{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:22ZFAPGX2GFCXSC5SQR2I7AQIS","short_pith_number":"pith:22ZFAPGX","schema_version":"1.0","canonical_sha256":"d6b2503cd7d18a2bc85d9423a47c1044beb565fe342f4524a97c76b5584e8e1c","source":{"kind":"arxiv","id":"2412.01335","version":1},"attestation_state":"computed","paper":{"title":"A Versatile Influence Function for Data Attribution with Non-Decomposable Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiaqi W. Ma, Junwei Deng, Weijing Tang","submitted_at":"2024-12-02T09:59:01Z","abstract_excerpt":"Influence function, a technique rooted in robust statistics, has been adapted in modern machine learning for a novel application: data attribution -- quantifying how individual training data points affect a model's predictions. However, the common derivation of influence functions in the data attribution literature is limited to loss functions that can be decomposed into a sum of individual data point losses, with the most prominent examples known as M-estimators. This restricts the application of influence functions to more complex learning objectives, which we refer to as non-decomposable lo"},"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":"2412.01335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T09:59:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4033db08c7a52c4290bcd477a6c2bd778647ffd253516f7763bf91093065eb06","abstract_canon_sha256":"e6a5249a34c31984adebca50a3d77b8853b3f271e7464ef710abc9bb29174e91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:58.322267Z","signature_b64":"Rc8tSbRuBuB6qoZXisNsjj6aPPq6N1+gtdWV34QKGnwfD7MkrQZvoOGZBJf388msLOGYU7Z9I0nuEv1uVPeoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6b2503cd7d18a2bc85d9423a47c1044beb565fe342f4524a97c76b5584e8e1c","last_reissued_at":"2026-07-05T09:42:58.321723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:58.321723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Versatile Influence Function for Data Attribution with Non-Decomposable Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiaqi W. Ma, Junwei Deng, Weijing Tang","submitted_at":"2024-12-02T09:59:01Z","abstract_excerpt":"Influence function, a technique rooted in robust statistics, has been adapted in modern machine learning for a novel application: data attribution -- quantifying how individual training data points affect a model's predictions. However, the common derivation of influence functions in the data attribution literature is limited to loss functions that can be decomposed into a sum of individual data point losses, with the most prominent examples known as M-estimators. This restricts the application of influence functions to more complex learning objectives, which we refer to as non-decomposable lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01335","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/2412.01335/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":"2412.01335","created_at":"2026-07-05T09:42:58.321791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01335v1","created_at":"2026-07-05T09:42:58.321791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01335","created_at":"2026-07-05T09:42:58.321791+00:00"},{"alias_kind":"pith_short_12","alias_value":"22ZFAPGX2GFC","created_at":"2026-07-05T09:42:58.321791+00:00"},{"alias_kind":"pith_short_16","alias_value":"22ZFAPGX2GFCXSC5","created_at":"2026-07-05T09:42:58.321791+00:00"},{"alias_kind":"pith_short_8","alias_value":"22ZFAPGX","created_at":"2026-07-05T09:42:58.321791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15675","citing_title":"Interaction-Aware Influence Functions for Group Attribution","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/22ZFAPGX2GFCXSC5SQR2I7AQIS","json":"https://pith.science/pith/22ZFAPGX2GFCXSC5SQR2I7AQIS.json","graph_json":"https://pith.science/api/pith-number/22ZFAPGX2GFCXSC5SQR2I7AQIS/graph.json","events_json":"https://pith.science/api/pith-number/22ZFAPGX2GFCXSC5SQR2I7AQIS/events.json","paper":"https://pith.science/paper/22ZFAPGX"},"agent_actions":{"view_html":"https://pith.science/pith/22ZFAPGX2GFCXSC5SQR2I7AQIS","download_json":"https://pith.science/pith/22ZFAPGX2GFCXSC5SQR2I7AQIS.json","view_paper":"https://pith.science/paper/22ZFAPGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01335&json=true","fetch_graph":"https://pith.science/api/pith-number/22ZFAPGX2GFCXSC5SQR2I7AQIS/graph.json","fetch_events":"https://pith.science/api/pith-number/22ZFAPGX2GFCXSC5SQR2I7AQIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22ZFAPGX2GFCXSC5SQR2I7AQIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22ZFAPGX2GFCXSC5SQR2I7AQIS/action/storage_attestation","attest_author":"https://pith.science/pith/22ZFAPGX2GFCXSC5SQR2I7AQIS/action/author_attestation","sign_citation":"https://pith.science/pith/22ZFAPGX2GFCXSC5SQR2I7AQIS/action/citation_signature","submit_replication":"https://pith.science/pith/22ZFAPGX2GFCXSC5SQR2I7AQIS/action/replication_record"}},"created_at":"2026-07-05T09:42:58.321791+00:00","updated_at":"2026-07-05T09:42:58.321791+00:00"}