{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XAXVRBQ5URBP2GNCYGCZBS5RRD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"56b62bee01a5db00c80140302c287fa104870fd0d7419f41402c27e99827865f","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-24T14:46:19Z","title_canon_sha256":"87f62470b11fbe49c78ad901b17597ea83564c321ac161099549cb6fba1b1abc"},"schema_version":"1.0","source":{"id":"2206.13503","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13503","created_at":"2026-07-05T05:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13503v4","created_at":"2026-07-05T05:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13503","created_at":"2026-07-05T05:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"XAXVRBQ5URBP","created_at":"2026-07-05T05:44:24Z"},{"alias_kind":"pith_short_16","alias_value":"XAXVRBQ5URBP2GNC","created_at":"2026-07-05T05:44:24Z"},{"alias_kind":"pith_short_8","alias_value":"XAXVRBQ5","created_at":"2026-07-05T05:44:24Z"}],"graph_snapshots":[{"event_id":"sha256:542d9b5d79c2c5225cc68172c023b85e4e8df5c9e0d390d0ce3195ece50c16e0","target":"graph","created_at":"2026-07-05T05:44:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.13503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ameet Talwalkar, Kasun Amarasinghe, Kit T. Rodolfa, Pedro Bizarro, Pedro Saleiro, Rayid Ghani, S\\'ergio Jesus, Valerie Chen, Vladimir Balayan","cross_cats":["cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-24T14:46:19Z","title":"On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13503","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:11dd6c69fee770de3a6fc30d531e54796196b9c1fde8220de1ddec33a32ff387","target":"record","created_at":"2026-07-05T05:44:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"56b62bee01a5db00c80140302c287fa104870fd0d7419f41402c27e99827865f","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-24T14:46:19Z","title_canon_sha256":"87f62470b11fbe49c78ad901b17597ea83564c321ac161099549cb6fba1b1abc"},"schema_version":"1.0","source":{"id":"2206.13503","kind":"arxiv","version":4}},"canonical_sha256":"b82f58861da442fd19a2c18590cbb188eaf598c5cee27905b43f1aa59f811e84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b82f58861da442fd19a2c18590cbb188eaf598c5cee27905b43f1aa59f811e84","first_computed_at":"2026-07-05T05:44:24.594206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:24.594206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FE1Nc0QLThwuDsgPCyPfNoaeKPhaDeP1utadAazk5rnXsEyPm52yF+zuvqmPR9rb7Mw7rCbjHpry0a3VVIvRBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:24.594669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.13503","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11dd6c69fee770de3a6fc30d531e54796196b9c1fde8220de1ddec33a32ff387","sha256:542d9b5d79c2c5225cc68172c023b85e4e8df5c9e0d390d0ce3195ece50c16e0"],"state_sha256":"5f79c4ab8af6f03f1f5de9d96cbffad4d397569ec819634ba1f702d2d105128c"}