{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FR34VPP2EZD3HBWHEQBWDUSPIO","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":"4384fccf121bf37fe62826488c81c6ca324e91d606158966ef14a0a38e7bfc24","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T13:19:23Z","title_canon_sha256":"95774977c5e6df6ecd830c70a6fb4658713a5bfd267725e4873adac7ef16b0d1"},"schema_version":"1.0","source":{"id":"2205.03860","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.03860","created_at":"2026-07-05T07:10:20Z"},{"alias_kind":"arxiv_version","alias_value":"2205.03860v6","created_at":"2026-07-05T07:10:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03860","created_at":"2026-07-05T07:10:20Z"},{"alias_kind":"pith_short_12","alias_value":"FR34VPP2EZD3","created_at":"2026-07-05T07:10:20Z"},{"alias_kind":"pith_short_16","alias_value":"FR34VPP2EZD3HBWH","created_at":"2026-07-05T07:10:20Z"},{"alias_kind":"pith_short_8","alias_value":"FR34VPP2","created_at":"2026-07-05T07:10:20Z"}],"graph_snapshots":[{"event_id":"sha256:907b72ce9f46bafa0fc87015a32b09614ccb4923ddc8c262bd2f061eea4d8414","target":"graph","created_at":"2026-07-05T07:10:20Z","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/2205.03860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T13:19:23Z","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03860","kind":"arxiv","version":6},"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:a13fdac2badccaa9fcd0022297a017a2870c22d1e3a6115c94c36b2bbec0c6b0","target":"record","created_at":"2026-07-05T07:10:20Z","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":"4384fccf121bf37fe62826488c81c6ca324e91d606158966ef14a0a38e7bfc24","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T13:19:23Z","title_canon_sha256":"95774977c5e6df6ecd830c70a6fb4658713a5bfd267725e4873adac7ef16b0d1"},"schema_version":"1.0","source":{"id":"2205.03860","kind":"arxiv","version":6}},"canonical_sha256":"2c77cabdfa2647b386c7240361d24f438713013e0eba5207ac6cdaff2981aa99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c77cabdfa2647b386c7240361d24f438713013e0eba5207ac6cdaff2981aa99","first_computed_at":"2026-07-05T07:10:20.230877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:20.230877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nLMTs8X1LR3sSPo61nRLgbgcFYwYBwwbRsD6T0g8zR4exPQ4tmSj9MnDIaTUDu3ufm2XdISA9iTTEbaexGU4Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:20.231368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.03860","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a13fdac2badccaa9fcd0022297a017a2870c22d1e3a6115c94c36b2bbec0c6b0","sha256:907b72ce9f46bafa0fc87015a32b09614ccb4923ddc8c262bd2f061eea4d8414"],"state_sha256":"d0616085483b419d8e1a725494b3c1a3ec551d84e8a514513deb7492405bf192"}