{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FR34VPP2EZD3HBWHEQBWDUSPIO","short_pith_number":"pith:FR34VPP2","schema_version":"1.0","canonical_sha256":"2c77cabdfa2647b386c7240361d24f438713013e0eba5207ac6cdaff2981aa99","source":{"kind":"arxiv","id":"2205.03860","version":6},"attestation_state":"computed","paper":{"title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Chunyu Xie, Dawei Leng, Dexin Wang, Fanjing Kong, Heng Cai, Henrique Morimitsu, Jianfei Song, Jincheng Li, Lin Yao, Xiangyang Ji, Xiangzheng Zhang, Xiaoyu Wu, Yafeng Deng","submitted_at":"2022-05-08T13:19:23Z","abstract_excerpt":"Vision-language pre-training (VLP) on large-scale datasets has shown premier performance on various downstream tasks. In contrast to plenty of available benchmarks with English corpus, large-scale pre-training datasets and downstream datasets with Chinese corpus remain largely unexplored. In this work, we build a large-scale high-quality Chinese Cross-Modal Benchmark named CCMB for the research community, which contains the currently largest public pre-training dataset Zero and five human-annotated fine-tuning datasets for downstream tasks. Zero contains 250 million images paired with 750 mill"},"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":"2205.03860","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T13:19:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"95774977c5e6df6ecd830c70a6fb4658713a5bfd267725e4873adac7ef16b0d1","abstract_canon_sha256":"4384fccf121bf37fe62826488c81c6ca324e91d606158966ef14a0a38e7bfc24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:20.231368Z","signature_b64":"nLMTs8X1LR3sSPo61nRLgbgcFYwYBwwbRsD6T0g8zR4exPQ4tmSj9MnDIaTUDu3ufm2XdISA9iTTEbaexGU4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c77cabdfa2647b386c7240361d24f438713013e0eba5207ac6cdaff2981aa99","last_reissued_at":"2026-07-05T07:10:20.230877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:20.230877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Chunyu Xie, Dawei Leng, Dexin Wang, Fanjing Kong, Heng Cai, Henrique Morimitsu, Jianfei Song, Jincheng Li, Lin Yao, Xiangyang Ji, Xiangzheng Zhang, Xiaoyu Wu, Yafeng Deng","submitted_at":"2022-05-08T13:19:23Z","abstract_excerpt":"Vision-language pre-training (VLP) on large-scale datasets has shown premier performance on various downstream tasks. In contrast to plenty of available benchmarks with English corpus, large-scale pre-training datasets and downstream datasets with Chinese corpus remain largely unexplored. In this work, we build a large-scale high-quality Chinese Cross-Modal Benchmark named CCMB for the research community, which contains the currently largest public pre-training dataset Zero and five human-annotated fine-tuning datasets for downstream tasks. Zero contains 250 million images paired with 750 mill"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03860","kind":"arxiv","version":6},"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/2205.03860/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":"2205.03860","created_at":"2026-07-05T07:10:20.230933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03860v6","created_at":"2026-07-05T07:10:20.230933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03860","created_at":"2026-07-05T07:10:20.230933+00:00"},{"alias_kind":"pith_short_12","alias_value":"FR34VPP2EZD3","created_at":"2026-07-05T07:10:20.230933+00:00"},{"alias_kind":"pith_short_16","alias_value":"FR34VPP2EZD3HBWH","created_at":"2026-07-05T07:10:20.230933+00:00"},{"alias_kind":"pith_short_8","alias_value":"FR34VPP2","created_at":"2026-07-05T07:10:20.230933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":160,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FR34VPP2EZD3HBWHEQBWDUSPIO","json":"https://pith.science/pith/FR34VPP2EZD3HBWHEQBWDUSPIO.json","graph_json":"https://pith.science/api/pith-number/FR34VPP2EZD3HBWHEQBWDUSPIO/graph.json","events_json":"https://pith.science/api/pith-number/FR34VPP2EZD3HBWHEQBWDUSPIO/events.json","paper":"https://pith.science/paper/FR34VPP2"},"agent_actions":{"view_html":"https://pith.science/pith/FR34VPP2EZD3HBWHEQBWDUSPIO","download_json":"https://pith.science/pith/FR34VPP2EZD3HBWHEQBWDUSPIO.json","view_paper":"https://pith.science/paper/FR34VPP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03860&json=true","fetch_graph":"https://pith.science/api/pith-number/FR34VPP2EZD3HBWHEQBWDUSPIO/graph.json","fetch_events":"https://pith.science/api/pith-number/FR34VPP2EZD3HBWHEQBWDUSPIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FR34VPP2EZD3HBWHEQBWDUSPIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FR34VPP2EZD3HBWHEQBWDUSPIO/action/storage_attestation","attest_author":"https://pith.science/pith/FR34VPP2EZD3HBWHEQBWDUSPIO/action/author_attestation","sign_citation":"https://pith.science/pith/FR34VPP2EZD3HBWHEQBWDUSPIO/action/citation_signature","submit_replication":"https://pith.science/pith/FR34VPP2EZD3HBWHEQBWDUSPIO/action/replication_record"}},"created_at":"2026-07-05T07:10:20.230933+00:00","updated_at":"2026-07-05T07:10:20.230933+00:00"}