{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5PAWPQFCEXM6CQRWRF4DY4WFFN","short_pith_number":"pith:5PAWPQFC","schema_version":"1.0","canonical_sha256":"ebc167c0a225d9e1423689783c72c52b51eb79b1ac51f58de559be63edd9fb06","source":{"kind":"arxiv","id":"2308.10755","version":3},"attestation_state":"computed","paper":{"title":"WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Chao Xu, Conghui He, Dahua Lin, Hang Yan, Jiantao Qiu, Jiaqi Wang, Wei Li, Zhenjiang Jin","submitted_at":"2023-08-21T14:40:48Z","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"},"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":"2308.10755","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T14:40:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"01497891f4be319530089ed66578318ec73648a340493a6f7ce48c289d4ae8e5","abstract_canon_sha256":"7ccbb7844b2f2decf1309ab8f6c363e003b2a8335f04ae08377c8cd5b0a7cf12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:57.574274Z","signature_b64":"sZ5SP51keJmRxTV4it9WK0RRtfkOPOAyZjOjGOt5vkf19opN0rPzPUxOF14ilMj7ZEYHHWxCHCX3sTboXZyFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebc167c0a225d9e1423689783c72c52b51eb79b1ac51f58de559be63edd9fb06","last_reissued_at":"2026-07-05T06:50:57.573865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:57.573865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Chao Xu, Conghui He, Dahua Lin, Hang Yan, Jiantao Qiu, Jiaqi Wang, Wei Li, Zhenjiang Jin","submitted_at":"2023-08-21T14:40:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10755","kind":"arxiv","version":3},"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/2308.10755/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":"2308.10755","created_at":"2026-07-05T06:50:57.573927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10755v3","created_at":"2026-07-05T06:50:57.573927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10755","created_at":"2026-07-05T06:50:57.573927+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PAWPQFCEXM6","created_at":"2026-07-05T06:50:57.573927+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PAWPQFCEXM6CQRW","created_at":"2026-07-05T06:50:57.573927+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PAWPQFC","created_at":"2026-07-05T06:50:57.573927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15079","citing_title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","ref_index":214,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28551","citing_title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28551","citing_title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2309.15112","citing_title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2401.16420","citing_title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06942","citing_title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10302","citing_title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PAWPQFCEXM6CQRWRF4DY4WFFN","json":"https://pith.science/pith/5PAWPQFCEXM6CQRWRF4DY4WFFN.json","graph_json":"https://pith.science/api/pith-number/5PAWPQFCEXM6CQRWRF4DY4WFFN/graph.json","events_json":"https://pith.science/api/pith-number/5PAWPQFCEXM6CQRWRF4DY4WFFN/events.json","paper":"https://pith.science/paper/5PAWPQFC"},"agent_actions":{"view_html":"https://pith.science/pith/5PAWPQFCEXM6CQRWRF4DY4WFFN","download_json":"https://pith.science/pith/5PAWPQFCEXM6CQRWRF4DY4WFFN.json","view_paper":"https://pith.science/paper/5PAWPQFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10755&json=true","fetch_graph":"https://pith.science/api/pith-number/5PAWPQFCEXM6CQRWRF4DY4WFFN/graph.json","fetch_events":"https://pith.science/api/pith-number/5PAWPQFCEXM6CQRWRF4DY4WFFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PAWPQFCEXM6CQRWRF4DY4WFFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PAWPQFCEXM6CQRWRF4DY4WFFN/action/storage_attestation","attest_author":"https://pith.science/pith/5PAWPQFCEXM6CQRWRF4DY4WFFN/action/author_attestation","sign_citation":"https://pith.science/pith/5PAWPQFCEXM6CQRWRF4DY4WFFN/action/citation_signature","submit_replication":"https://pith.science/pith/5PAWPQFCEXM6CQRWRF4DY4WFFN/action/replication_record"}},"created_at":"2026-07-05T06:50:57.573927+00:00","updated_at":"2026-07-05T06:50:57.573927+00:00"}