{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RDC53ZN7HSTXR3DCQOLE6FYL47","short_pith_number":"pith:RDC53ZN7","schema_version":"1.0","canonical_sha256":"88c5dde5bf3ca778ec6283964f170be7d161457ad50453d2acc25c1da519a560","source":{"kind":"arxiv","id":"2302.04732","version":1},"attestation_state":"computed","paper":{"title":"Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Adam Perer, Ameet Talwalkar, \\'Angel Alexander Cabrera, Donald Bertucci, Erica Fu, Jason I. Hong, Kenneth Holstein","submitted_at":"2023-02-09T16:15:04Z","abstract_excerpt":"Machine learning models with high accuracy on test data can still produce systematic failures, such as harmful biases and safety issues, when deployed in the real world. To detect and mitigate such failures, practitioners run behavioral evaluation of their models, checking model outputs for specific types of inputs. Behavioral evaluation is important but challenging, requiring that practitioners discover real-world patterns and validate systematic failures. We conducted 18 semi-structured interviews with ML practitioners to better understand the challenges of behavioral evaluation and found th"},"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":"2302.04732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-02-09T16:15:04Z","cross_cats_sorted":[],"title_canon_sha256":"09f1e6043d3c137b4d6aa6fc3f43970bac71f119d3c4c4712e91fbf6bd051891","abstract_canon_sha256":"b5ce8ff982ea19c8519a0cee1f9b525a92a31156312adff5d4e69808512b08a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:17.923719Z","signature_b64":"qZABA8V1whKhxBNLXRfy92Ysc0zp8kaP6VwnUg+w7giPgkNBZSOf8XlAYqCF3kLc8JdU9lfvWt+H026I1635Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88c5dde5bf3ca778ec6283964f170be7d161457ad50453d2acc25c1da519a560","last_reissued_at":"2026-07-05T05:40:17.923239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:17.923239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Adam Perer, Ameet Talwalkar, \\'Angel Alexander Cabrera, Donald Bertucci, Erica Fu, Jason I. Hong, Kenneth Holstein","submitted_at":"2023-02-09T16:15:04Z","abstract_excerpt":"Machine learning models with high accuracy on test data can still produce systematic failures, such as harmful biases and safety issues, when deployed in the real world. To detect and mitigate such failures, practitioners run behavioral evaluation of their models, checking model outputs for specific types of inputs. Behavioral evaluation is important but challenging, requiring that practitioners discover real-world patterns and validate systematic failures. We conducted 18 semi-structured interviews with ML practitioners to better understand the challenges of behavioral evaluation and found th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04732","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/2302.04732/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":"2302.04732","created_at":"2026-07-05T05:40:17.923296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04732v1","created_at":"2026-07-05T05:40:17.923296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04732","created_at":"2026-07-05T05:40:17.923296+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDC53ZN7HSTX","created_at":"2026-07-05T05:40:17.923296+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDC53ZN7HSTXR3DC","created_at":"2026-07-05T05:40:17.923296+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDC53ZN7","created_at":"2026-07-05T05:40:17.923296+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/RDC53ZN7HSTXR3DCQOLE6FYL47","json":"https://pith.science/pith/RDC53ZN7HSTXR3DCQOLE6FYL47.json","graph_json":"https://pith.science/api/pith-number/RDC53ZN7HSTXR3DCQOLE6FYL47/graph.json","events_json":"https://pith.science/api/pith-number/RDC53ZN7HSTXR3DCQOLE6FYL47/events.json","paper":"https://pith.science/paper/RDC53ZN7"},"agent_actions":{"view_html":"https://pith.science/pith/RDC53ZN7HSTXR3DCQOLE6FYL47","download_json":"https://pith.science/pith/RDC53ZN7HSTXR3DCQOLE6FYL47.json","view_paper":"https://pith.science/paper/RDC53ZN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04732&json=true","fetch_graph":"https://pith.science/api/pith-number/RDC53ZN7HSTXR3DCQOLE6FYL47/graph.json","fetch_events":"https://pith.science/api/pith-number/RDC53ZN7HSTXR3DCQOLE6FYL47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDC53ZN7HSTXR3DCQOLE6FYL47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDC53ZN7HSTXR3DCQOLE6FYL47/action/storage_attestation","attest_author":"https://pith.science/pith/RDC53ZN7HSTXR3DCQOLE6FYL47/action/author_attestation","sign_citation":"https://pith.science/pith/RDC53ZN7HSTXR3DCQOLE6FYL47/action/citation_signature","submit_replication":"https://pith.science/pith/RDC53ZN7HSTXR3DCQOLE6FYL47/action/replication_record"}},"created_at":"2026-07-05T05:40:17.923296+00:00","updated_at":"2026-07-05T05:40:17.923296+00:00"}