{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:G7HBSOYONVESGDHXTJ5S3VYCQ6","short_pith_number":"pith:G7HBSOYO","canonical_record":{"source":{"id":"2207.04631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-11T05:09:11Z","cross_cats_sorted":[],"title_canon_sha256":"cab171de44e9866fdcb982062fd2faba87d00a7e9d9bc8a694435e1c8764f19a","abstract_canon_sha256":"0e30de0927912e376d6d114d346557cd512bdb747459e38934a5cd732e1ce63d"},"schema_version":"1.0"},"canonical_sha256":"37ce193b0e6d49230cf79a7b2dd702878800d219b9ebbf879ae40368c98a6bc1","source":{"kind":"arxiv","id":"2207.04631","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04631","created_at":"2026-07-05T04:39:01Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04631v1","created_at":"2026-07-05T04:39:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04631","created_at":"2026-07-05T04:39:01Z"},{"alias_kind":"pith_short_12","alias_value":"G7HBSOYONVES","created_at":"2026-07-05T04:39:01Z"},{"alias_kind":"pith_short_16","alias_value":"G7HBSOYONVESGDHX","created_at":"2026-07-05T04:39:01Z"},{"alias_kind":"pith_short_8","alias_value":"G7HBSOYO","created_at":"2026-07-05T04:39:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:G7HBSOYONVESGDHXTJ5S3VYCQ6","target":"record","payload":{"canonical_record":{"source":{"id":"2207.04631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-11T05:09:11Z","cross_cats_sorted":[],"title_canon_sha256":"cab171de44e9866fdcb982062fd2faba87d00a7e9d9bc8a694435e1c8764f19a","abstract_canon_sha256":"0e30de0927912e376d6d114d346557cd512bdb747459e38934a5cd732e1ce63d"},"schema_version":"1.0"},"canonical_sha256":"37ce193b0e6d49230cf79a7b2dd702878800d219b9ebbf879ae40368c98a6bc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:01.395753Z","signature_b64":"dGi4hEY6aH9EeVXOn46fiUVoBYLttaDbGhh0BxWSF+PlhyGbaDnQO9jr+xE0BFK4X/pcZFj65Mc/KB8+OnrkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37ce193b0e6d49230cf79a7b2dd702878800d219b9ebbf879ae40368c98a6bc1","last_reissued_at":"2026-07-05T04:39:01.395305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:01.395305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.04631","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":"2026-07-05T04:39:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVHNbkLyDfdiFGqPZ+0lywBHDC+nCsPNVZIFSk4lBqtJpQTLEPnEk77+/Nu60IuMzXKTxr7FhksCRQ/JSykVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:47:16.507171Z"},"content_sha256":"c4c40346b1c80def15afe7e5dfd7f9d0687cf5de94fc84491a0989c959dbf4b1","schema_version":"1.0","event_id":"sha256:c4c40346b1c80def15afe7e5dfd7f9d0687cf5de94fc84491a0989c959dbf4b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:G7HBSOYONVESGDHXTJ5S3VYCQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Partial Resampling of Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir F. Atiya, Dina Elreedy, Firuz Kamalov","submitted_at":"2022-07-11T05:09:11Z","abstract_excerpt":"Imbalanced data is a frequently encountered problem in machine learning. Despite a vast amount of literature on sampling techniques for imbalanced data, there is a limited number of studies that address the issue of the optimal sampling ratio. In this paper, we attempt to fill the gap in the literature by conducting a large scale study of the effects of sampling ratio on classification accuracy. We consider 10 popular sampling methods and evaluate their performance over a range of ratios based on 20 datasets. The results of the numerical experiments suggest that the optimal sampling ratio is b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04631","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/2207.04631/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":"2026-07-05T04:39:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bSHocGwgDO4LGgf+p/x/pnHslMuDvodeb5lMnrFil/l8EyLeQcc4XUsLTPyH3JjehKqg1UOs37fd2ftEUz8iAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:47:16.507713Z"},"content_sha256":"442dafcbef250c239aa710564cb2ab166fe396f0153dc530b78a0bca5bd2ca79","schema_version":"1.0","event_id":"sha256:442dafcbef250c239aa710564cb2ab166fe396f0153dc530b78a0bca5bd2ca79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7HBSOYONVESGDHXTJ5S3VYCQ6/bundle.json","state_url":"https://pith.science/pith/G7HBSOYONVESGDHXTJ5S3VYCQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7HBSOYONVESGDHXTJ5S3VYCQ6/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":"2026-08-11T15:47:16Z","links":{"resolver":"https://pith.science/pith/G7HBSOYONVESGDHXTJ5S3VYCQ6","bundle":"https://pith.science/pith/G7HBSOYONVESGDHXTJ5S3VYCQ6/bundle.json","state":"https://pith.science/pith/G7HBSOYONVESGDHXTJ5S3VYCQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7HBSOYONVESGDHXTJ5S3VYCQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:G7HBSOYONVESGDHXTJ5S3VYCQ6","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":"0e30de0927912e376d6d114d346557cd512bdb747459e38934a5cd732e1ce63d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-11T05:09:11Z","title_canon_sha256":"cab171de44e9866fdcb982062fd2faba87d00a7e9d9bc8a694435e1c8764f19a"},"schema_version":"1.0","source":{"id":"2207.04631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04631","created_at":"2026-07-05T04:39:01Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04631v1","created_at":"2026-07-05T04:39:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04631","created_at":"2026-07-05T04:39:01Z"},{"alias_kind":"pith_short_12","alias_value":"G7HBSOYONVES","created_at":"2026-07-05T04:39:01Z"},{"alias_kind":"pith_short_16","alias_value":"G7HBSOYONVESGDHX","created_at":"2026-07-05T04:39:01Z"},{"alias_kind":"pith_short_8","alias_value":"G7HBSOYO","created_at":"2026-07-05T04:39:01Z"}],"graph_snapshots":[{"event_id":"sha256:442dafcbef250c239aa710564cb2ab166fe396f0153dc530b78a0bca5bd2ca79","target":"graph","created_at":"2026-07-05T04:39:01Z","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/2207.04631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imbalanced data is a frequently encountered problem in machine learning. Despite a vast amount of literature on sampling techniques for imbalanced data, there is a limited number of studies that address the issue of the optimal sampling ratio. In this paper, we attempt to fill the gap in the literature by conducting a large scale study of the effects of sampling ratio on classification accuracy. We consider 10 popular sampling methods and evaluate their performance over a range of ratios based on 20 datasets. The results of the numerical experiments suggest that the optimal sampling ratio is b","authors_text":"Amir F. Atiya, Dina Elreedy, Firuz Kamalov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-11T05:09:11Z","title":"Partial Resampling of Imbalanced Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04631","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:c4c40346b1c80def15afe7e5dfd7f9d0687cf5de94fc84491a0989c959dbf4b1","target":"record","created_at":"2026-07-05T04:39:01Z","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":"0e30de0927912e376d6d114d346557cd512bdb747459e38934a5cd732e1ce63d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-11T05:09:11Z","title_canon_sha256":"cab171de44e9866fdcb982062fd2faba87d00a7e9d9bc8a694435e1c8764f19a"},"schema_version":"1.0","source":{"id":"2207.04631","kind":"arxiv","version":1}},"canonical_sha256":"37ce193b0e6d49230cf79a7b2dd702878800d219b9ebbf879ae40368c98a6bc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37ce193b0e6d49230cf79a7b2dd702878800d219b9ebbf879ae40368c98a6bc1","first_computed_at":"2026-07-05T04:39:01.395305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:39:01.395305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dGi4hEY6aH9EeVXOn46fiUVoBYLttaDbGhh0BxWSF+PlhyGbaDnQO9jr+xE0BFK4X/pcZFj65Mc/KB8+OnrkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:39:01.395753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.04631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4c40346b1c80def15afe7e5dfd7f9d0687cf5de94fc84491a0989c959dbf4b1","sha256:442dafcbef250c239aa710564cb2ab166fe396f0153dc530b78a0bca5bd2ca79"],"state_sha256":"6ae9c2ff8311421113f3e22d8913b43ca5c700297741f794b95350b56985125d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yhLjhD+7YaNPBIbAkQmfPI+OLiOqtVSN8j+1J1NowTiZpN8GeCf4jGboXESbrnCvmwNGo13vhubCpKsjNjdWBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:47:16.514395Z","bundle_sha256":"3feef39d444e5a8a246b72111eba01ecfcb80f31721856fc728470a8442c97c0"}}