{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EBKDNYYCIRPYOHA26VUIOK5Z35","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":"2c3a52cb6b20d75909d21f2ac38fe8a1ef56fc1ff913474657cc144060795557","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-15T04:23:42Z","title_canon_sha256":"bdfbdb4e84ef5ade225e316ace1338d2fa29c269b985519530039db236d5820e"},"schema_version":"1.0","source":{"id":"2207.07285","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.07285","created_at":"2026-07-05T05:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2207.07285v2","created_at":"2026-07-05T05:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07285","created_at":"2026-07-05T05:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"EBKDNYYCIRPY","created_at":"2026-07-05T05:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"EBKDNYYCIRPYOHA2","created_at":"2026-07-05T05:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"EBKDNYYC","created_at":"2026-07-05T05:00:01Z"}],"graph_snapshots":[{"event_id":"sha256:d9a0d68b563cfa698218a419d72bba276fae8ac6d87dc01d395b50dcee7a593b","target":"graph","created_at":"2026-07-05T05:00:01Z","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/2207.07285/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-text retrieval has been a crucial and fundamental task in multi-modal research. The development of video-text retrieval has been considerably promoted by large-scale multi-modal contrastive pre-training, which primarily focuses on coarse-grained or fine-grained contrast. However, cross-grained contrast, which is the contrast between coarse-grained representations and fine-grained representations, has rarely been explored in prior research. Compared with fine-grained or coarse-grained contrasts, cross-grained contrast calculate the correlation between coarse-grained features and each fine","authors_text":"Guohai Xu, Ji Zhang, Ming Yan, Rongrong Ji, Xiaoshuai Sun, Yiwei Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-15T04:23:42Z","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07285","kind":"arxiv","version":2},"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":"sha256:16a93063611cc9ff0bc0e5acde3de5c7d4613304cec37579e0ce2420c9816645","target":"record","created_at":"2026-07-05T05:00:01Z","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":"2c3a52cb6b20d75909d21f2ac38fe8a1ef56fc1ff913474657cc144060795557","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-15T04:23:42Z","title_canon_sha256":"bdfbdb4e84ef5ade225e316ace1338d2fa29c269b985519530039db236d5820e"},"schema_version":"1.0","source":{"id":"2207.07285","kind":"arxiv","version":2}},"canonical_sha256":"205436e302445f871c1af568872bb9df669188609e69b9f68ac59420531e5216","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"205436e302445f871c1af568872bb9df669188609e69b9f68ac59420531e5216","first_computed_at":"2026-07-05T05:00:01.970547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:00:01.970547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a8w0FSools4pi5ss2k6n64Q1vchwVSZZLbyh32WzlwxELYepbUGIo1e8EbSYWeRMtZx2hYzB+81arus535f9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T05:00:01.970926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.07285","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16a93063611cc9ff0bc0e5acde3de5c7d4613304cec37579e0ce2420c9816645","sha256:d9a0d68b563cfa698218a419d72bba276fae8ac6d87dc01d395b50dcee7a593b"],"state_sha256":"cd4696f00842298291542c90b294c6902b3e71a8cfc65cd4b1bc6f430d1b2476"}