{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WU6EPTRZT7JVYOXPSPPN3ZOHP3","short_pith_number":"pith:WU6EPTRZ","schema_version":"1.0","canonical_sha256":"b53c47ce399fd35c3aef93dedde5c77ef1c4f4c0ac32da68e9e493246271ce05","source":{"kind":"arxiv","id":"2302.07444","version":2},"attestation_state":"computed","paper":{"title":"A Case Study on Designing Evaluations of ML Explanations with Simulated User Studies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Ada Martin, Pedro Saleiro, S\\'ergio Jesus, Valerie Chen","submitted_at":"2023-02-15T03:27:55Z","abstract_excerpt":"When conducting user studies to ascertain the usefulness of model explanations in aiding human decision-making, it is important to use real-world use cases, data, and users. However, this process can be resource-intensive, allowing only a limited number of explanation methods to be evaluated. Simulated user evaluations (SimEvals), which use machine learning models as a proxy for human users, have been proposed as an intermediate step to select promising explanation methods. In this work, we conduct the first SimEvals on a real-world use case to evaluate whether explanations can better support "},"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":"2302.07444","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-15T03:27:55Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"57b6f239ae9820786bfde9747632b5f75e7c8882308d0b7f4b7a354ebbf37a1e","abstract_canon_sha256":"380ce644e81b67bff69e41430e9cc638b48f9df047e173f88396214d249995c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:14.185148Z","signature_b64":"wdbPYA8NQym7htfWmuGvt3NMtkkDkfk9fzTjgkAG51X14Kt4dWtKhDZbHH1TsFRUkmD+P720EnPFIiFYNmikDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b53c47ce399fd35c3aef93dedde5c77ef1c4f4c0ac32da68e9e493246271ce05","last_reissued_at":"2026-07-05T05:53:14.184650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:14.184650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Case Study on Designing Evaluations of ML Explanations with Simulated User Studies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Ada Martin, Pedro Saleiro, S\\'ergio Jesus, Valerie Chen","submitted_at":"2023-02-15T03:27:55Z","abstract_excerpt":"When conducting user studies to ascertain the usefulness of model explanations in aiding human decision-making, it is important to use real-world use cases, data, and users. However, this process can be resource-intensive, allowing only a limited number of explanation methods to be evaluated. Simulated user evaluations (SimEvals), which use machine learning models as a proxy for human users, have been proposed as an intermediate step to select promising explanation methods. In this work, we conduct the first SimEvals on a real-world use case to evaluate whether explanations can better support "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07444","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/2302.07444/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":"2302.07444","created_at":"2026-07-05T05:53:14.184706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.07444v2","created_at":"2026-07-05T05:53:14.184706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07444","created_at":"2026-07-05T05:53:14.184706+00:00"},{"alias_kind":"pith_short_12","alias_value":"WU6EPTRZT7JV","created_at":"2026-07-05T05:53:14.184706+00:00"},{"alias_kind":"pith_short_16","alias_value":"WU6EPTRZT7JVYOXP","created_at":"2026-07-05T05:53:14.184706+00:00"},{"alias_kind":"pith_short_8","alias_value":"WU6EPTRZ","created_at":"2026-07-05T05:53:14.184706+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/WU6EPTRZT7JVYOXPSPPN3ZOHP3","json":"https://pith.science/pith/WU6EPTRZT7JVYOXPSPPN3ZOHP3.json","graph_json":"https://pith.science/api/pith-number/WU6EPTRZT7JVYOXPSPPN3ZOHP3/graph.json","events_json":"https://pith.science/api/pith-number/WU6EPTRZT7JVYOXPSPPN3ZOHP3/events.json","paper":"https://pith.science/paper/WU6EPTRZ"},"agent_actions":{"view_html":"https://pith.science/pith/WU6EPTRZT7JVYOXPSPPN3ZOHP3","download_json":"https://pith.science/pith/WU6EPTRZT7JVYOXPSPPN3ZOHP3.json","view_paper":"https://pith.science/paper/WU6EPTRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.07444&json=true","fetch_graph":"https://pith.science/api/pith-number/WU6EPTRZT7JVYOXPSPPN3ZOHP3/graph.json","fetch_events":"https://pith.science/api/pith-number/WU6EPTRZT7JVYOXPSPPN3ZOHP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WU6EPTRZT7JVYOXPSPPN3ZOHP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WU6EPTRZT7JVYOXPSPPN3ZOHP3/action/storage_attestation","attest_author":"https://pith.science/pith/WU6EPTRZT7JVYOXPSPPN3ZOHP3/action/author_attestation","sign_citation":"https://pith.science/pith/WU6EPTRZT7JVYOXPSPPN3ZOHP3/action/citation_signature","submit_replication":"https://pith.science/pith/WU6EPTRZT7JVYOXPSPPN3ZOHP3/action/replication_record"}},"created_at":"2026-07-05T05:53:14.184706+00:00","updated_at":"2026-07-05T05:53:14.184706+00:00"}