{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SLYBZVVX2ME4DM76CPAD2B2NIZ","short_pith_number":"pith:SLYBZVVX","schema_version":"1.0","canonical_sha256":"92f01cd6b7d309c1b3fe13c03d074d4672e2455a9564d2700df18ebe5211efe6","source":{"kind":"arxiv","id":"2107.07436","version":3},"attestation_state":"computed","paper":{"title":"FastSHAP: Real-Time Shapley Value Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ian Covert, Mukund Sudarshan, Neil Jethani, Rajesh Ranganath, Su-In Lee","submitted_at":"2021-07-15T16:34:45Z","abstract_excerpt":"Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations. We introduce FastSHAP, a method for estimating Shapley values in a single forward pass using a learned explainer model. FastSHAP amortizes the cost of explaining many inputs via a learning approach inspired by the Shapley value's weighted least squares characterization, and it can be trained using standard stochastic gradient optimization. We compare FastSHAP to existing estimation approaches, revealing that it generates high-quality explanations with orders"},"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":"2107.07436","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-07-15T16:34:45Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"31449c3d08a6497bdbfd89ebe0bcb063103ef9d3c9d3e7ead6b01617e34978f5","abstract_canon_sha256":"1723dddf168088f6fbdaf3d158c5d6d863096a32c1f51b3dded70f2247878235"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:39.514246Z","signature_b64":"x16wS/P51hs83nb25WWXbfh6UDCPU13RQc+VwvBB5EQqvZ8miWxVDR6aj3mEwSnKHSmFfswQU/hjXWG3H5hwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92f01cd6b7d309c1b3fe13c03d074d4672e2455a9564d2700df18ebe5211efe6","last_reissued_at":"2026-07-05T04:07:39.513728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:39.513728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FastSHAP: Real-Time Shapley Value Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ian Covert, Mukund Sudarshan, Neil Jethani, Rajesh Ranganath, Su-In Lee","submitted_at":"2021-07-15T16:34:45Z","abstract_excerpt":"Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations. We introduce FastSHAP, a method for estimating Shapley values in a single forward pass using a learned explainer model. FastSHAP amortizes the cost of explaining many inputs via a learning approach inspired by the Shapley value's weighted least squares characterization, and it can be trained using standard stochastic gradient optimization. We compare FastSHAP to existing estimation approaches, revealing that it generates high-quality explanations with orders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07436","kind":"arxiv","version":3},"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/2107.07436/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":"2107.07436","created_at":"2026-07-05T04:07:39.513795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.07436v3","created_at":"2026-07-05T04:07:39.513795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07436","created_at":"2026-07-05T04:07:39.513795+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLYBZVVX2ME4","created_at":"2026-07-05T04:07:39.513795+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLYBZVVX2ME4DM76","created_at":"2026-07-05T04:07:39.513795+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLYBZVVX","created_at":"2026-07-05T04:07:39.513795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28065","citing_title":"OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2502.00270","citing_title":"DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SLYBZVVX2ME4DM76CPAD2B2NIZ","json":"https://pith.science/pith/SLYBZVVX2ME4DM76CPAD2B2NIZ.json","graph_json":"https://pith.science/api/pith-number/SLYBZVVX2ME4DM76CPAD2B2NIZ/graph.json","events_json":"https://pith.science/api/pith-number/SLYBZVVX2ME4DM76CPAD2B2NIZ/events.json","paper":"https://pith.science/paper/SLYBZVVX"},"agent_actions":{"view_html":"https://pith.science/pith/SLYBZVVX2ME4DM76CPAD2B2NIZ","download_json":"https://pith.science/pith/SLYBZVVX2ME4DM76CPAD2B2NIZ.json","view_paper":"https://pith.science/paper/SLYBZVVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.07436&json=true","fetch_graph":"https://pith.science/api/pith-number/SLYBZVVX2ME4DM76CPAD2B2NIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SLYBZVVX2ME4DM76CPAD2B2NIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLYBZVVX2ME4DM76CPAD2B2NIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLYBZVVX2ME4DM76CPAD2B2NIZ/action/storage_attestation","attest_author":"https://pith.science/pith/SLYBZVVX2ME4DM76CPAD2B2NIZ/action/author_attestation","sign_citation":"https://pith.science/pith/SLYBZVVX2ME4DM76CPAD2B2NIZ/action/citation_signature","submit_replication":"https://pith.science/pith/SLYBZVVX2ME4DM76CPAD2B2NIZ/action/replication_record"}},"created_at":"2026-07-05T04:07:39.513795+00:00","updated_at":"2026-07-05T04:07:39.513795+00:00"}