{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:POFLFSKUZ24POOZDTCD7XXZNPS","short_pith_number":"pith:POFLFSKU","schema_version":"1.0","canonical_sha256":"7b8ab2c954ceb8f73b239887fbdf2d7cbcbf50da003ee80983c1ac9512028d3c","source":{"kind":"arxiv","id":"2210.14056","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical Encodings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ajay Chawda, Marius Kloft, Stefanie Grimm","submitted_at":"2022-10-25T14:33:17Z","abstract_excerpt":"In this paper, we introduce the Vehicle Claims dataset, consisting of fraudulent insurance claims for automotive repairs. The data belongs to the more broad category of Auditing data, which includes also Journals and Network Intrusion data. Insurance claim data are distinctively different from other auditing data (such as network intrusion data) in their high number of categorical attributes. We tackle the common problem of missing benchmark datasets for anomaly detection: datasets are mostly confidential, and the public tabular datasets do not contain relevant and sufficient categorical attri"},"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":"2210.14056","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T14:33:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4a9c49d9139fc0c57102cbdfa6ca1e8d2226cc1c123ba273b17b0e3838e20ef","abstract_canon_sha256":"1ac20e6f58b3140d6f000467bac282820b3f99bb7608bb6b17a9fd1a311a6367"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:43.037013Z","signature_b64":"X+377HSyq8jxLTYdcuTM2FaRUGcJWOaUPEI1wRixoL+9lSA1iWJQdUUiPvBkUSds9JbgpquOjHyh1HeU+lJlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b8ab2c954ceb8f73b239887fbdf2d7cbcbf50da003ee80983c1ac9512028d3c","last_reissued_at":"2026-07-05T05:10:43.036364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:43.036364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical Encodings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ajay Chawda, Marius Kloft, Stefanie Grimm","submitted_at":"2022-10-25T14:33:17Z","abstract_excerpt":"In this paper, we introduce the Vehicle Claims dataset, consisting of fraudulent insurance claims for automotive repairs. The data belongs to the more broad category of Auditing data, which includes also Journals and Network Intrusion data. Insurance claim data are distinctively different from other auditing data (such as network intrusion data) in their high number of categorical attributes. We tackle the common problem of missing benchmark datasets for anomaly detection: datasets are mostly confidential, and the public tabular datasets do not contain relevant and sufficient categorical attri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14056","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/2210.14056/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":"2210.14056","created_at":"2026-07-05T05:10:43.036434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14056v2","created_at":"2026-07-05T05:10:43.036434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14056","created_at":"2026-07-05T05:10:43.036434+00:00"},{"alias_kind":"pith_short_12","alias_value":"POFLFSKUZ24P","created_at":"2026-07-05T05:10:43.036434+00:00"},{"alias_kind":"pith_short_16","alias_value":"POFLFSKUZ24POOZD","created_at":"2026-07-05T05:10:43.036434+00:00"},{"alias_kind":"pith_short_8","alias_value":"POFLFSKU","created_at":"2026-07-05T05:10:43.036434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30046","citing_title":"Masked Diffusion Modeling for Anomaly Detection","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POFLFSKUZ24POOZDTCD7XXZNPS","json":"https://pith.science/pith/POFLFSKUZ24POOZDTCD7XXZNPS.json","graph_json":"https://pith.science/api/pith-number/POFLFSKUZ24POOZDTCD7XXZNPS/graph.json","events_json":"https://pith.science/api/pith-number/POFLFSKUZ24POOZDTCD7XXZNPS/events.json","paper":"https://pith.science/paper/POFLFSKU"},"agent_actions":{"view_html":"https://pith.science/pith/POFLFSKUZ24POOZDTCD7XXZNPS","download_json":"https://pith.science/pith/POFLFSKUZ24POOZDTCD7XXZNPS.json","view_paper":"https://pith.science/paper/POFLFSKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14056&json=true","fetch_graph":"https://pith.science/api/pith-number/POFLFSKUZ24POOZDTCD7XXZNPS/graph.json","fetch_events":"https://pith.science/api/pith-number/POFLFSKUZ24POOZDTCD7XXZNPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POFLFSKUZ24POOZDTCD7XXZNPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POFLFSKUZ24POOZDTCD7XXZNPS/action/storage_attestation","attest_author":"https://pith.science/pith/POFLFSKUZ24POOZDTCD7XXZNPS/action/author_attestation","sign_citation":"https://pith.science/pith/POFLFSKUZ24POOZDTCD7XXZNPS/action/citation_signature","submit_replication":"https://pith.science/pith/POFLFSKUZ24POOZDTCD7XXZNPS/action/replication_record"}},"created_at":"2026-07-05T05:10:43.036434+00:00","updated_at":"2026-07-05T05:10:43.036434+00:00"}