{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KHCGZXDO4TB47JHLS5YYT2ZKJV","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":"2295a1fb8ad4d87bb056009d9d12fcbbf23cc094d4b2988bc5cc3f6804d9c329","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-19T15:58:45Z","title_canon_sha256":"b3793bd6f9b023ae329bdb6a28ef12313a3e8cf416e5b1b4708261f60bf5f3b0"},"schema_version":"1.0","source":{"id":"2104.09411","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09411","created_at":"2026-07-05T02:33:13Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09411v1","created_at":"2026-07-05T02:33:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09411","created_at":"2026-07-05T02:33:13Z"},{"alias_kind":"pith_short_12","alias_value":"KHCGZXDO4TB4","created_at":"2026-07-05T02:33:13Z"},{"alias_kind":"pith_short_16","alias_value":"KHCGZXDO4TB47JHL","created_at":"2026-07-05T02:33:13Z"},{"alias_kind":"pith_short_8","alias_value":"KHCGZXDO","created_at":"2026-07-05T02:33:13Z"}],"graph_snapshots":[{"event_id":"sha256:f43e53fa800340aaee7d8e3ee8ad22618569d0535651c740a406b5a6cf305041","target":"graph","created_at":"2026-07-05T02:33:13Z","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/2104.09411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pre-trained neural models have recently achieved impressive performances in understanding multimodal content. However, it is still very challenging to pre-train neural models for video and language understanding, especially for Chinese video-language data, due to the following reasons. Firstly, existing video-language pre-training algorithms mainly focus on the co-occurrence of words and video frames, but ignore other valuable semantic and structure information of video-language content, e.g., sequential order and spatiotemporal relationships. Secondly, there exist conflicts between video ","authors_text":"Chenyi Lei, Chunyan Miao, Guoxin Wang, Haihong Tang, Houqiang Li, Jiamang Wang, Shixian Luo, Wanggui He, Yong Liu","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-19T15:58:45Z","title":"Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09411","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":"sha256:664aa55a6388125e46c7232d9a1af659eff80fea341c4baff0c53ad54b32954f","target":"record","created_at":"2026-07-05T02:33:13Z","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":"2295a1fb8ad4d87bb056009d9d12fcbbf23cc094d4b2988bc5cc3f6804d9c329","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-19T15:58:45Z","title_canon_sha256":"b3793bd6f9b023ae329bdb6a28ef12313a3e8cf416e5b1b4708261f60bf5f3b0"},"schema_version":"1.0","source":{"id":"2104.09411","kind":"arxiv","version":1}},"canonical_sha256":"51c46cdc6ee4c3cfa4eb977189eb2a4d5b43a58c338786cdee1d7b2cc847c25b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51c46cdc6ee4c3cfa4eb977189eb2a4d5b43a58c338786cdee1d7b2cc847c25b","first_computed_at":"2026-07-05T02:33:13.002091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:13.002091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Ceigx+P0HXI5cywIsFVaY35692j5i/WrQr2x0rSJ8qaon4xs28dv2wsTq9zR9wkQvvyOP/JVIqm1IBTu1CuBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:13.002546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.09411","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:664aa55a6388125e46c7232d9a1af659eff80fea341c4baff0c53ad54b32954f","sha256:f43e53fa800340aaee7d8e3ee8ad22618569d0535651c740a406b5a6cf305041"],"state_sha256":"05f845242fa146cbef25b0b2ddaf4c44c07f5f512b7d875e50d4b0b3f28b230d"}