{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LZI3BMEPBWMCKFWMDQE6FIRSG3","short_pith_number":"pith:LZI3BMEP","schema_version":"1.0","canonical_sha256":"5e51b0b08f0d982516cc1c09e2a23236e0c5bdcf42e01542b746fa221b0b6a06","source":{"kind":"arxiv","id":"2003.07680","version":2},"attestation_state":"computed","paper":{"title":"Designing Tools for Semi-Automated Detection of Machine Learning Biases: An Interview Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CY","authors_text":"Fan Du, Moumita Sinha, Po-Ming Law, Sana Malik","submitted_at":"2020-03-13T00:18:58Z","abstract_excerpt":"Machine learning models often make predictions that bias against certain subgroups of input data. When undetected, machine learning biases can constitute significant financial and ethical implications. Semi-automated tools that involve humans in the loop could facilitate bias detection. Yet, little is known about the considerations involved in their design. In this paper, we report on an interview study with 11 machine learning practitioners for investigating the needs surrounding semi-automated bias detection tools. Based on the findings, we highlight four considerations in designing to guide"},"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":"2003.07680","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2020-03-13T00:18:58Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"be69541c8f11e0187871ad57e393d5d60b77f2f4d3c1993c32516dd4523b067c","abstract_canon_sha256":"e150a24682e58477292b5218fd68077c486ed1318c16da26e50be5093778e03d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:02.279099Z","signature_b64":"yE8h966WLNbrsZ2dSibgvf67QfIJco2HBuWtd7XxQ1VkK5ZEp5vCvpH9bXSHbPwW38p+CfhNvr6X5xddr9kQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e51b0b08f0d982516cc1c09e2a23236e0c5bdcf42e01542b746fa221b0b6a06","last_reissued_at":"2026-07-05T00:49:02.278655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:02.278655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Designing Tools for Semi-Automated Detection of Machine Learning Biases: An Interview Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CY","authors_text":"Fan Du, Moumita Sinha, Po-Ming Law, Sana Malik","submitted_at":"2020-03-13T00:18:58Z","abstract_excerpt":"Machine learning models often make predictions that bias against certain subgroups of input data. When undetected, machine learning biases can constitute significant financial and ethical implications. Semi-automated tools that involve humans in the loop could facilitate bias detection. Yet, little is known about the considerations involved in their design. In this paper, we report on an interview study with 11 machine learning practitioners for investigating the needs surrounding semi-automated bias detection tools. Based on the findings, we highlight four considerations in designing to guide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.07680","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/2003.07680/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":"2003.07680","created_at":"2026-07-05T00:49:02.278712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.07680v2","created_at":"2026-07-05T00:49:02.278712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.07680","created_at":"2026-07-05T00:49:02.278712+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZI3BMEPBWMC","created_at":"2026-07-05T00:49:02.278712+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZI3BMEPBWMCKFWM","created_at":"2026-07-05T00:49:02.278712+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZI3BMEP","created_at":"2026-07-05T00:49:02.278712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02773","citing_title":"A Critical Pragmatism Approach for Algorithmic Fairness: Lessons from Urban Planning Theory","ref_index":104,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZI3BMEPBWMCKFWMDQE6FIRSG3","json":"https://pith.science/pith/LZI3BMEPBWMCKFWMDQE6FIRSG3.json","graph_json":"https://pith.science/api/pith-number/LZI3BMEPBWMCKFWMDQE6FIRSG3/graph.json","events_json":"https://pith.science/api/pith-number/LZI3BMEPBWMCKFWMDQE6FIRSG3/events.json","paper":"https://pith.science/paper/LZI3BMEP"},"agent_actions":{"view_html":"https://pith.science/pith/LZI3BMEPBWMCKFWMDQE6FIRSG3","download_json":"https://pith.science/pith/LZI3BMEPBWMCKFWMDQE6FIRSG3.json","view_paper":"https://pith.science/paper/LZI3BMEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.07680&json=true","fetch_graph":"https://pith.science/api/pith-number/LZI3BMEPBWMCKFWMDQE6FIRSG3/graph.json","fetch_events":"https://pith.science/api/pith-number/LZI3BMEPBWMCKFWMDQE6FIRSG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZI3BMEPBWMCKFWMDQE6FIRSG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZI3BMEPBWMCKFWMDQE6FIRSG3/action/storage_attestation","attest_author":"https://pith.science/pith/LZI3BMEPBWMCKFWMDQE6FIRSG3/action/author_attestation","sign_citation":"https://pith.science/pith/LZI3BMEPBWMCKFWMDQE6FIRSG3/action/citation_signature","submit_replication":"https://pith.science/pith/LZI3BMEPBWMCKFWMDQE6FIRSG3/action/replication_record"}},"created_at":"2026-07-05T00:49:02.278712+00:00","updated_at":"2026-07-05T00:49:02.278712+00:00"}