{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2JACWPGFRVP3SIUD2SFEUVXHMW","short_pith_number":"pith:2JACWPGF","canonical_record":{"source":{"id":"2201.08528","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-21T03:37:39Z","cross_cats_sorted":[],"title_canon_sha256":"83cc93a9452e7ccb0993d3a09b73df8f0eb8bad81d7743c398bde8ab01d4c6fb","abstract_canon_sha256":"832722a85491a1ec7f0aaf22e95dd038dd909d5d8059b16e3a7e4b7cb908d21e"},"schema_version":"1.0"},"canonical_sha256":"d2402b3cc58d5fb92283d48a4a56e765960cbddd2a164844341b2fcacaf93a2b","source":{"kind":"arxiv","id":"2201.08528","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.08528","created_at":"2026-07-05T04:22:19Z"},{"alias_kind":"arxiv_version","alias_value":"2201.08528v3","created_at":"2026-07-05T04:22:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08528","created_at":"2026-07-05T04:22:19Z"},{"alias_kind":"pith_short_12","alias_value":"2JACWPGFRVP3","created_at":"2026-07-05T04:22:19Z"},{"alias_kind":"pith_short_16","alias_value":"2JACWPGFRVP3SIUD","created_at":"2026-07-05T04:22:19Z"},{"alias_kind":"pith_short_8","alias_value":"2JACWPGF","created_at":"2026-07-05T04:22:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2JACWPGFRVP3SIUD2SFEUVXHMW","target":"record","payload":{"canonical_record":{"source":{"id":"2201.08528","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-21T03:37:39Z","cross_cats_sorted":[],"title_canon_sha256":"83cc93a9452e7ccb0993d3a09b73df8f0eb8bad81d7743c398bde8ab01d4c6fb","abstract_canon_sha256":"832722a85491a1ec7f0aaf22e95dd038dd909d5d8059b16e3a7e4b7cb908d21e"},"schema_version":"1.0"},"canonical_sha256":"d2402b3cc58d5fb92283d48a4a56e765960cbddd2a164844341b2fcacaf93a2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:19.242620Z","signature_b64":"H3kRRj26mjH/B5IOFAjIb1A1qKY440u4P5YT70fYCvtouQ8JvEsPNUug+bC5yDKJkt/EZp9PX1T7nDvsWx8MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2402b3cc58d5fb92283d48a4a56e765960cbddd2a164844341b2fcacaf93a2b","last_reissued_at":"2026-07-05T04:22:19.242071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:19.242071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.08528","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:22:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4j+8ZBAyFJ/i+y18I11t4/E3Gtre5o9tqCIE5fa/ggHeNT7fbWKZ3kNKYbwbOM0QiTuKL9R0JSszGNB5oHP7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:22:55.293828Z"},"content_sha256":"72e3661daddab1b1e15b7f8051a2d8b309c2f2c86bfe9fe90244a911860bd5bf","schema_version":"1.0","event_id":"sha256:72e3661daddab1b1e15b7f8051a2d8b309c2f2c86bfe9fe90244a911860bd5bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2JACWPGFRVP3SIUD2SFEUVXHMW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"To SMOTE, or not to SMOTE?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hadar Averbuch-Elor, Yotam Elor","submitted_at":"2022-01-21T03:37:39Z","abstract_excerpt":"Balancing the data before training a classifier is a popular technique to address the challenges of imbalanced binary classification in tabular data. Balancing is commonly achieved by duplication of minority samples or by generation of synthetic minority samples. While it is well known that balancing affects each classifier differently, most prior empirical studies did not include strong state-of-the-art (SOTA) classifiers as baselines. In this work, we are interested in understanding whether balancing is beneficial, particularly in the context of SOTA classifiers. Thus, we conduct extensive e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08528","kind":"arxiv","version":3},"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/2201.08528/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":"2026-07-05T04:22:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJUrAi4XooYTvkEU2fXtsjVtbirHLDZeXQp7oZuXGaCrA09qywYoN1jZdM6j5iC9aAIOaJiGVsMozE3xxLw2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:22:55.294319Z"},"content_sha256":"08cc82383fa9fffeead3c3ee403a24b3559f7aaa00b70e80b157f6edc47bc8f5","schema_version":"1.0","event_id":"sha256:08cc82383fa9fffeead3c3ee403a24b3559f7aaa00b70e80b157f6edc47bc8f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/bundle.json","state_url":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/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":"2026-08-07T09:22:55Z","links":{"resolver":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW","bundle":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/bundle.json","state":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2JACWPGFRVP3SIUD2SFEUVXHMW","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":"832722a85491a1ec7f0aaf22e95dd038dd909d5d8059b16e3a7e4b7cb908d21e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-21T03:37:39Z","title_canon_sha256":"83cc93a9452e7ccb0993d3a09b73df8f0eb8bad81d7743c398bde8ab01d4c6fb"},"schema_version":"1.0","source":{"id":"2201.08528","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.08528","created_at":"2026-07-05T04:22:19Z"},{"alias_kind":"arxiv_version","alias_value":"2201.08528v3","created_at":"2026-07-05T04:22:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08528","created_at":"2026-07-05T04:22:19Z"},{"alias_kind":"pith_short_12","alias_value":"2JACWPGFRVP3","created_at":"2026-07-05T04:22:19Z"},{"alias_kind":"pith_short_16","alias_value":"2JACWPGFRVP3SIUD","created_at":"2026-07-05T04:22:19Z"},{"alias_kind":"pith_short_8","alias_value":"2JACWPGF","created_at":"2026-07-05T04:22:19Z"}],"graph_snapshots":[{"event_id":"sha256:08cc82383fa9fffeead3c3ee403a24b3559f7aaa00b70e80b157f6edc47bc8f5","target":"graph","created_at":"2026-07-05T04:22:19Z","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/2201.08528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Balancing the data before training a classifier is a popular technique to address the challenges of imbalanced binary classification in tabular data. Balancing is commonly achieved by duplication of minority samples or by generation of synthetic minority samples. While it is well known that balancing affects each classifier differently, most prior empirical studies did not include strong state-of-the-art (SOTA) classifiers as baselines. In this work, we are interested in understanding whether balancing is beneficial, particularly in the context of SOTA classifiers. Thus, we conduct extensive e","authors_text":"Hadar Averbuch-Elor, Yotam Elor","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-21T03:37:39Z","title":"To SMOTE, or not to SMOTE?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08528","kind":"arxiv","version":3},"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":"sha256:72e3661daddab1b1e15b7f8051a2d8b309c2f2c86bfe9fe90244a911860bd5bf","target":"record","created_at":"2026-07-05T04:22:19Z","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":"832722a85491a1ec7f0aaf22e95dd038dd909d5d8059b16e3a7e4b7cb908d21e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-21T03:37:39Z","title_canon_sha256":"83cc93a9452e7ccb0993d3a09b73df8f0eb8bad81d7743c398bde8ab01d4c6fb"},"schema_version":"1.0","source":{"id":"2201.08528","kind":"arxiv","version":3}},"canonical_sha256":"d2402b3cc58d5fb92283d48a4a56e765960cbddd2a164844341b2fcacaf93a2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2402b3cc58d5fb92283d48a4a56e765960cbddd2a164844341b2fcacaf93a2b","first_computed_at":"2026-07-05T04:22:19.242071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:19.242071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H3kRRj26mjH/B5IOFAjIb1A1qKY440u4P5YT70fYCvtouQ8JvEsPNUug+bC5yDKJkt/EZp9PX1T7nDvsWx8MDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:19.242620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.08528","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72e3661daddab1b1e15b7f8051a2d8b309c2f2c86bfe9fe90244a911860bd5bf","sha256:08cc82383fa9fffeead3c3ee403a24b3559f7aaa00b70e80b157f6edc47bc8f5"],"state_sha256":"5cffcf207b3656b5114e58c1bbd953cf4f94a1d3198e740fa896109e8b2a64f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cVcHY9Nk24p03E2GIQqQO2JsudTHFERHdrpxkfNIXYgaLa0vfmtj8PrwXnbBJ2hR06PUzuRUjrrSuEEN1+5EAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T09:22:55.297775Z","bundle_sha256":"9a946bd9cad8902f4946ca6bdba34545dcf8f39243a9fc4d2aefa6a3d36d1158"}}