{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RF3MEPHHGNGCLCQ7FD25FPEHP2","short_pith_number":"pith:RF3MEPHH","schema_version":"1.0","canonical_sha256":"8976c23ce7334c258a1f28f5d2bc877e8fde18fc9181e1b1f736d3ef86ea37a1","source":{"kind":"arxiv","id":"1911.00418","version":2},"attestation_state":"computed","paper":{"title":"On Second-Order Group Influence Functions for Black-Box Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Samyadeep Basu, Soheil Feizi, Xuchen You","submitted_at":"2019-11-01T15:14:06Z","abstract_excerpt":"With the rapid adoption of machine learning systems in sensitive applications, there is an increasing need to make black-box models explainable. Often we want to identify an influential group of training samples in a particular test prediction for a given machine learning model. Existing influence functions tackle this problem by using first-order approximations of the effect of removing a sample from the training set on model parameters. To compute the influence of a group of training samples (rather than an individual point) in model predictions, the change in optimal model parameters after "},"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":"1911.00418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-01T15:14:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"afd9682d905afcb8da4b6b1f0cb9d8b3d5b71cb71ccd5eaad9f31fe9638877ab","abstract_canon_sha256":"4a5b8a5dc043ac64d4b79da716a30ef5af97743fb1f0109c6eb83cbed594d367"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:41.594457Z","signature_b64":"O83dwSjbWrdQnrKkpDLrlVwScDlN3T7KtbIIK1kTW/BNKT5M2PIERTAwjNfYp0VfbMhOErPZmDgcHJNISjtIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8976c23ce7334c258a1f28f5d2bc877e8fde18fc9181e1b1f736d3ef86ea37a1","last_reissued_at":"2026-07-05T01:16:41.594048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:41.594048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Second-Order Group Influence Functions for Black-Box Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Samyadeep Basu, Soheil Feizi, Xuchen You","submitted_at":"2019-11-01T15:14:06Z","abstract_excerpt":"With the rapid adoption of machine learning systems in sensitive applications, there is an increasing need to make black-box models explainable. Often we want to identify an influential group of training samples in a particular test prediction for a given machine learning model. Existing influence functions tackle this problem by using first-order approximations of the effect of removing a sample from the training set on model parameters. To compute the influence of a group of training samples (rather than an individual point) in model predictions, the change in optimal model parameters after "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00418","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/1911.00418/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":"1911.00418","created_at":"2026-07-05T01:16:41.594106+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.00418v2","created_at":"2026-07-05T01:16:41.594106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00418","created_at":"2026-07-05T01:16:41.594106+00:00"},{"alias_kind":"pith_short_12","alias_value":"RF3MEPHHGNGC","created_at":"2026-07-05T01:16:41.594106+00:00"},{"alias_kind":"pith_short_16","alias_value":"RF3MEPHHGNGCLCQ7","created_at":"2026-07-05T01:16:41.594106+00:00"},{"alias_kind":"pith_short_8","alias_value":"RF3MEPHH","created_at":"2026-07-05T01:16:41.594106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26084","citing_title":"FruitProM-V2: Robust Probabilistic Maturity Estimation and Detection of Fruits and Vegetables","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RF3MEPHHGNGCLCQ7FD25FPEHP2","json":"https://pith.science/pith/RF3MEPHHGNGCLCQ7FD25FPEHP2.json","graph_json":"https://pith.science/api/pith-number/RF3MEPHHGNGCLCQ7FD25FPEHP2/graph.json","events_json":"https://pith.science/api/pith-number/RF3MEPHHGNGCLCQ7FD25FPEHP2/events.json","paper":"https://pith.science/paper/RF3MEPHH"},"agent_actions":{"view_html":"https://pith.science/pith/RF3MEPHHGNGCLCQ7FD25FPEHP2","download_json":"https://pith.science/pith/RF3MEPHHGNGCLCQ7FD25FPEHP2.json","view_paper":"https://pith.science/paper/RF3MEPHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.00418&json=true","fetch_graph":"https://pith.science/api/pith-number/RF3MEPHHGNGCLCQ7FD25FPEHP2/graph.json","fetch_events":"https://pith.science/api/pith-number/RF3MEPHHGNGCLCQ7FD25FPEHP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RF3MEPHHGNGCLCQ7FD25FPEHP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RF3MEPHHGNGCLCQ7FD25FPEHP2/action/storage_attestation","attest_author":"https://pith.science/pith/RF3MEPHHGNGCLCQ7FD25FPEHP2/action/author_attestation","sign_citation":"https://pith.science/pith/RF3MEPHHGNGCLCQ7FD25FPEHP2/action/citation_signature","submit_replication":"https://pith.science/pith/RF3MEPHHGNGCLCQ7FD25FPEHP2/action/replication_record"}},"created_at":"2026-07-05T01:16:41.594106+00:00","updated_at":"2026-07-05T01:16:41.594106+00:00"}