{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NJKS3MNXYHNYAQO7DQFD5HKWJA","short_pith_number":"pith:NJKS3MNX","canonical_record":{"source":{"id":"2411.19668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T12:48:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6074268da6c1a8f6bb6dbdb8d12561e2742d167b274e82efacc4baa48168b63c","abstract_canon_sha256":"76d65884d67c00a1d08e667cac686d884865c3da32849d21345e2ffef9976662"},"schema_version":"1.0"},"canonical_sha256":"6a552db1b7c1db8041df1c0a3e9d564825942915d7fb0cfc7505d2d477009cf6","source":{"kind":"arxiv","id":"2411.19668","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19668","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19668v1","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19668","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"NJKS3MNXYHNY","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"NJKS3MNXYHNYAQO7","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"NJKS3MNX","created_at":"2026-07-05T09:42:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NJKS3MNXYHNYAQO7DQFD5HKWJA","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T12:48:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6074268da6c1a8f6bb6dbdb8d12561e2742d167b274e82efacc4baa48168b63c","abstract_canon_sha256":"76d65884d67c00a1d08e667cac686d884865c3da32849d21345e2ffef9976662"},"schema_version":"1.0"},"canonical_sha256":"6a552db1b7c1db8041df1c0a3e9d564825942915d7fb0cfc7505d2d477009cf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:06.355161Z","signature_b64":"krborpSOHuya69yf/Dd+Tcpy5Pl8fvOCSUtSo328vMjAmab+QVaZLBZxn95QrWdiWzJgJFrrJRweHcGDYAvVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a552db1b7c1db8041df1c0a3e9d564825942915d7fb0cfc7505d2d477009cf6","last_reissued_at":"2026-07-05T09:42:06.354534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:06.354534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19668","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hEiRoK1HqxZ1yGlDZKjAfYzGQuXPxXzazN4jx8loImV1iqW1NXzvkPG4M4q0IAf3WYsIS+zbsd/Att+t06MzBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:30:53.767020Z"},"content_sha256":"ae7351c7082adba02940173c1ee15af13f60906188984b92b03890d86033022f","schema_version":"1.0","event_id":"sha256:ae7351c7082adba02940173c1ee15af13f60906188984b92b03890d86033022f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NJKS3MNXYHNYAQO7DQFD5HKWJA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ChineseWebText 2.0: Large-Scale High-quality Chinese Web Text with Multi-dimensional and fine-grained information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Chunlin Leng, Jiajun Zhang, Qianlong Du, Wanyue Zhang, Wen Yang, Yinan Bai, Ziyong Li","submitted_at":"2024-11-29T12:48:49Z","abstract_excerpt":"During the development of large language models (LLMs), pre-training data play a critical role in shaping LLMs' capabilities. In recent years several large-scale and high-quality pre-training datasets have been released to accelerate the research of LLMs, including ChineseWebText1.0, C4, Pile, WanJuan, MAPCC and others. However, as LLMs continue to evolve, focus has increasingly shifted to domain-specific capabilities and safety concerns, making those previous coarse-grained texts insufficient for meeting training requirements. Furthermore, fine-grained information, such as quality, domain and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19668","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/2411.19668/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ogS8tNi1SuG8LApV/wXnCkrvVL9fDM4aTyllPNOGa46UveCDcGWVSAkV/ShCsC2T45D+hYA1aPy6faIbbwYsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:30:53.767512Z"},"content_sha256":"e5f84031836eb561df81bbd059e8489c44b6f2295d59e11e505d6ac427117e94","schema_version":"1.0","event_id":"sha256:e5f84031836eb561df81bbd059e8489c44b6f2295d59e11e505d6ac427117e94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJKS3MNXYHNYAQO7DQFD5HKWJA/bundle.json","state_url":"https://pith.science/pith/NJKS3MNXYHNYAQO7DQFD5HKWJA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJKS3MNXYHNYAQO7DQFD5HKWJA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T18:30:53Z","links":{"resolver":"https://pith.science/pith/NJKS3MNXYHNYAQO7DQFD5HKWJA","bundle":"https://pith.science/pith/NJKS3MNXYHNYAQO7DQFD5HKWJA/bundle.json","state":"https://pith.science/pith/NJKS3MNXYHNYAQO7DQFD5HKWJA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJKS3MNXYHNYAQO7DQFD5HKWJA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NJKS3MNXYHNYAQO7DQFD5HKWJA","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":"76d65884d67c00a1d08e667cac686d884865c3da32849d21345e2ffef9976662","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T12:48:49Z","title_canon_sha256":"6074268da6c1a8f6bb6dbdb8d12561e2742d167b274e82efacc4baa48168b63c"},"schema_version":"1.0","source":{"id":"2411.19668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19668","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19668v1","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19668","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"NJKS3MNXYHNY","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"NJKS3MNXYHNYAQO7","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"NJKS3MNX","created_at":"2026-07-05T09:42:06Z"}],"graph_snapshots":[{"event_id":"sha256:e5f84031836eb561df81bbd059e8489c44b6f2295d59e11e505d6ac427117e94","target":"graph","created_at":"2026-07-05T09:42:06Z","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/2411.19668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"During the development of large language models (LLMs), pre-training data play a critical role in shaping LLMs' capabilities. In recent years several large-scale and high-quality pre-training datasets have been released to accelerate the research of LLMs, including ChineseWebText1.0, C4, Pile, WanJuan, MAPCC and others. However, as LLMs continue to evolve, focus has increasingly shifted to domain-specific capabilities and safety concerns, making those previous coarse-grained texts insufficient for meeting training requirements. Furthermore, fine-grained information, such as quality, domain and","authors_text":"Chengqing Zong, Chunlin Leng, Jiajun Zhang, Qianlong Du, Wanyue Zhang, Wen Yang, Yinan Bai, Ziyong Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T12:48:49Z","title":"ChineseWebText 2.0: Large-Scale High-quality Chinese Web Text with Multi-dimensional and fine-grained information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19668","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:ae7351c7082adba02940173c1ee15af13f60906188984b92b03890d86033022f","target":"record","created_at":"2026-07-05T09:42:06Z","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":"76d65884d67c00a1d08e667cac686d884865c3da32849d21345e2ffef9976662","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T12:48:49Z","title_canon_sha256":"6074268da6c1a8f6bb6dbdb8d12561e2742d167b274e82efacc4baa48168b63c"},"schema_version":"1.0","source":{"id":"2411.19668","kind":"arxiv","version":1}},"canonical_sha256":"6a552db1b7c1db8041df1c0a3e9d564825942915d7fb0cfc7505d2d477009cf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a552db1b7c1db8041df1c0a3e9d564825942915d7fb0cfc7505d2d477009cf6","first_computed_at":"2026-07-05T09:42:06.354534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:06.354534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"krborpSOHuya69yf/Dd+Tcpy5Pl8fvOCSUtSo328vMjAmab+QVaZLBZxn95QrWdiWzJgJFrrJRweHcGDYAvVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:06.355161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae7351c7082adba02940173c1ee15af13f60906188984b92b03890d86033022f","sha256:e5f84031836eb561df81bbd059e8489c44b6f2295d59e11e505d6ac427117e94"],"state_sha256":"902397f075f03f43029a088f493803894f0ea0c416dece665ae27a29b09f0e17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tMl72T9Zqhq5hC+uIYZQxEK2EcYkbkAEf+HAQ+DGnKNPZQSxRTf41dhdag0TiP2fH+uol37bEJp3P3IomHzGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:30:53.771119Z","bundle_sha256":"02da2182e59f5083848bda67caaa16489b84bc7e1a867052cf924157baaae5fc"}}