{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4ECPA3GRBU4DG45XUV7X457ASF","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":"86a7319b655a801dfaf47ec1b93e13ea55efba5ec8e1f0c9ae49c80ea1a77353","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T13:49:45Z","title_canon_sha256":"35a85cdc6f4ed702bba8abf14a88277920fc6dfcc77bf9f02dc75cbfbea6116a"},"schema_version":"1.0","source":{"id":"2411.16387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16387","created_at":"2026-07-05T09:40:08Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16387v1","created_at":"2026-07-05T09:40:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16387","created_at":"2026-07-05T09:40:08Z"},{"alias_kind":"pith_short_12","alias_value":"4ECPA3GRBU4D","created_at":"2026-07-05T09:40:08Z"},{"alias_kind":"pith_short_16","alias_value":"4ECPA3GRBU4DG45X","created_at":"2026-07-05T09:40:08Z"},{"alias_kind":"pith_short_8","alias_value":"4ECPA3GR","created_at":"2026-07-05T09:40:08Z"}],"graph_snapshots":[{"event_id":"sha256:f4abc00d2b180db22b87767e5c595c05023b67ab5a6026c8d58dc94aa69b9d45","target":"graph","created_at":"2026-07-05T09:40:08Z","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/2411.16387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The quality and size of a pretraining dataset significantly influence the performance of large language models (LLMs). While there have been numerous efforts in the curation of such a dataset for English users, there is a relative lack of similar initiatives for Traditional Chinese. Building upon this foundation of FineWeb, we introduce FineWeb-zhtw, a dataset tailored specifically for Traditional Chinese users. We came up with multiple stages of meticulously designed filters to cater to the linguistic difference between English and Traditional Chinese, to ensure comprehensiveness and quality.","authors_text":"Chan-Jan Hsu, Cheng-Wei Lin, Chia-Chen Kuo, Chuan-Lin Lai, Chung-Wei Chung, Da-shan Shiu, Kai-Xin Guan, Ming-Jen Wang, Wan-Hsuan Hsieh","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T13:49:45Z","title":"FineWeb-zhtw: Scalable Curation of Traditional Chinese Text Data from the Web"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16387","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":"sha256:7dba10fcaa2faba609699e3b61ea490a4f12e482cb691d3668545ce05373829d","target":"record","created_at":"2026-07-05T09:40:08Z","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":"86a7319b655a801dfaf47ec1b93e13ea55efba5ec8e1f0c9ae49c80ea1a77353","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T13:49:45Z","title_canon_sha256":"35a85cdc6f4ed702bba8abf14a88277920fc6dfcc77bf9f02dc75cbfbea6116a"},"schema_version":"1.0","source":{"id":"2411.16387","kind":"arxiv","version":1}},"canonical_sha256":"e104f06cd10d383373b7a57f7e77e0914e05e211569666cb288ac557e5739373","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e104f06cd10d383373b7a57f7e77e0914e05e211569666cb288ac557e5739373","first_computed_at":"2026-07-05T09:40:08.528363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:08.528363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aJpSB1xfXo1vKOAFaVMfEYrzbTeN2/oF6X1/fV0/CUYBV1TsYTxupY2R2qjAwNrhPeYrz4WXxr0Odm1QETkADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:08.528705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dba10fcaa2faba609699e3b61ea490a4f12e482cb691d3668545ce05373829d","sha256:f4abc00d2b180db22b87767e5c595c05023b67ab5a6026c8d58dc94aa69b9d45"],"state_sha256":"fcdf3b828379a6f563e9faa1c566a903265d48307c20ca0e0087bb02fd6af232"}