{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VR35ULVJSNLQF26EVPXJTHTF2H","short_pith_number":"pith:VR35ULVJ","canonical_record":{"source":{"id":"2405.09535","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2024-05-15T17:45:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1f9b1d94ed650f3f13138b993348a40a8a070786ef377ef10ff96be8e539827e","abstract_canon_sha256":"c68fd887f466291ec78564606970a95cfad12905f8aa4fa28bb19848bbb50c51"},"schema_version":"1.0"},"canonical_sha256":"ac77da2ea9935702ebc4abee999e65d1ef57433189d733a7d2c5cb79770517ee","source":{"kind":"arxiv","id":"2405.09535","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.09535","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.09535v2","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09535","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_12","alias_value":"VR35ULVJSNLQ","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_16","alias_value":"VR35ULVJSNLQF26E","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_8","alias_value":"VR35ULVJ","created_at":"2026-07-05T10:07:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VR35ULVJSNLQF26EVPXJTHTF2H","target":"record","payload":{"canonical_record":{"source":{"id":"2405.09535","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2024-05-15T17:45:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1f9b1d94ed650f3f13138b993348a40a8a070786ef377ef10ff96be8e539827e","abstract_canon_sha256":"c68fd887f466291ec78564606970a95cfad12905f8aa4fa28bb19848bbb50c51"},"schema_version":"1.0"},"canonical_sha256":"ac77da2ea9935702ebc4abee999e65d1ef57433189d733a7d2c5cb79770517ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:41.435083Z","signature_b64":"PNyCzfwKjX+L85L4yUKhE032dxFyfyQ21NRwhGY02KToiWaF2+FezYhTLPSIZPjCvqdUBAyujnyqFy3+yvmyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac77da2ea9935702ebc4abee999e65d1ef57433189d733a7d2c5cb79770517ee","last_reissued_at":"2026-07-05T10:07:41.434602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:41.434602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.09535","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:07:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vKduCSMX6vLOZgnwUa8M4fjuO+vgniwlZ7eyqmzS3FiMICqmksi5oinCiAPbwaJvYZcFNZpeHIdRJecPxOFCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:47:48.545407Z"},"content_sha256":"d5e1efea43363e2b128a4d652456f31e03166192de3fe767033cdb946be8b4b9","schema_version":"1.0","event_id":"sha256:d5e1efea43363e2b128a4d652456f31e03166192de3fe767033cdb946be8b4b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VR35ULVJSNLQF26EVPXJTHTF2H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Restoring balance: principled under/oversampling of data for optimal classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Emanuele Loffredo, Mauro Pastore, R\\'emi Monasson, Simona Cocco","submitted_at":"2024-05-15T17:45:34Z","abstract_excerpt":"Class imbalance in real-world data poses a common bottleneck for machine learning tasks, since achieving good generalization on under-represented examples is often challenging. Mitigation strategies, such as under or oversampling the data depending on their abundances, are routinely proposed and tested empirically, but how they should adapt to the data statistics remains poorly understood. In this work, we determine exact analytical expressions of the generalization curves in the high-dimensional regime for linear classifiers (Support Vector Machines). We also provide a sharp prediction of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09535","kind":"arxiv","version":2},"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/2405.09535/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":"2026-07-05T10:07:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T9jqKjmcuiMSGOgHcfs9ozzQmjrVxvvtf1e8rbN0Pad0DHVRd4DjLOsk7QysDeMHH8TZxg9ZUIqM0MGCvxpkDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:47:48.546957Z"},"content_sha256":"57e3442394eda842a4ee572920f043ec866677a4a34e1d161eaba2356f547868","schema_version":"1.0","event_id":"sha256:57e3442394eda842a4ee572920f043ec866677a4a34e1d161eaba2356f547868"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VR35ULVJSNLQF26EVPXJTHTF2H/bundle.json","state_url":"https://pith.science/pith/VR35ULVJSNLQF26EVPXJTHTF2H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VR35ULVJSNLQF26EVPXJTHTF2H/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":"2026-08-11T15:47:48Z","links":{"resolver":"https://pith.science/pith/VR35ULVJSNLQF26EVPXJTHTF2H","bundle":"https://pith.science/pith/VR35ULVJSNLQF26EVPXJTHTF2H/bundle.json","state":"https://pith.science/pith/VR35ULVJSNLQF26EVPXJTHTF2H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VR35ULVJSNLQF26EVPXJTHTF2H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VR35ULVJSNLQF26EVPXJTHTF2H","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":"c68fd887f466291ec78564606970a95cfad12905f8aa4fa28bb19848bbb50c51","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2024-05-15T17:45:34Z","title_canon_sha256":"1f9b1d94ed650f3f13138b993348a40a8a070786ef377ef10ff96be8e539827e"},"schema_version":"1.0","source":{"id":"2405.09535","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.09535","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.09535v2","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09535","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_12","alias_value":"VR35ULVJSNLQ","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_16","alias_value":"VR35ULVJSNLQF26E","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_8","alias_value":"VR35ULVJ","created_at":"2026-07-05T10:07:41Z"}],"graph_snapshots":[{"event_id":"sha256:57e3442394eda842a4ee572920f043ec866677a4a34e1d161eaba2356f547868","target":"graph","created_at":"2026-07-05T10:07:41Z","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/2405.09535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Class imbalance in real-world data poses a common bottleneck for machine learning tasks, since achieving good generalization on under-represented examples is often challenging. Mitigation strategies, such as under or oversampling the data depending on their abundances, are routinely proposed and tested empirically, but how they should adapt to the data statistics remains poorly understood. In this work, we determine exact analytical expressions of the generalization curves in the high-dimensional regime for linear classifiers (Support Vector Machines). We also provide a sharp prediction of the","authors_text":"Emanuele Loffredo, Mauro Pastore, R\\'emi Monasson, Simona Cocco","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2024-05-15T17:45:34Z","title":"Restoring balance: principled under/oversampling of data for optimal classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09535","kind":"arxiv","version":2},"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:d5e1efea43363e2b128a4d652456f31e03166192de3fe767033cdb946be8b4b9","target":"record","created_at":"2026-07-05T10:07:41Z","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":"c68fd887f466291ec78564606970a95cfad12905f8aa4fa28bb19848bbb50c51","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2024-05-15T17:45:34Z","title_canon_sha256":"1f9b1d94ed650f3f13138b993348a40a8a070786ef377ef10ff96be8e539827e"},"schema_version":"1.0","source":{"id":"2405.09535","kind":"arxiv","version":2}},"canonical_sha256":"ac77da2ea9935702ebc4abee999e65d1ef57433189d733a7d2c5cb79770517ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac77da2ea9935702ebc4abee999e65d1ef57433189d733a7d2c5cb79770517ee","first_computed_at":"2026-07-05T10:07:41.434602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:41.434602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PNyCzfwKjX+L85L4yUKhE032dxFyfyQ21NRwhGY02KToiWaF2+FezYhTLPSIZPjCvqdUBAyujnyqFy3+yvmyCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:41.435083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.09535","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5e1efea43363e2b128a4d652456f31e03166192de3fe767033cdb946be8b4b9","sha256:57e3442394eda842a4ee572920f043ec866677a4a34e1d161eaba2356f547868"],"state_sha256":"c1ab6329a97417f8d85ed4242887a42d7df6d581e99b057fdd9cf555c2d7bb49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tm5zthpB+Bh6hZY5LOg5SXp4Q7bwUGIMZD105est7QiWZy1DSYUzbSCUerb2FQOIQgy0OUISoPr1PRWU54/LAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:47:48.555304Z","bundle_sha256":"65c14118e37ef445e34206e968352d406e1cae9a498fcdc1d87fb0ce5cd8ad05"}}