{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3FXRTHO5VQCABUZUANDDV5DYZ2","short_pith_number":"pith:3FXRTHO5","schema_version":"1.0","canonical_sha256":"d96f199dddac0400d33403463af478ce99bc124f0ba30a301866e89dd00f2b04","source":{"kind":"arxiv","id":"1907.09701","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Attribution Methods with Relative Feature Importance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Been Kim, Mengjiao Yang","submitted_at":"2019-07-23T05:50:14Z","abstract_excerpt":"Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative evaluation of feature attribution methods remains difficult due to the lack of ground truth: we do not know which input features are in fact important to a model. In this work, we propose a framework for Benchmarking Attribution Methods (BAM) with a priori knowledge of relative feature importance. BAM includes 1) a carefully crafted dataset and models trained with "},"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":"1907.09701","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-23T05:50:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4ed55b5454d91cf238fbe4ad762918d649a0e31af8c81939cce3d65d3a5c842f","abstract_canon_sha256":"b7468d85c946319ecffe0e1792bb3fd14bca63eb869fb04b91f5a2ce75f221f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:50.400440Z","signature_b64":"r9sXufI/1NVHsIDiCNIQoHkIe8CEvl40cvLuoPPCK8fY8yVWaokYc0ylWTveJ4YHq3dcdAD4IJ5OrF75r/8mDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d96f199dddac0400d33403463af478ce99bc124f0ba30a301866e89dd00f2b04","last_reissued_at":"2026-07-05T00:16:50.399917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:50.399917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Attribution Methods with Relative Feature Importance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Been Kim, Mengjiao Yang","submitted_at":"2019-07-23T05:50:14Z","abstract_excerpt":"Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative evaluation of feature attribution methods remains difficult due to the lack of ground truth: we do not know which input features are in fact important to a model. In this work, we propose a framework for Benchmarking Attribution Methods (BAM) with a priori knowledge of relative feature importance. BAM includes 1) a carefully crafted dataset and models trained with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.09701","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/1907.09701/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":"1907.09701","created_at":"2026-07-05T00:16:50.399976+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.09701v2","created_at":"2026-07-05T00:16:50.399976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.09701","created_at":"2026-07-05T00:16:50.399976+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FXRTHO5VQCA","created_at":"2026-07-05T00:16:50.399976+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FXRTHO5VQCABUZU","created_at":"2026-07-05T00:16:50.399976+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FXRTHO5","created_at":"2026-07-05T00:16:50.399976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15700","citing_title":"AGOP-IxG: A Gradient Covariance Filter for Local Feature Attribution on Tabular Data, with a Controlled Benchmark","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18878","citing_title":"Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08519","citing_title":"SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data","ref_index":173,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3FXRTHO5VQCABUZUANDDV5DYZ2","json":"https://pith.science/pith/3FXRTHO5VQCABUZUANDDV5DYZ2.json","graph_json":"https://pith.science/api/pith-number/3FXRTHO5VQCABUZUANDDV5DYZ2/graph.json","events_json":"https://pith.science/api/pith-number/3FXRTHO5VQCABUZUANDDV5DYZ2/events.json","paper":"https://pith.science/paper/3FXRTHO5"},"agent_actions":{"view_html":"https://pith.science/pith/3FXRTHO5VQCABUZUANDDV5DYZ2","download_json":"https://pith.science/pith/3FXRTHO5VQCABUZUANDDV5DYZ2.json","view_paper":"https://pith.science/paper/3FXRTHO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.09701&json=true","fetch_graph":"https://pith.science/api/pith-number/3FXRTHO5VQCABUZUANDDV5DYZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/3FXRTHO5VQCABUZUANDDV5DYZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FXRTHO5VQCABUZUANDDV5DYZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FXRTHO5VQCABUZUANDDV5DYZ2/action/storage_attestation","attest_author":"https://pith.science/pith/3FXRTHO5VQCABUZUANDDV5DYZ2/action/author_attestation","sign_citation":"https://pith.science/pith/3FXRTHO5VQCABUZUANDDV5DYZ2/action/citation_signature","submit_replication":"https://pith.science/pith/3FXRTHO5VQCABUZUANDDV5DYZ2/action/replication_record"}},"created_at":"2026-07-05T00:16:50.399976+00:00","updated_at":"2026-07-05T00:16:50.399976+00:00"}