{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O32QDTO7IA4IZZGK4LCK27FLBP","short_pith_number":"pith:O32QDTO7","schema_version":"1.0","canonical_sha256":"76f501cddf40388ce4cae2c4ad7cab0bfd12187afb47dc8728674f06e28da1f5","source":{"kind":"arxiv","id":"2507.11895","version":1},"attestation_state":"computed","paper":{"title":"Newfluence: Boosting Model interpretability and Understanding in High Dimensions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Arian Maleki, Arnab Auddy, Haolin Zou, Kamiar Rahnama Rad, Yongchan Kwon","submitted_at":"2025-07-16T04:22:16Z","abstract_excerpt":"The increasing complexity of machine learning (ML) and artificial intelligence (AI) models has created a pressing need for tools that help scientists, engineers, and policymakers interpret and refine model decisions and predictions. Influence functions, originating from robust statistics, have emerged as a popular approach for this purpose.\n  However, the heuristic foundations of influence functions rely on low-dimensional assumptions where the number of parameters $p$ is much smaller than the number of observations $n$. In contrast, modern AI models often operate in high-dimensional regimes w"},"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":"2507.11895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-16T04:22:16Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"6a310670364e8d134a85c5264137b5a592788a7a5c0452c133f2377c1742f28d","abstract_canon_sha256":"3b0b302f0d7adf08af485333cfca60186cf1f520ddf7001fa12c02d46dc0bb72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:52.988150Z","signature_b64":"bkN59qCJPOdvaliZi8aWjL8smCfr/vuKPYTyFZbiI2ojFYpRSA4ZuFSSt3G4z3Brr1uRNWn106y5DhS4RZOuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76f501cddf40388ce4cae2c4ad7cab0bfd12187afb47dc8728674f06e28da1f5","last_reissued_at":"2026-07-05T11:37:52.987700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:52.987700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Newfluence: Boosting Model interpretability and Understanding in High Dimensions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Arian Maleki, Arnab Auddy, Haolin Zou, Kamiar Rahnama Rad, Yongchan Kwon","submitted_at":"2025-07-16T04:22:16Z","abstract_excerpt":"The increasing complexity of machine learning (ML) and artificial intelligence (AI) models has created a pressing need for tools that help scientists, engineers, and policymakers interpret and refine model decisions and predictions. Influence functions, originating from robust statistics, have emerged as a popular approach for this purpose.\n  However, the heuristic foundations of influence functions rely on low-dimensional assumptions where the number of parameters $p$ is much smaller than the number of observations $n$. In contrast, modern AI models often operate in high-dimensional regimes w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11895","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/2507.11895/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":"2507.11895","created_at":"2026-07-05T11:37:52.987774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.11895v1","created_at":"2026-07-05T11:37:52.987774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11895","created_at":"2026-07-05T11:37:52.987774+00:00"},{"alias_kind":"pith_short_12","alias_value":"O32QDTO7IA4I","created_at":"2026-07-05T11:37:52.987774+00:00"},{"alias_kind":"pith_short_16","alias_value":"O32QDTO7IA4IZZGK","created_at":"2026-07-05T11:37:52.987774+00:00"},{"alias_kind":"pith_short_8","alias_value":"O32QDTO7","created_at":"2026-07-05T11:37:52.987774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.12572","citing_title":"On the Accuracy of Newton Step and Influence Function Data Attributions","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O32QDTO7IA4IZZGK4LCK27FLBP","json":"https://pith.science/pith/O32QDTO7IA4IZZGK4LCK27FLBP.json","graph_json":"https://pith.science/api/pith-number/O32QDTO7IA4IZZGK4LCK27FLBP/graph.json","events_json":"https://pith.science/api/pith-number/O32QDTO7IA4IZZGK4LCK27FLBP/events.json","paper":"https://pith.science/paper/O32QDTO7"},"agent_actions":{"view_html":"https://pith.science/pith/O32QDTO7IA4IZZGK4LCK27FLBP","download_json":"https://pith.science/pith/O32QDTO7IA4IZZGK4LCK27FLBP.json","view_paper":"https://pith.science/paper/O32QDTO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.11895&json=true","fetch_graph":"https://pith.science/api/pith-number/O32QDTO7IA4IZZGK4LCK27FLBP/graph.json","fetch_events":"https://pith.science/api/pith-number/O32QDTO7IA4IZZGK4LCK27FLBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O32QDTO7IA4IZZGK4LCK27FLBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O32QDTO7IA4IZZGK4LCK27FLBP/action/storage_attestation","attest_author":"https://pith.science/pith/O32QDTO7IA4IZZGK4LCK27FLBP/action/author_attestation","sign_citation":"https://pith.science/pith/O32QDTO7IA4IZZGK4LCK27FLBP/action/citation_signature","submit_replication":"https://pith.science/pith/O32QDTO7IA4IZZGK4LCK27FLBP/action/replication_record"}},"created_at":"2026-07-05T11:37:52.987774+00:00","updated_at":"2026-07-05T11:37:52.987774+00:00"}