{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QFTTKVGOUEJVD3N3YH3NFEE3V2","short_pith_number":"pith:QFTTKVGO","schema_version":"1.0","canonical_sha256":"81673554cea11351edbbc1f6d2909bae9829a4bf4e5ca1f9ea5c250c90068690","source":{"kind":"arxiv","id":"2211.13358","version":2},"attestation_state":"computed","paper":{"title":"Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andr\\'e Cruz, Duarte Alves, Jo\\~ao Gama, Jos\\'e Pombal, Pedro Bizarro, Pedro Saleiro, Rita P. Ribeiro, S\\'ergio Jesus","submitted_at":"2022-11-24T00:03:29Z","abstract_excerpt":"Evaluating new techniques on realistic datasets plays a crucial role in the development of ML research and its broader adoption by practitioners. In recent years, there has been a significant increase of publicly available unstructured data resources for computer vision and NLP tasks. However, tabular data -- which is prevalent in many high-stakes domains -- has been lagging behind. To bridge this gap, we present Bank Account Fraud (BAF), the first publicly available privacy-preserving, large-scale, realistic suite of tabular datasets. The suite was generated by applying state-of-the-art tabul"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.13358","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-24T00:03:29Z","cross_cats_sorted":[],"title_canon_sha256":"316926d7525090944fb1e512e7aa4899d8c7863bbadbbd4c40071eb78dbdcb16","abstract_canon_sha256":"6c65f71c60441976cf1dcd3c4af4f63e20bb03574b01fe3aad2aede8e5033863"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:56.485351Z","signature_b64":"+35PGeEE5WPU9/tKgAw4ojXuUJqxCwxrYJO315kvEUVMl/uIz59xzYHCCKCBF43SzIlA7jJEY+t5SSKzoJBiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81673554cea11351edbbc1f6d2909bae9829a4bf4e5ca1f9ea5c250c90068690","last_reissued_at":"2026-07-05T05:19:56.484909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:56.484909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andr\\'e Cruz, Duarte Alves, Jo\\~ao Gama, Jos\\'e Pombal, Pedro Bizarro, Pedro Saleiro, Rita P. Ribeiro, S\\'ergio Jesus","submitted_at":"2022-11-24T00:03:29Z","abstract_excerpt":"Evaluating new techniques on realistic datasets plays a crucial role in the development of ML research and its broader adoption by practitioners. In recent years, there has been a significant increase of publicly available unstructured data resources for computer vision and NLP tasks. However, tabular data -- which is prevalent in many high-stakes domains -- has been lagging behind. To bridge this gap, we present Bank Account Fraud (BAF), the first publicly available privacy-preserving, large-scale, realistic suite of tabular datasets. The suite was generated by applying state-of-the-art tabul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13358","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/2211.13358/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.13358","created_at":"2026-07-05T05:19:56.484964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13358v2","created_at":"2026-07-05T05:19:56.484964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13358","created_at":"2026-07-05T05:19:56.484964+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFTTKVGOUEJV","created_at":"2026-07-05T05:19:56.484964+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFTTKVGOUEJVD3N3","created_at":"2026-07-05T05:19:56.484964+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFTTKVGO","created_at":"2026-07-05T05:19:56.484964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFTTKVGOUEJVD3N3YH3NFEE3V2","json":"https://pith.science/pith/QFTTKVGOUEJVD3N3YH3NFEE3V2.json","graph_json":"https://pith.science/api/pith-number/QFTTKVGOUEJVD3N3YH3NFEE3V2/graph.json","events_json":"https://pith.science/api/pith-number/QFTTKVGOUEJVD3N3YH3NFEE3V2/events.json","paper":"https://pith.science/paper/QFTTKVGO"},"agent_actions":{"view_html":"https://pith.science/pith/QFTTKVGOUEJVD3N3YH3NFEE3V2","download_json":"https://pith.science/pith/QFTTKVGOUEJVD3N3YH3NFEE3V2.json","view_paper":"https://pith.science/paper/QFTTKVGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13358&json=true","fetch_graph":"https://pith.science/api/pith-number/QFTTKVGOUEJVD3N3YH3NFEE3V2/graph.json","fetch_events":"https://pith.science/api/pith-number/QFTTKVGOUEJVD3N3YH3NFEE3V2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFTTKVGOUEJVD3N3YH3NFEE3V2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFTTKVGOUEJVD3N3YH3NFEE3V2/action/storage_attestation","attest_author":"https://pith.science/pith/QFTTKVGOUEJVD3N3YH3NFEE3V2/action/author_attestation","sign_citation":"https://pith.science/pith/QFTTKVGOUEJVD3N3YH3NFEE3V2/action/citation_signature","submit_replication":"https://pith.science/pith/QFTTKVGOUEJVD3N3YH3NFEE3V2/action/replication_record"}},"created_at":"2026-07-05T05:19:56.484964+00:00","updated_at":"2026-07-05T05:19:56.484964+00:00"}