{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3IEOYD5GW4GCY7MPYVF5YJF3PM","short_pith_number":"pith:3IEOYD5G","schema_version":"1.0","canonical_sha256":"da08ec0fa6b70c2c7d8fc54bdc24bb7b00eda093e8be57c5c5e9a74224d73eaa","source":{"kind":"arxiv","id":"2506.20573","version":4},"attestation_state":"computed","paper":{"title":"LARP: Learner-Agnostic Robust Data Prefiltering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dimitar I. Dimitrov, Kristian Minchev, Nikola Konstantinov","submitted_at":"2025-06-25T16:07:59Z","abstract_excerpt":"Public datasets, crucial for modern machine learning and statistical inference, often contain low-quality or contaminated samples that can harm model performance. This creates a need for principled prefiltering procedures that a data provider can apply to protect the accuracy of a range of potential downstream statistical and learning procedures simultaneously. In this work, we formalize and analyze Learner-Agnostic Robust data Prefiltering (LARP), the problem of designing prefiltering procedures with guarantees on the worst-case loss over a pre-specified set of learners. We establish the feas"},"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":"2506.20573","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-25T16:07:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"581ff50e054a60dd2057c6b35ff64b141ab780c1604c459dc4898a35f35f4d8a","abstract_canon_sha256":"2253e0e108da17be1cca0109779d17a923dbdece7d1f71cb82281662956e9006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:04.657637Z","signature_b64":"+pfOsqtntmytKUwarbUe8ersfmuX4HDi6STgGr0/8NovovIkYViAEpurAySJeTL6743d5WMDw8wz1PrzafyPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da08ec0fa6b70c2c7d8fc54bdc24bb7b00eda093e8be57c5c5e9a74224d73eaa","last_reissued_at":"2026-06-09T02:07:04.656601Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:04.656601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LARP: Learner-Agnostic Robust Data Prefiltering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dimitar I. Dimitrov, Kristian Minchev, Nikola Konstantinov","submitted_at":"2025-06-25T16:07:59Z","abstract_excerpt":"Public datasets, crucial for modern machine learning and statistical inference, often contain low-quality or contaminated samples that can harm model performance. This creates a need for principled prefiltering procedures that a data provider can apply to protect the accuracy of a range of potential downstream statistical and learning procedures simultaneously. In this work, we formalize and analyze Learner-Agnostic Robust data Prefiltering (LARP), the problem of designing prefiltering procedures with guarantees on the worst-case loss over a pre-specified set of learners. We establish the feas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20573","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/2506.20573/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":"2506.20573","created_at":"2026-06-09T02:07:04.656749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20573v4","created_at":"2026-06-09T02:07:04.656749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20573","created_at":"2026-06-09T02:07:04.656749+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IEOYD5GW4GC","created_at":"2026-06-09T02:07:04.656749+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IEOYD5GW4GCY7MP","created_at":"2026-06-09T02:07:04.656749+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IEOYD5G","created_at":"2026-06-09T02:07:04.656749+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/3IEOYD5GW4GCY7MPYVF5YJF3PM","json":"https://pith.science/pith/3IEOYD5GW4GCY7MPYVF5YJF3PM.json","graph_json":"https://pith.science/api/pith-number/3IEOYD5GW4GCY7MPYVF5YJF3PM/graph.json","events_json":"https://pith.science/api/pith-number/3IEOYD5GW4GCY7MPYVF5YJF3PM/events.json","paper":"https://pith.science/paper/3IEOYD5G"},"agent_actions":{"view_html":"https://pith.science/pith/3IEOYD5GW4GCY7MPYVF5YJF3PM","download_json":"https://pith.science/pith/3IEOYD5GW4GCY7MPYVF5YJF3PM.json","view_paper":"https://pith.science/paper/3IEOYD5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20573&json=true","fetch_graph":"https://pith.science/api/pith-number/3IEOYD5GW4GCY7MPYVF5YJF3PM/graph.json","fetch_events":"https://pith.science/api/pith-number/3IEOYD5GW4GCY7MPYVF5YJF3PM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IEOYD5GW4GCY7MPYVF5YJF3PM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IEOYD5GW4GCY7MPYVF5YJF3PM/action/storage_attestation","attest_author":"https://pith.science/pith/3IEOYD5GW4GCY7MPYVF5YJF3PM/action/author_attestation","sign_citation":"https://pith.science/pith/3IEOYD5GW4GCY7MPYVF5YJF3PM/action/citation_signature","submit_replication":"https://pith.science/pith/3IEOYD5GW4GCY7MPYVF5YJF3PM/action/replication_record"}},"created_at":"2026-06-09T02:07:04.656749+00:00","updated_at":"2026-06-09T02:07:04.656749+00:00"}