{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EQOELHDY3SSTAEQ5GOM4RUDVK5","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":"f3c601b2afd8cf3596542573e096d52c6984d93c815960f9a80fe4ef0b885fb3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T07:50:07Z","title_canon_sha256":"ae2e133690522f7154acbe2a3c219005e92051b9da76282bc6736c74e37a1898"},"schema_version":"1.0","source":{"id":"2410.18505","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18505","created_at":"2026-07-05T09:25:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18505v2","created_at":"2026-07-05T09:25:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18505","created_at":"2026-07-05T09:25:49Z"},{"alias_kind":"pith_short_12","alias_value":"EQOELHDY3SST","created_at":"2026-07-05T09:25:49Z"},{"alias_kind":"pith_short_16","alias_value":"EQOELHDY3SSTAEQ5","created_at":"2026-07-05T09:25:49Z"},{"alias_kind":"pith_short_8","alias_value":"EQOELHDY","created_at":"2026-07-05T09:25:49Z"}],"graph_snapshots":[{"event_id":"sha256:db99f7b190649fed1946c0b44e72229c32e6da4762a90abc54a75b25f5906b46","target":"graph","created_at":"2026-07-05T09:25:49Z","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/2410.18505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CCI3.0-HQ (https://huggingface.co/datasets/BAAI/CCI3-HQ), a high-quality 500GB subset of the Chinese Corpora Internet 3.0 (CCI3.0)(https://huggingface.co/datasets/BAAI/CCI3-Data), developed using a novel two-stage hybrid filtering pipeline that significantly enhances data quality. To evaluate its effectiveness, we trained a 0.5B parameter model from scratch on 100B tokens across various datasets, achieving superior performance on 10 benchmarks in a zero-shot setting compared to CCI3.0, SkyPile, and WanjuanV1. The high-quality filtering process effectively distills the capabilities o","authors_text":"Bo-Wen Zhang, Chengwei Wu, Guang Liu, Hanyu Zhao, Jijie Li, Liangdong Wang, Quanyue Ma, Shuhao Gu, Tengfei Pan, Xiaofeng Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T07:50:07Z","title":"CCI3.0-HQ: a large-scale Chinese dataset of high quality designed for pre-training large language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18505","kind":"arxiv","version":2},"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:fbaded4daad8796f79c3b3a2a9a93c98498215f39232cf7ec92543ec0657065f","target":"record","created_at":"2026-07-05T09:25:49Z","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":"f3c601b2afd8cf3596542573e096d52c6984d93c815960f9a80fe4ef0b885fb3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T07:50:07Z","title_canon_sha256":"ae2e133690522f7154acbe2a3c219005e92051b9da76282bc6736c74e37a1898"},"schema_version":"1.0","source":{"id":"2410.18505","kind":"arxiv","version":2}},"canonical_sha256":"241c459c78dca530121d3399c8d07557478674d599a5aefec837a784c0c1e829","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"241c459c78dca530121d3399c8d07557478674d599a5aefec837a784c0c1e829","first_computed_at":"2026-07-05T09:25:49.141833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:49.141833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"03pIK94dfe5eajbdF8RZdcOe7OEszqPGWohZEp5zUeO1nzb9BOEjTw1LHTfqKbw0iOy/B7Ly6mN5ymreasoICw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:49.142267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18505","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbaded4daad8796f79c3b3a2a9a93c98498215f39232cf7ec92543ec0657065f","sha256:db99f7b190649fed1946c0b44e72229c32e6da4762a90abc54a75b25f5906b46"],"state_sha256":"18bb2e47029e8643ef71bb867e17251ad24bc1a1a0d22fd646ea30c5d1cb560c"}