{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R7ROMFXLLQN2CIQZ2XSQCXQLPW","short_pith_number":"pith:R7ROMFXL","schema_version":"1.0","canonical_sha256":"8fe2e616eb5c1ba12219d5e5015e0b7d8ee7a63be7f1c5abbe733d069235b8ad","source":{"kind":"arxiv","id":"2307.04468","version":1},"attestation_state":"computed","paper":{"title":"Badgers: generating data quality deficits with Python","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Trendowicz, Daniel Seifert, Julien Siebert, Michael Kl\\\"as, Patricia Kelbert","submitted_at":"2023-07-10T10:34:12Z","abstract_excerpt":"Generating context specific data quality deficits is necessary to experimentally assess data quality of data-driven (artificial intelligence (AI) or machine learning (ML)) applications. In this paper we present badgers, an extensible open-source Python library to generate data quality deficits (outliers, imbalanced data, drift, etc.) for different modalities (tabular data, time-series, text, etc.). The documentation is accessible at https://fraunhofer-iese.github.io/badgers/ and the source code at https://github.com/Fraunhofer-IESE/badgers"},"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":"2307.04468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-10T10:34:12Z","cross_cats_sorted":[],"title_canon_sha256":"2de526923913f26fbd8412ab199a6af32acbf6752fd163d61138781787d05e96","abstract_canon_sha256":"f05ddc6ca17bc77300221f4468b47908b295d3234a9e7a77cc85ef480ff5a0d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:13.847389Z","signature_b64":"ohkzkx6DaQFOQWjIaZohmqP2Hx8nj2rlAL4RMM1MAwHMQ2sjKMQ7H3REFfv9pBg96wqDtv1u3eKI798HJG7tDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fe2e616eb5c1ba12219d5e5015e0b7d8ee7a63be7f1c5abbe733d069235b8ad","last_reissued_at":"2026-07-05T06:29:13.846932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:13.846932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Badgers: generating data quality deficits with Python","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Trendowicz, Daniel Seifert, Julien Siebert, Michael Kl\\\"as, Patricia Kelbert","submitted_at":"2023-07-10T10:34:12Z","abstract_excerpt":"Generating context specific data quality deficits is necessary to experimentally assess data quality of data-driven (artificial intelligence (AI) or machine learning (ML)) applications. In this paper we present badgers, an extensible open-source Python library to generate data quality deficits (outliers, imbalanced data, drift, etc.) for different modalities (tabular data, time-series, text, etc.). The documentation is accessible at https://fraunhofer-iese.github.io/badgers/ and the source code at https://github.com/Fraunhofer-IESE/badgers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04468","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/2307.04468/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":"2307.04468","created_at":"2026-07-05T06:29:13.846986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04468v1","created_at":"2026-07-05T06:29:13.846986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04468","created_at":"2026-07-05T06:29:13.846986+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7ROMFXLLQN2","created_at":"2026-07-05T06:29:13.846986+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7ROMFXLLQN2CIQZ","created_at":"2026-07-05T06:29:13.846986+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7ROMFXL","created_at":"2026-07-05T06:29:13.846986+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/R7ROMFXLLQN2CIQZ2XSQCXQLPW","json":"https://pith.science/pith/R7ROMFXLLQN2CIQZ2XSQCXQLPW.json","graph_json":"https://pith.science/api/pith-number/R7ROMFXLLQN2CIQZ2XSQCXQLPW/graph.json","events_json":"https://pith.science/api/pith-number/R7ROMFXLLQN2CIQZ2XSQCXQLPW/events.json","paper":"https://pith.science/paper/R7ROMFXL"},"agent_actions":{"view_html":"https://pith.science/pith/R7ROMFXLLQN2CIQZ2XSQCXQLPW","download_json":"https://pith.science/pith/R7ROMFXLLQN2CIQZ2XSQCXQLPW.json","view_paper":"https://pith.science/paper/R7ROMFXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04468&json=true","fetch_graph":"https://pith.science/api/pith-number/R7ROMFXLLQN2CIQZ2XSQCXQLPW/graph.json","fetch_events":"https://pith.science/api/pith-number/R7ROMFXLLQN2CIQZ2XSQCXQLPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7ROMFXLLQN2CIQZ2XSQCXQLPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7ROMFXLLQN2CIQZ2XSQCXQLPW/action/storage_attestation","attest_author":"https://pith.science/pith/R7ROMFXLLQN2CIQZ2XSQCXQLPW/action/author_attestation","sign_citation":"https://pith.science/pith/R7ROMFXLLQN2CIQZ2XSQCXQLPW/action/citation_signature","submit_replication":"https://pith.science/pith/R7ROMFXLLQN2CIQZ2XSQCXQLPW/action/replication_record"}},"created_at":"2026-07-05T06:29:13.846986+00:00","updated_at":"2026-07-05T06:29:13.846986+00:00"}