Z","links":{"resolver":"https://pith.science/pith/UWXXOCHWLYXLCDMXPYPVDEXX6D","bundle":"https://pith.science/pith/UWXXOCHWLYXLCDMXPYPVDEXX6D/bundle.json","state":"https://pith.science/pith/UWXXOCHWLYXLCDMXPYPVDEXX6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UWXXOCHWLYXLCDMXPYPVDEXX6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UWXXOCHWLYXLCDMXPYPVDEXX6D","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":"26f9f41c00f8cfcb5f715e86ccf4a955322d5ddf260258028d0d530a4d4d720e","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-02-17T00:21:33Z","title_canon_sha256":"de776060e7c1c0ccec37a17017c039a3f14338eb16d1023516ed8f74b5a01edc"},"schema_version":"1.0","source":{"id":"2502.11323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11323","created_at":"2026-07-05T10:15:06Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11323v1","created_at":"2026-07-05T10:15:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11323","created_at":"2026-07-05T10:15:06Z"},{"alias_kind":"pith_short_12","alias_value":"UWXXOCHWLYXL","created_at":"2026-07-05T10:15:06Z"},{"alias_kind":"pith_short_16","alias_value":"UWXXOCHWLYXLCDMX","created_at":"2026-07-05T10:15:06Z"},{"alias_kind":"pith_short_8","alias_value":"UWXXOCHW","created_at":"2026-07-05T10:15:06Z"}],"graph_snapshots":[{"event_id":"sha256:2d4c6808900e905cd058fc8f6685b05884de770c352239d147cd93f8a8cd5c30","target":"graph","created_at":"2026-07-05T10:15:06Z","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/2502.11323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classification with imbalanced data is a common challenge in data analysis, where certain classes (minority classes) account for a small fraction of the training data compared with other classes (majority classes). Classical statistical theory based on large-sample asymptotics and finite-sample corrections is often ineffective for high-dimensional data, leaving many overfitting phenomena in empirical machine learning unexplained.\n  In this paper, we develop a statistical theory for high-dimensional imbalanced classification by investigating support vector machines and logistic regression. We f","authors_text":"Jingyang Lyu, Kangjie Zhou, Yiqiao Zhong","cross_cats":["cs.LG","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-02-17T00:21:33Z","title":"A statistical theory of overfitting for imbalanced classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11323","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":"sha256:4b2fb953baecc20c51beebce91e1315a5ee09a2ebaf9764edb4ba6f8bc36659b","target":"record","created_at":"2026-07-05T10:15:06Z","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":"26f9f41c00f8cfcb5f715e86ccf4a955322d5ddf260258028d0d530a4d4d720e","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-02-17T00:21:33Z","title_canon_sha256":"de776060e7c1c0ccec37a17017c039a3f14338eb16d1023516ed8f74b5a01edc"},"schema_version":"1.0","source":{"id":"2502.11323","kind":"arxiv","version":1}},"canonical_sha256":"a5af7708f65e2eb10d977e1f5192f7f0e84cd2da89a4493f65f276ad66e38466","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5af7708f65e2eb10d977e1f5192f7f0e84cd2da89a4493f65f276ad66e38466","first_computed_at":"2026-07-05T10:15:06.733453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:06.733453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nsfXNri/Prz1JO8DMKHPp/jZz687r7t92OigvCmwPtdmgu3v2Rsxn1bhyFlx9XZNEfMWqExsKLaWn58pMZ1wBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:06.733949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b2fb953baecc20c51beebce91e1315a5ee09a2ebaf9764edb4ba6f8bc36659b","sha256:2d4c6808900e905cd058fc8f6685b05884de770c352239d147cd93f8a8cd5c30"],"state_sha256":"140e174ce85017105d7459ebaabcd4730677d66c070b9bb51ce062ee9098d8c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qBkg4+lH/0xyeh5hz0D4GtIXg2P5IYLEvsYvk3JyKAqnAzaUZL/SwQvizg1euGplbmRjSnXGADjD//hYzCE2DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T03:19:22.524287Z","bundle_sha256":"42a2034e9c7c663db6215694ff1b64a9913ca3a6a15b0615f72b3fd92d798b0d"}}