{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VEPYSK4KDSCV557W6G4YMORHOD","short_pith_number":"pith:VEPYSK4K","schema_version":"1.0","canonical_sha256":"a91f892b8a1c855ef7f6f1b9863a2770d04d34d3313d48715d342a581729ebff","source":{"kind":"arxiv","id":"2506.07463","version":1},"attestation_state":"computed","paper":{"title":"CCI4.0: A Bilingual Pretraining Dataset for Enhancing Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Feng Liao, Guang Liu, Jiabei Chen, Jijie Li, Liangdong Wang, Yang Yu, Yao Xu, Yonghua Lin, Yu Bai","submitted_at":"2025-06-09T06:14:19Z","abstract_excerpt":"We introduce CCI4.0, a large-scale bilingual pre-training dataset engineered for superior data quality and diverse human-like reasoning trajectory. CCI4.0 occupies roughly $35$ TB of disk space and comprises two sub-datasets: CCI4.0-M2-Base and CCI4.0-M2-CoT. CCI4.0-M2-Base combines a $5.2$ TB carefully curated Chinese web corpus, a $22.5$ TB English subset from Nemotron-CC, and diverse sources from math, wiki, arxiv, and code. Although these data are mostly sourced from well-processed datasets, the quality standards of various domains are dynamic and require extensive expert experience and la"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.07463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T06:14:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"126a76d20f62980edb8b79ac56a3b2d88ec5fc61a90c7ea8f8d65228f527d82f","abstract_canon_sha256":"dcd47d9977114eafd812d1729c8b4e93c92e7a0245f27d1b4bf7861b5de55807"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:27.792641Z","signature_b64":"hKxJcNTZfkPZZuk6DWq/V1WB+OThA9gwAPUQllSc3yTH+u3/uev9XUQDePz6Wo8XGJtAPyVIZ8XxONJtxsVyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a91f892b8a1c855ef7f6f1b9863a2770d04d34d3313d48715d342a581729ebff","last_reissued_at":"2026-07-05T11:18:27.792150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:27.792150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CCI4.0: A Bilingual Pretraining Dataset for Enhancing Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Feng Liao, Guang Liu, Jiabei Chen, Jijie Li, Liangdong Wang, Yang Yu, Yao Xu, Yonghua Lin, Yu Bai","submitted_at":"2025-06-09T06:14:19Z","abstract_excerpt":"We introduce CCI4.0, a large-scale bilingual pre-training dataset engineered for superior data quality and diverse human-like reasoning trajectory. CCI4.0 occupies roughly $35$ TB of disk space and comprises two sub-datasets: CCI4.0-M2-Base and CCI4.0-M2-CoT. CCI4.0-M2-Base combines a $5.2$ TB carefully curated Chinese web corpus, a $22.5$ TB English subset from Nemotron-CC, and diverse sources from math, wiki, arxiv, and code. Although these data are mostly sourced from well-processed datasets, the quality standards of various domains are dynamic and require extensive expert experience and la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07463","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.07463/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.07463","created_at":"2026-07-05T11:18:27.792208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07463v1","created_at":"2026-07-05T11:18:27.792208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07463","created_at":"2026-07-05T11:18:27.792208+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEPYSK4KDSCV","created_at":"2026-07-05T11:18:27.792208+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEPYSK4KDSCV557W","created_at":"2026-07-05T11:18:27.792208+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEPYSK4K","created_at":"2026-07-05T11:18:27.792208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEPYSK4KDSCV557W6G4YMORHOD","json":"https://pith.science/pith/VEPYSK4KDSCV557W6G4YMORHOD.json","graph_json":"https://pith.science/api/pith-number/VEPYSK4KDSCV557W6G4YMORHOD/graph.json","events_json":"https://pith.science/api/pith-number/VEPYSK4KDSCV557W6G4YMORHOD/events.json","paper":"https://pith.science/paper/VEPYSK4K"},"agent_actions":{"view_html":"https://pith.science/pith/VEPYSK4KDSCV557W6G4YMORHOD","download_json":"https://pith.science/pith/VEPYSK4KDSCV557W6G4YMORHOD.json","view_paper":"https://pith.science/paper/VEPYSK4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07463&json=true","fetch_graph":"https://pith.science/api/pith-number/VEPYSK4KDSCV557W6G4YMORHOD/graph.json","fetch_events":"https://pith.science/api/pith-number/VEPYSK4KDSCV557W6G4YMORHOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEPYSK4KDSCV557W6G4YMORHOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEPYSK4KDSCV557W6G4YMORHOD/action/storage_attestation","attest_author":"https://pith.science/pith/VEPYSK4KDSCV557W6G4YMORHOD/action/author_attestation","sign_citation":"https://pith.science/pith/VEPYSK4KDSCV557W6G4YMORHOD/action/citation_signature","submit_replication":"https://pith.science/pith/VEPYSK4KDSCV557W6G4YMORHOD/action/replication_record"}},"created_at":"2026-07-05T11:18:27.792208+00:00","updated_at":"2026-07-05T11:18:27.792208+00:00"}