{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AET2TPVQEFQ5DT5OM6BLW777K7","short_pith_number":"pith:AET2TPVQ","canonical_record":{"source":{"id":"2111.14120","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-28T11:48:26Z","cross_cats_sorted":[],"title_canon_sha256":"fdf05d128b95279046c82a27abfab1e97446c0ab0e860baa63411180e38093c6","abstract_canon_sha256":"b6bda6146adb6c0f20311de18efddacbd12fcb7c6d26e0f235d51081f8c75121"},"schema_version":"1.0"},"canonical_sha256":"0127a9beb02161d1cfae6782bb7fff57c0ce9fa236e7ad53acdb61700dcdcc57","source":{"kind":"arxiv","id":"2111.14120","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.14120","created_at":"2026-07-05T03:35:39Z"},{"alias_kind":"arxiv_version","alias_value":"2111.14120v1","created_at":"2026-07-05T03:35:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14120","created_at":"2026-07-05T03:35:39Z"},{"alias_kind":"pith_short_12","alias_value":"AET2TPVQEFQ5","created_at":"2026-07-05T03:35:39Z"},{"alias_kind":"pith_short_16","alias_value":"AET2TPVQEFQ5DT5O","created_at":"2026-07-05T03:35:39Z"},{"alias_kind":"pith_short_8","alias_value":"AET2TPVQ","created_at":"2026-07-05T03:35:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AET2TPVQEFQ5DT5OM6BLW777K7","target":"record","payload":{"canonical_record":{"source":{"id":"2111.14120","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-28T11:48:26Z","cross_cats_sorted":[],"title_canon_sha256":"fdf05d128b95279046c82a27abfab1e97446c0ab0e860baa63411180e38093c6","abstract_canon_sha256":"b6bda6146adb6c0f20311de18efddacbd12fcb7c6d26e0f235d51081f8c75121"},"schema_version":"1.0"},"canonical_sha256":"0127a9beb02161d1cfae6782bb7fff57c0ce9fa236e7ad53acdb61700dcdcc57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:39.410906Z","signature_b64":"l+h6LRBqY9+hNS89egkJoHrQDRWM/ehLyfUt6KBtLipF7Qa5kcblTJ26pLTbVEE2+10ey2Lrb3DZTlh1l7m2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0127a9beb02161d1cfae6782bb7fff57c0ce9fa236e7ad53acdb61700dcdcc57","last_reissued_at":"2026-07-05T03:35:39.410482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:39.410482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.14120","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":"2026-07-05T03:35:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZL7oRciVE+RAxAfF09oLjycIFLdzfPhFZ9tGl/5CA6XqbHKX047j+cRtxVy3HMTsOZoZLKIqt+bp7YFjR43rDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T04:24:30.080123Z"},"content_sha256":"84d3071cc6b7b315fc9ff57b7562eaabd047f8c8fd09c3ed06b6d7d7ab8de4f8","schema_version":"1.0","event_id":"sha256:84d3071cc6b7b315fc9ff57b7562eaabd047f8c8fd09c3ed06b6d7d7ab8de4f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AET2TPVQEFQ5DT5OM6BLW777K7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imbalanced data preprocessing techniques utilizing local data characteristics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Micha{\\l} Koziarski","submitted_at":"2021-11-28T11:48:26Z","abstract_excerpt":"Data imbalance, that is the disproportion between the number of training observations coming from different classes, remains one of the most significant challenges affecting contemporary machine learning. The negative impact of data imbalance on traditional classification algorithms can be reduced by the data preprocessing techniques, methods that manipulate the training data to artificially reduce the degree of imbalance. However, the existing data preprocessing techniques, in particular SMOTE and its derivatives, which constitute the most prevalent paradigm of imbalanced data preprocessing, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14120","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/2111.14120/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":"2026-07-05T03:35:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BBqeYmD+4vtSHTokGG60aAUAbqIsaddjlcUmOXLQEZymPmdFvx3okVA2dye0nR1zG3kz+3USkX+vPD0CpoFUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T04:24:30.080481Z"},"content_sha256":"9010c9297f84293327f26c5fca898a3e41a5a4976c33a49321dec579fe639920","schema_version":"1.0","event_id":"sha256:9010c9297f84293327f26c5fca898a3e41a5a4976c33a49321dec579fe639920"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AET2TPVQEFQ5DT5OM6BLW777K7/bundle.json","state_url":"https://pith.science/pith/AET2TPVQEFQ5DT5OM6BLW777K7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AET2TPVQEFQ5DT5OM6BLW777K7/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":"2026-08-24T04:24:30Z","links":{"resolver":"https://pith.science/pith/AET2TPVQEFQ5DT5OM6BLW777K7","bundle":"https://pith.science/pith/AET2TPVQEFQ5DT5OM6BLW777K7/bundle.json","state":"https://pith.science/pith/AET2TPVQEFQ5DT5OM6BLW777K7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AET2TPVQEFQ5DT5OM6BLW777K7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AET2TPVQEFQ5DT5OM6BLW777K7","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":"b6bda6146adb6c0f20311de18efddacbd12fcb7c6d26e0f235d51081f8c75121","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-28T11:48:26Z","title_canon_sha256":"fdf05d128b95279046c82a27abfab1e97446c0ab0e860baa63411180e38093c6"},"schema_version":"1.0","source":{"id":"2111.14120","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.14120","created_at":"2026-07-05T03:35:39Z"},{"alias_kind":"arxiv_version","alias_value":"2111.14120v1","created_at":"2026-07-05T03:35:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14120","created_at":"2026-07-05T03:35:39Z"},{"alias_kind":"pith_short_12","alias_value":"AET2TPVQEFQ5","created_at":"2026-07-05T03:35:39Z"},{"alias_kind":"pith_short_16","alias_value":"AET2TPVQEFQ5DT5O","created_at":"2026-07-05T03:35:39Z"},{"alias_kind":"pith_short_8","alias_value":"AET2TPVQ","created_at":"2026-07-05T03:35:39Z"}],"graph_snapshots":[{"event_id":"sha256:9010c9297f84293327f26c5fca898a3e41a5a4976c33a49321dec579fe639920","target":"graph","created_at":"2026-07-05T03:35:39Z","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/2111.14120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data imbalance, that is the disproportion between the number of training observations coming from different classes, remains one of the most significant challenges affecting contemporary machine learning. The negative impact of data imbalance on traditional classification algorithms can be reduced by the data preprocessing techniques, methods that manipulate the training data to artificially reduce the degree of imbalance. However, the existing data preprocessing techniques, in particular SMOTE and its derivatives, which constitute the most prevalent paradigm of imbalanced data preprocessing, ","authors_text":"Micha{\\l} Koziarski","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-28T11:48:26Z","title":"Imbalanced data preprocessing techniques utilizing local data characteristics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14120","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":"sha256:84d3071cc6b7b315fc9ff57b7562eaabd047f8c8fd09c3ed06b6d7d7ab8de4f8","target":"record","created_at":"2026-07-05T03:35:39Z","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":"b6bda6146adb6c0f20311de18efddacbd12fcb7c6d26e0f235d51081f8c75121","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-28T11:48:26Z","title_canon_sha256":"fdf05d128b95279046c82a27abfab1e97446c0ab0e860baa63411180e38093c6"},"schema_version":"1.0","source":{"id":"2111.14120","kind":"arxiv","version":1}},"canonical_sha256":"0127a9beb02161d1cfae6782bb7fff57c0ce9fa236e7ad53acdb61700dcdcc57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0127a9beb02161d1cfae6782bb7fff57c0ce9fa236e7ad53acdb61700dcdcc57","first_computed_at":"2026-07-05T03:35:39.410482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:35:39.410482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l+h6LRBqY9+hNS89egkJoHrQDRWM/ehLyfUt6KBtLipF7Qa5kcblTJ26pLTbVEE2+10ey2Lrb3DZTlh1l7m2CA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:35:39.410906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.14120","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84d3071cc6b7b315fc9ff57b7562eaabd047f8c8fd09c3ed06b6d7d7ab8de4f8","sha256:9010c9297f84293327f26c5fca898a3e41a5a4976c33a49321dec579fe639920"],"state_sha256":"5ecae0cc7e87b61fc1682aec3e7a31484912b987e029839d7b741f3f8e97cc8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPtmvasRMnUrU60iocqRmEVM35hC/m62KwD68+p0oSCUmUqKe4SOetWMtf8DaYZiUh9JiJFhpzXno7wO17UyDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T04:24:30.083905Z","bundle_sha256":"642c47d7916143f94a91dbef6699c52ac885757e88866faa5cf8b414f39e1560"}}