{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VEPYSK4KDSCV557W6G4YMORHOD","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":"dcd47d9977114eafd812d1729c8b4e93c92e7a0245f27d1b4bf7861b5de55807","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T06:14:19Z","title_canon_sha256":"126a76d20f62980edb8b79ac56a3b2d88ec5fc61a90c7ea8f8d65228f527d82f"},"schema_version":"1.0","source":{"id":"2506.07463","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07463","created_at":"2026-07-05T11:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07463v1","created_at":"2026-07-05T11:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07463","created_at":"2026-07-05T11:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"VEPYSK4KDSCV","created_at":"2026-07-05T11:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"VEPYSK4KDSCV557W","created_at":"2026-07-05T11:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"VEPYSK4K","created_at":"2026-07-05T11:18:27Z"}],"graph_snapshots":[{"event_id":"sha256:429a5db0be205f4f759f2d2697ba127e5545b95346ae6745bdf1197578eb4d77","target":"graph","created_at":"2026-07-05T11:18:27Z","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/2506.07463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Feng Liao, Guang Liu, Jiabei Chen, Jijie Li, Liangdong Wang, Yang Yu, Yao Xu, Yonghua Lin, Yu Bai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T06:14:19Z","title":"CCI4.0: A Bilingual Pretraining Dataset for Enhancing Reasoning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07463","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":"sha256:415dfb2b1f2adc65b8cd5aa463ce73f2180cb9a1fda9518cd196c6bdb5e272c8","target":"record","created_at":"2026-07-05T11:18:27Z","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":"dcd47d9977114eafd812d1729c8b4e93c92e7a0245f27d1b4bf7861b5de55807","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T06:14:19Z","title_canon_sha256":"126a76d20f62980edb8b79ac56a3b2d88ec5fc61a90c7ea8f8d65228f527d82f"},"schema_version":"1.0","source":{"id":"2506.07463","kind":"arxiv","version":1}},"canonical_sha256":"a91f892b8a1c855ef7f6f1b9863a2770d04d34d3313d48715d342a581729ebff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a91f892b8a1c855ef7f6f1b9863a2770d04d34d3313d48715d342a581729ebff","first_computed_at":"2026-07-05T11:18:27.792150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:27.792150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hKxJcNTZfkPZZuk6DWq/V1WB+OThA9gwAPUQllSc3yTH+u3/uev9XUQDePz6Wo8XGJtAPyVIZ8XxONJtxsVyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:27.792641Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07463","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:415dfb2b1f2adc65b8cd5aa463ce73f2180cb9a1fda9518cd196c6bdb5e272c8","sha256:429a5db0be205f4f759f2d2697ba127e5545b95346ae6745bdf1197578eb4d77"],"state_sha256":"4dbb9e038a90955a0904ed358aaa5eaaa906a06c8fa4f16a1c40ea932f66ce33"}