{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WKIITVDMQB333B4E654MO2KZ2J","short_pith_number":"pith:WKIITVDM","schema_version":"1.0","canonical_sha256":"b29089d46c8077bd8784f778c76959d2443f18c503654e731e4f5c138a3df35a","source":{"kind":"arxiv","id":"2510.20372","version":4},"attestation_state":"computed","paper":{"title":"Testing Most Influential Sets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","econ.EM","math.ST","stat.ME","stat.TH"],"primary_cat":"stat.ML","authors_text":"Lucas D. Konrad, Nikolas Kuschnig","submitted_at":"2025-10-23T09:12:29Z","abstract_excerpt":"Small influential data subsets can dramatically impact model conclusions, with a few data points overturning key findings. While recent work identifies these most influential sets, there is no formal way to tell when maximum influence is excessive rather than expected under natural random sampling variation. We address this gap by developing a principled framework for most influential sets. Focusing on linear least-squares, we derive a convenient exact influence formula and identify the extreme value distributions of maximal influence - the heavy-tailed Fr\\'echet for constant-size sets and hea"},"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":"2510.20372","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-10-23T09:12:29Z","cross_cats_sorted":["cs.LG","econ.EM","math.ST","stat.ME","stat.TH"],"title_canon_sha256":"b01d5df508b20cc63b9d395401efea0b4f5f99ebae42e9127a668183546ce703","abstract_canon_sha256":"c916e84b8447eed5d9e35ce2308507aa541994a3e53bdadd9c5a1980785131dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:45.954645Z","signature_b64":"YzmLjWASZNyb7nzy4HHAo6QHzN14ZMiLtbH1hHWJiwhAmMmA6j31g6pH4tUIXqPhzA34r+b/PCtJOMn9ZqdVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b29089d46c8077bd8784f778c76959d2443f18c503654e731e4f5c138a3df35a","last_reissued_at":"2026-06-03T01:05:45.954181Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:45.954181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Testing Most Influential Sets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","econ.EM","math.ST","stat.ME","stat.TH"],"primary_cat":"stat.ML","authors_text":"Lucas D. Konrad, Nikolas Kuschnig","submitted_at":"2025-10-23T09:12:29Z","abstract_excerpt":"Small influential data subsets can dramatically impact model conclusions, with a few data points overturning key findings. While recent work identifies these most influential sets, there is no formal way to tell when maximum influence is excessive rather than expected under natural random sampling variation. We address this gap by developing a principled framework for most influential sets. Focusing on linear least-squares, we derive a convenient exact influence formula and identify the extreme value distributions of maximal influence - the heavy-tailed Fr\\'echet for constant-size sets and hea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.20372","kind":"arxiv","version":4},"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/2510.20372/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":"2510.20372","created_at":"2026-06-03T01:05:45.954241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.20372v4","created_at":"2026-06-03T01:05:45.954241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.20372","created_at":"2026-06-03T01:05:45.954241+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKIITVDMQB33","created_at":"2026-06-03T01:05:45.954241+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKIITVDMQB333B4E","created_at":"2026-06-03T01:05:45.954241+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKIITVDM","created_at":"2026-06-03T01:05:45.954241+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/WKIITVDMQB333B4E654MO2KZ2J","json":"https://pith.science/pith/WKIITVDMQB333B4E654MO2KZ2J.json","graph_json":"https://pith.science/api/pith-number/WKIITVDMQB333B4E654MO2KZ2J/graph.json","events_json":"https://pith.science/api/pith-number/WKIITVDMQB333B4E654MO2KZ2J/events.json","paper":"https://pith.science/paper/WKIITVDM"},"agent_actions":{"view_html":"https://pith.science/pith/WKIITVDMQB333B4E654MO2KZ2J","download_json":"https://pith.science/pith/WKIITVDMQB333B4E654MO2KZ2J.json","view_paper":"https://pith.science/paper/WKIITVDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.20372&json=true","fetch_graph":"https://pith.science/api/pith-number/WKIITVDMQB333B4E654MO2KZ2J/graph.json","fetch_events":"https://pith.science/api/pith-number/WKIITVDMQB333B4E654MO2KZ2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKIITVDMQB333B4E654MO2KZ2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKIITVDMQB333B4E654MO2KZ2J/action/storage_attestation","attest_author":"https://pith.science/pith/WKIITVDMQB333B4E654MO2KZ2J/action/author_attestation","sign_citation":"https://pith.science/pith/WKIITVDMQB333B4E654MO2KZ2J/action/citation_signature","submit_replication":"https://pith.science/pith/WKIITVDMQB333B4E654MO2KZ2J/action/replication_record"}},"created_at":"2026-06-03T01:05:45.954241+00:00","updated_at":"2026-06-03T01:05:45.954241+00:00"}