{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VNMF227SBVLGACUY7WCAQORDQW","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":"ebd3c56e2397d37742d6f43511ff4cab21114c1679c1ff00fddd7269b172118a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T08:59:11Z","title_canon_sha256":"39fefcedcd2fff75ba1c8f1d0d7a47228b3bcc49ff23c502e34431ea8db92ac5"},"schema_version":"1.0","source":{"id":"2605.23721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23721","created_at":"2026-05-25T02:02:28Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23721v1","created_at":"2026-05-25T02:02:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23721","created_at":"2026-05-25T02:02:28Z"},{"alias_kind":"pith_short_12","alias_value":"VNMF227SBVLG","created_at":"2026-05-25T02:02:28Z"},{"alias_kind":"pith_short_16","alias_value":"VNMF227SBVLGACUY","created_at":"2026-05-25T02:02:28Z"},{"alias_kind":"pith_short_8","alias_value":"VNMF227S","created_at":"2026-05-25T02:02:28Z"}],"graph_snapshots":[{"event_id":"sha256:2396f6069fcef3128e1eb772cfed4eb792bbcb1301235d7090c23dd69fb79811","target":"graph","created_at":"2026-05-25T02:02:28Z","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/2605.23721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classifier-based Quality Filtering has recently emerged as a fundamental technique in constructing pre-training corpora. The ability to deploy a single model that can replace or supplement a set of heuristics has proven effective across numerous Large Language Models. In this work, we expose a critical vulnerability in this approach by demonstrating how a straightforward Wikipedia-style reformatting operation can substantially alter a model's quality assessment and enable low-quality content to surpass filtering thresholds. Our analysis reveals that the FineWeb-Edu CQF model would reverse its ","authors_text":"Mateusz Klimaszewski, Piotr Andruszkiewicz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T08:59:11Z","title":"Is a Document Educational or Just Wikipedia-Style? -- Pitfalls of Classifier-Based Quality Filtering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23721","kind":"arxiv","version":1},"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:e884ed08b54c1b3c79f74b62d9e4182eca6b1b5f82d091591aec33c9c648abb8","target":"record","created_at":"2026-05-25T02:02:28Z","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":"ebd3c56e2397d37742d6f43511ff4cab21114c1679c1ff00fddd7269b172118a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T08:59:11Z","title_canon_sha256":"39fefcedcd2fff75ba1c8f1d0d7a47228b3bcc49ff23c502e34431ea8db92ac5"},"schema_version":"1.0","source":{"id":"2605.23721","kind":"arxiv","version":1}},"canonical_sha256":"ab585d6bf20d56600a98fd84083a23858d3b84b7d55e746ee36c384b4d3aa9cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab585d6bf20d56600a98fd84083a23858d3b84b7d55e746ee36c384b4d3aa9cf","first_computed_at":"2026-05-25T02:02:28.414923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:28.414923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0VPFHZ1FjqLG68tgFfE7ZsPJa89ohdbn30Q8P4Bo2nY3rHUE1KZhalwNMwddph3gLMHQUpfUqWShns6YXtbqAA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:28.415760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e884ed08b54c1b3c79f74b62d9e4182eca6b1b5f82d091591aec33c9c648abb8","sha256:2396f6069fcef3128e1eb772cfed4eb792bbcb1301235d7090c23dd69fb79811"],"state_sha256":"890aa3c7c120965a00e803f925b17e8fc992df66aa25439855b15772c842644b"}