{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5RIBYIL3AZPRGMEDQGRMT7Q4IT","short_pith_number":"pith:5RIBYIL3","schema_version":"1.0","canonical_sha256":"ec501c217b065f13308381a2c9fe1c44eabb964f81d6b82b00a99787fa07a9f2","source":{"kind":"arxiv","id":"2106.12543","version":4},"attestation_state":"computed","paper":{"title":"Synthetic Benchmarks for Scientific Research in Explainable Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Colin White, Sujay Khandagale, Willie Neiswanger, Yang Liu","submitted_at":"2021-06-23T17:10:21Z","abstract_excerpt":"As machine learning models grow more complex and their applications become more high-stakes, tools for explaining model predictions have become increasingly important. This has spurred a flurry of research in model explainability and has given rise to feature attribution methods such as LIME and SHAP. Despite their widespread use, evaluating and comparing different feature attribution methods remains challenging: evaluations ideally require human studies, and empirical evaluation metrics are often data-intensive or computationally prohibitive on real-world datasets. In this work, we address 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":"2106.12543","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T17:10:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"56a367d757ea503e25849f83e2079f4466f562dc54915e6791895e80c87a1d55","abstract_canon_sha256":"24a5805cec80b159a4da87aed8a2e83c56f70ec661c377a1d08216024fa97884"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:17.409491Z","signature_b64":"DtLlrj9D156YXsthneTQOU89l1FQZVz6B9exFwAv9MqPGQFQor9aQBktd+OECvIfah1iTfUNZUg0Q+jKhqUTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec501c217b065f13308381a2c9fe1c44eabb964f81d6b82b00a99787fa07a9f2","last_reissued_at":"2026-07-05T03:29:17.408376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:17.408376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Benchmarks for Scientific Research in Explainable Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Colin White, Sujay Khandagale, Willie Neiswanger, Yang Liu","submitted_at":"2021-06-23T17:10:21Z","abstract_excerpt":"As machine learning models grow more complex and their applications become more high-stakes, tools for explaining model predictions have become increasingly important. This has spurred a flurry of research in model explainability and has given rise to feature attribution methods such as LIME and SHAP. Despite their widespread use, evaluating and comparing different feature attribution methods remains challenging: evaluations ideally require human studies, and empirical evaluation metrics are often data-intensive or computationally prohibitive on real-world datasets. In this work, we address th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12543","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/2106.12543/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":"2106.12543","created_at":"2026-07-05T03:29:17.409074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.12543v4","created_at":"2026-07-05T03:29:17.409074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12543","created_at":"2026-07-05T03:29:17.409074+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RIBYIL3AZPR","created_at":"2026-07-05T03:29:17.409074+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RIBYIL3AZPRGMED","created_at":"2026-07-05T03:29:17.409074+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RIBYIL3","created_at":"2026-07-05T03:29:17.409074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07153","citing_title":"Feature Importance Depends on Properties of the Data: Towards Choosing the Correct Explanations for Your Data and Decision Trees based Models","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RIBYIL3AZPRGMEDQGRMT7Q4IT","json":"https://pith.science/pith/5RIBYIL3AZPRGMEDQGRMT7Q4IT.json","graph_json":"https://pith.science/api/pith-number/5RIBYIL3AZPRGMEDQGRMT7Q4IT/graph.json","events_json":"https://pith.science/api/pith-number/5RIBYIL3AZPRGMEDQGRMT7Q4IT/events.json","paper":"https://pith.science/paper/5RIBYIL3"},"agent_actions":{"view_html":"https://pith.science/pith/5RIBYIL3AZPRGMEDQGRMT7Q4IT","download_json":"https://pith.science/pith/5RIBYIL3AZPRGMEDQGRMT7Q4IT.json","view_paper":"https://pith.science/paper/5RIBYIL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.12543&json=true","fetch_graph":"https://pith.science/api/pith-number/5RIBYIL3AZPRGMEDQGRMT7Q4IT/graph.json","fetch_events":"https://pith.science/api/pith-number/5RIBYIL3AZPRGMEDQGRMT7Q4IT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RIBYIL3AZPRGMEDQGRMT7Q4IT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RIBYIL3AZPRGMEDQGRMT7Q4IT/action/storage_attestation","attest_author":"https://pith.science/pith/5RIBYIL3AZPRGMEDQGRMT7Q4IT/action/author_attestation","sign_citation":"https://pith.science/pith/5RIBYIL3AZPRGMEDQGRMT7Q4IT/action/citation_signature","submit_replication":"https://pith.science/pith/5RIBYIL3AZPRGMEDQGRMT7Q4IT/action/replication_record"}},"created_at":"2026-07-05T03:29:17.409074+00:00","updated_at":"2026-07-05T03:29:17.409074+00:00"}