{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3IEOYD5GW4GCY7MPYVF5YJF3PM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2253e0e108da17be1cca0109779d17a923dbdece7d1f71cb82281662956e9006","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-25T16:07:59Z","title_canon_sha256":"581ff50e054a60dd2057c6b35ff64b141ab780c1604c459dc4898a35f35f4d8a"},"schema_version":"1.0","source":{"id":"2506.20573","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20573","created_at":"2026-06-09T02:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20573v4","created_at":"2026-06-09T02:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20573","created_at":"2026-06-09T02:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"3IEOYD5GW4GC","created_at":"2026-06-09T02:07:04Z"},{"alias_kind":"pith_short_16","alias_value":"3IEOYD5GW4GCY7MP","created_at":"2026-06-09T02:07:04Z"},{"alias_kind":"pith_short_8","alias_value":"3IEOYD5G","created_at":"2026-06-09T02:07:04Z"}],"graph_snapshots":[{"event_id":"sha256:6e3d9be94cab186687ff316c44323e83e4d66ee13b4b49d5a06d279a298997ce","target":"graph","created_at":"2026-06-09T02:07:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.20573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dimitar I. Dimitrov, Kristian Minchev, Nikola Konstantinov","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-25T16:07:59Z","title":"LARP: Learner-Agnostic Robust Data Prefiltering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20573","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e3c42e9accd6eb393fab349c1dd57a2f27bc0dac6503b1ad55168977fbaf95a5","target":"record","created_at":"2026-06-09T02:07:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2253e0e108da17be1cca0109779d17a923dbdece7d1f71cb82281662956e9006","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-25T16:07:59Z","title_canon_sha256":"581ff50e054a60dd2057c6b35ff64b141ab780c1604c459dc4898a35f35f4d8a"},"schema_version":"1.0","source":{"id":"2506.20573","kind":"arxiv","version":4}},"canonical_sha256":"da08ec0fa6b70c2c7d8fc54bdc24bb7b00eda093e8be57c5c5e9a74224d73eaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da08ec0fa6b70c2c7d8fc54bdc24bb7b00eda093e8be57c5c5e9a74224d73eaa","first_computed_at":"2026-06-09T02:07:04.656601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:04.656601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+pfOsqtntmytKUwarbUe8ersfmuX4HDi6STgGr0/8NovovIkYViAEpurAySJeTL6743d5WMDw8wz1PrzafyPDg==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:04.657637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20573","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3c42e9accd6eb393fab349c1dd57a2f27bc0dac6503b1ad55168977fbaf95a5","sha256:6e3d9be94cab186687ff316c44323e83e4d66ee13b4b49d5a06d279a298997ce"],"state_sha256":"8a4407e26950b31c8d9fc78bcdcc076cbce246bb7f06ecef5dd0e9a510f0e667"}