{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XAXVRBQ5URBP2GNCYGCZBS5RRD","short_pith_number":"pith:XAXVRBQ5","schema_version":"1.0","canonical_sha256":"b82f58861da442fd19a2c18590cbb188eaf598c5cee27905b43f1aa59f811e84","source":{"kind":"arxiv","id":"2206.13503","version":4},"attestation_state":"computed","paper":{"title":"On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Ameet Talwalkar, Kasun Amarasinghe, Kit T. Rodolfa, Pedro Bizarro, Pedro Saleiro, Rayid Ghani, S\\'ergio Jesus, Valerie Chen, Vladimir Balayan","submitted_at":"2022-06-24T14:46:19Z","abstract_excerpt":"Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, resulting in limited conclusions of methods' real-world utility. In this work, we seek to bridge this gap by conducting a study that evaluates three popular explainable ML methods in a setting consistent with the intended deployment context. We build on a previous study on e-commerce fraud detection and make crucial modifications to its setup re"},"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":"2206.13503","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-24T14:46:19Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"87f62470b11fbe49c78ad901b17597ea83564c321ac161099549cb6fba1b1abc","abstract_canon_sha256":"56b62bee01a5db00c80140302c287fa104870fd0d7419f41402c27e99827865f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:24.594669Z","signature_b64":"FE1Nc0QLThwuDsgPCyPfNoaeKPhaDeP1utadAazk5rnXsEyPm52yF+zuvqmPR9rb7Mw7rCbjHpry0a3VVIvRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b82f58861da442fd19a2c18590cbb188eaf598c5cee27905b43f1aa59f811e84","last_reissued_at":"2026-07-05T05:44:24.594206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:24.594206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Ameet Talwalkar, Kasun Amarasinghe, Kit T. Rodolfa, Pedro Bizarro, Pedro Saleiro, Rayid Ghani, S\\'ergio Jesus, Valerie Chen, Vladimir Balayan","submitted_at":"2022-06-24T14:46:19Z","abstract_excerpt":"Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, resulting in limited conclusions of methods' real-world utility. In this work, we seek to bridge this gap by conducting a study that evaluates three popular explainable ML methods in a setting consistent with the intended deployment context. We build on a previous study on e-commerce fraud detection and make crucial modifications to its setup re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13503","kind":"arxiv","version":4},"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/2206.13503/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":"2206.13503","created_at":"2026-07-05T05:44:24.594263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.13503v4","created_at":"2026-07-05T05:44:24.594263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13503","created_at":"2026-07-05T05:44:24.594263+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAXVRBQ5URBP","created_at":"2026-07-05T05:44:24.594263+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAXVRBQ5URBP2GNC","created_at":"2026-07-05T05:44:24.594263+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAXVRBQ5","created_at":"2026-07-05T05:44:24.594263+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/XAXVRBQ5URBP2GNCYGCZBS5RRD","json":"https://pith.science/pith/XAXVRBQ5URBP2GNCYGCZBS5RRD.json","graph_json":"https://pith.science/api/pith-number/XAXVRBQ5URBP2GNCYGCZBS5RRD/graph.json","events_json":"https://pith.science/api/pith-number/XAXVRBQ5URBP2GNCYGCZBS5RRD/events.json","paper":"https://pith.science/paper/XAXVRBQ5"},"agent_actions":{"view_html":"https://pith.science/pith/XAXVRBQ5URBP2GNCYGCZBS5RRD","download_json":"https://pith.science/pith/XAXVRBQ5URBP2GNCYGCZBS5RRD.json","view_paper":"https://pith.science/paper/XAXVRBQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.13503&json=true","fetch_graph":"https://pith.science/api/pith-number/XAXVRBQ5URBP2GNCYGCZBS5RRD/graph.json","fetch_events":"https://pith.science/api/pith-number/XAXVRBQ5URBP2GNCYGCZBS5RRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAXVRBQ5URBP2GNCYGCZBS5RRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAXVRBQ5URBP2GNCYGCZBS5RRD/action/storage_attestation","attest_author":"https://pith.science/pith/XAXVRBQ5URBP2GNCYGCZBS5RRD/action/author_attestation","sign_citation":"https://pith.science/pith/XAXVRBQ5URBP2GNCYGCZBS5RRD/action/citation_signature","submit_replication":"https://pith.science/pith/XAXVRBQ5URBP2GNCYGCZBS5RRD/action/replication_record"}},"created_at":"2026-07-05T05:44:24.594263+00:00","updated_at":"2026-07-05T05:44:24.594263+00:00"}