{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5PAWPQFCEXM6CQRWRF4DY4WFFN","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":"7ccbb7844b2f2decf1309ab8f6c363e003b2a8335f04ae08377c8cd5b0a7cf12","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T14:40:48Z","title_canon_sha256":"01497891f4be319530089ed66578318ec73648a340493a6f7ce48c289d4ae8e5"},"schema_version":"1.0","source":{"id":"2308.10755","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10755","created_at":"2026-07-05T06:50:57Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10755v3","created_at":"2026-07-05T06:50:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10755","created_at":"2026-07-05T06:50:57Z"},{"alias_kind":"pith_short_12","alias_value":"5PAWPQFCEXM6","created_at":"2026-07-05T06:50:57Z"},{"alias_kind":"pith_short_16","alias_value":"5PAWPQFCEXM6CQRW","created_at":"2026-07-05T06:50:57Z"},{"alias_kind":"pith_short_8","alias_value":"5PAWPQFC","created_at":"2026-07-05T06:50:57Z"}],"graph_snapshots":[{"event_id":"sha256:350a67adf17696e1c69e9cccf26fff17edc45f17c9ea88e1c042ad8ade798c8d","target":"graph","created_at":"2026-07-05T06:50:57Z","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/2308.10755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rise in popularity of ChatGPT and GPT-4 has significantly accelerated the development of large models, leading to the creation of numerous impressive large language models(LLMs) and multimodal large language models (MLLMs). These cutting-edge models owe their remarkable performance to high-quality data. However, the details of the training data used in leading paradigms are often kept confidential. This lack of transparency, coupled with the scarcity of open-source data, impedes further developments within the community. As a response, this paper presents \"Wan Juan\", a large-scale multimod","authors_text":"Bin Wang, Chao Xu, Conghui He, Dahua Lin, Hang Yan, Jiantao Qiu, Jiaqi Wang, Wei Li, Zhenjiang Jin","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T14:40:48Z","title":"WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10755","kind":"arxiv","version":3},"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:f547305b9c1763bc3372a70d8936e120b5dd3ff3656deb034550ef0e4e398246","target":"record","created_at":"2026-07-05T06:50:57Z","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":"7ccbb7844b2f2decf1309ab8f6c363e003b2a8335f04ae08377c8cd5b0a7cf12","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T14:40:48Z","title_canon_sha256":"01497891f4be319530089ed66578318ec73648a340493a6f7ce48c289d4ae8e5"},"schema_version":"1.0","source":{"id":"2308.10755","kind":"arxiv","version":3}},"canonical_sha256":"ebc167c0a225d9e1423689783c72c52b51eb79b1ac51f58de559be63edd9fb06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebc167c0a225d9e1423689783c72c52b51eb79b1ac51f58de559be63edd9fb06","first_computed_at":"2026-07-05T06:50:57.573865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:57.573865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sZ5SP51keJmRxTV4it9WK0RRtfkOPOAyZjOjGOt5vkf19opN0rPzPUxOF14ilMj7ZEYHHWxCHCX3sTboXZyFAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:57.574274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10755","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f547305b9c1763bc3372a70d8936e120b5dd3ff3656deb034550ef0e4e398246","sha256:350a67adf17696e1c69e9cccf26fff17edc45f17c9ea88e1c042ad8ade798c8d"],"state_sha256":"5fdf60ba700d3af151ed0892bed063c9aada2a7ebb71eecf61b901afa974b5df"}