{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RE53LYEVTM4KVL7XP2TF2UFOEM","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":"b179fe23828c212d1b29e60c232988f1d3ce1a8644594db3b698f6d65521a595","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-15T05:27:56Z","title_canon_sha256":"00c909c6e8fd10133257f766d6ac6934b29213e443091343d6c4ab9b1e2308e3"},"schema_version":"1.0","source":{"id":"2409.09613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09613","created_at":"2026-07-05T09:07:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09613v1","created_at":"2026-07-05T09:07:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09613","created_at":"2026-07-05T09:07:12Z"},{"alias_kind":"pith_short_12","alias_value":"RE53LYEVTM4K","created_at":"2026-07-05T09:07:12Z"},{"alias_kind":"pith_short_16","alias_value":"RE53LYEVTM4KVL7X","created_at":"2026-07-05T09:07:12Z"},{"alias_kind":"pith_short_8","alias_value":"RE53LYEV","created_at":"2026-07-05T09:07:12Z"}],"graph_snapshots":[{"event_id":"sha256:a89181c7edffc19b046e2424b1c6d72b0388485bbe740bde551cb8c17b59c4b6","target":"graph","created_at":"2026-07-05T09:07:12Z","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/2409.09613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the increasing demand for substantial amounts of high-quality data to train large language models (LLMs), efficiently filtering large web corpora has become a critical challenge. For this purpose, KenLM, a lightweight n-gram-based language model that operates on CPUs, is widely used. However, the traditional method of training KenLM utilizes only high-quality data and, consequently, does not explicitly learn the linguistic patterns of low-quality data. To address this issue, we propose an ensemble approach that leverages two contrasting KenLMs: (i) Good KenLM, trained on high-quality data","authors_text":"Chanjun Park, Hyunsoo Ha, Jihoo Kim, Seonghoon Yang, Sukyung Lee, Yungi Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-15T05:27:56Z","title":"Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09613","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":"sha256:3146bb22c399e7ae90d257ee8e40598a75bf9fb7cfa26b5c085fe1cc71434aa1","target":"record","created_at":"2026-07-05T09:07:12Z","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":"b179fe23828c212d1b29e60c232988f1d3ce1a8644594db3b698f6d65521a595","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-15T05:27:56Z","title_canon_sha256":"00c909c6e8fd10133257f766d6ac6934b29213e443091343d6c4ab9b1e2308e3"},"schema_version":"1.0","source":{"id":"2409.09613","kind":"arxiv","version":1}},"canonical_sha256":"893bb5e0959b38aaaff77ea65d50ae23186ad63b076a6811d44a919a5c6f5596","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"893bb5e0959b38aaaff77ea65d50ae23186ad63b076a6811d44a919a5c6f5596","first_computed_at":"2026-07-05T09:07:12.084358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:12.084358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Ctjg2KekjaGK3Ku777rPmu/Su1ob7+NaYqXTSaqF9IA2CgWKhv0rpAx0w4vAD2LQaJ8KhL1qmL6Sr+F77BMAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:12.084842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3146bb22c399e7ae90d257ee8e40598a75bf9fb7cfa26b5c085fe1cc71434aa1","sha256:a89181c7edffc19b046e2424b1c6d72b0388485bbe740bde551cb8c17b59c4b6"],"state_sha256":"62593baddb6328268f40c3b4b44f1aaf7003b576cae0673edda08f9a9170e741"}