{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FSZ4R55RA7COA4ZDKOK3GGDWYS","short_pith_number":"pith:FSZ4R55R","schema_version":"1.0","canonical_sha256":"2cb3c8f7b107c4e073235395b31876c49cd010759a6052b8f2896f6ae9d1f342","source":{"kind":"arxiv","id":"2605.15700","version":1},"attestation_state":"computed","paper":{"title":"AGOP-IxG: A Gradient Covariance Filter for Local Feature Attribution on Tabular Data, with a Controlled Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Raj Kiran Gupta Katakam","submitted_at":"2026-05-15T07:45:35Z","abstract_excerpt":"Automated machine learning pipelines increasingly produce models whose predictions must be explained to end users, auditors, and downstream decision systems. The most widely used feature attribution methods (SHAP, Integrated Gradients, LIME) are typically chosen by convention rather than measured fidelity, because rigorous evaluation is impeded by the absence of ground-truth attribution on real data. We propose AGOP-IxG, a fast per-sample attribution method for tabular classifiers that pre-multiplies the per-sample gradient by a top-$K$ rank-truncated Average Gradient Outer Product matrix, and"},"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":"2605.15700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T07:45:35Z","cross_cats_sorted":[],"title_canon_sha256":"1195a194a95dd15722a9bc73bd04207a31b0a8a5ad8f6c9e0b524b218ac06ca8","abstract_canon_sha256":"90b0d574bb33aed63653ac9e9b8ce4604215bff55eafc1300e783db309ec00e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:13.212900Z","signature_b64":"hOOIokdZWV0QJ6llCdpUwKHfZIT/X+F0kpXSfhcIV/Vv9Ia8Hn9yCJ3iR1NiA6+eDehdYh+7OYwqPKj+JA82Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cb3c8f7b107c4e073235395b31876c49cd010759a6052b8f2896f6ae9d1f342","last_reissued_at":"2026-05-20T00:01:13.212279Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:13.212279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AGOP-IxG: A Gradient Covariance Filter for Local Feature Attribution on Tabular Data, with a Controlled Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Raj Kiran Gupta Katakam","submitted_at":"2026-05-15T07:45:35Z","abstract_excerpt":"Automated machine learning pipelines increasingly produce models whose predictions must be explained to end users, auditors, and downstream decision systems. The most widely used feature attribution methods (SHAP, Integrated Gradients, LIME) are typically chosen by convention rather than measured fidelity, because rigorous evaluation is impeded by the absence of ground-truth attribution on real data. We propose AGOP-IxG, a fast per-sample attribution method for tabular classifiers that pre-multiplies the per-sample gradient by a top-$K$ rank-truncated Average Gradient Outer Product matrix, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15700","kind":"arxiv","version":1},"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/2605.15700/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:27.256218Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.033644Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7a60d5bed8ff2d291f864a746a45b3e68d32163f1c8ac5bea39df9c3228b802c"},"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":"2605.15700","created_at":"2026-05-20T00:01:13.212386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15700v1","created_at":"2026-05-20T00:01:13.212386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15700","created_at":"2026-05-20T00:01:13.212386+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSZ4R55RA7CO","created_at":"2026-05-20T00:01:13.212386+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSZ4R55RA7COA4ZD","created_at":"2026-05-20T00:01:13.212386+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSZ4R55R","created_at":"2026-05-20T00:01:13.212386+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/FSZ4R55RA7COA4ZDKOK3GGDWYS","json":"https://pith.science/pith/FSZ4R55RA7COA4ZDKOK3GGDWYS.json","graph_json":"https://pith.science/api/pith-number/FSZ4R55RA7COA4ZDKOK3GGDWYS/graph.json","events_json":"https://pith.science/api/pith-number/FSZ4R55RA7COA4ZDKOK3GGDWYS/events.json","paper":"https://pith.science/paper/FSZ4R55R"},"agent_actions":{"view_html":"https://pith.science/pith/FSZ4R55RA7COA4ZDKOK3GGDWYS","download_json":"https://pith.science/pith/FSZ4R55RA7COA4ZDKOK3GGDWYS.json","view_paper":"https://pith.science/paper/FSZ4R55R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15700&json=true","fetch_graph":"https://pith.science/api/pith-number/FSZ4R55RA7COA4ZDKOK3GGDWYS/graph.json","fetch_events":"https://pith.science/api/pith-number/FSZ4R55RA7COA4ZDKOK3GGDWYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSZ4R55RA7COA4ZDKOK3GGDWYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSZ4R55RA7COA4ZDKOK3GGDWYS/action/storage_attestation","attest_author":"https://pith.science/pith/FSZ4R55RA7COA4ZDKOK3GGDWYS/action/author_attestation","sign_citation":"https://pith.science/pith/FSZ4R55RA7COA4ZDKOK3GGDWYS/action/citation_signature","submit_replication":"https://pith.science/pith/FSZ4R55RA7COA4ZDKOK3GGDWYS/action/replication_record"}},"created_at":"2026-05-20T00:01:13.212386+00:00","updated_at":"2026-05-20T00:01:13.212386+00:00"}