{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EBKDNYYCIRPYOHA26VUIOK5Z35","short_pith_number":"pith:EBKDNYYC","schema_version":"1.0","canonical_sha256":"205436e302445f871c1af568872bb9df669188609e69b9f68ac59420531e5216","source":{"kind":"arxiv","id":"2207.07285","version":2},"attestation_state":"computed","paper":{"title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guohai Xu, Ji Zhang, Ming Yan, Rongrong Ji, Xiaoshuai Sun, Yiwei Ma","submitted_at":"2022-07-15T04:23:42Z","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"},"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":"2207.07285","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-15T04:23:42Z","cross_cats_sorted":[],"title_canon_sha256":"bdfbdb4e84ef5ade225e316ace1338d2fa29c269b985519530039db236d5820e","abstract_canon_sha256":"2c3a52cb6b20d75909d21f2ac38fe8a1ef56fc1ff913474657cc144060795557"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:01.970926Z","signature_b64":"a8w0FSools4pi5ss2k6n64Q1vchwVSZZLbyh32WzlwxELYepbUGIo1e8EbSYWeRMtZx2hYzB+81arus535f9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"205436e302445f871c1af568872bb9df669188609e69b9f68ac59420531e5216","last_reissued_at":"2026-07-05T05:00:01.970547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:01.970547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guohai Xu, Ji Zhang, Ming Yan, Rongrong Ji, Xiaoshuai Sun, Yiwei Ma","submitted_at":"2022-07-15T04:23:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07285","kind":"arxiv","version":2},"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/2207.07285/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":"2207.07285","created_at":"2026-07-05T05:00:01.970602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.07285v2","created_at":"2026-07-05T05:00:01.970602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07285","created_at":"2026-07-05T05:00:01.970602+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBKDNYYCIRPY","created_at":"2026-07-05T05:00:01.970602+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBKDNYYCIRPYOHA2","created_at":"2026-07-05T05:00:01.970602+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBKDNYYC","created_at":"2026-07-05T05:00:01.970602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00950","citing_title":"MVP: Winning Solution to SMP Challenge 2025 Video Track","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBKDNYYCIRPYOHA26VUIOK5Z35","json":"https://pith.science/pith/EBKDNYYCIRPYOHA26VUIOK5Z35.json","graph_json":"https://pith.science/api/pith-number/EBKDNYYCIRPYOHA26VUIOK5Z35/graph.json","events_json":"https://pith.science/api/pith-number/EBKDNYYCIRPYOHA26VUIOK5Z35/events.json","paper":"https://pith.science/paper/EBKDNYYC"},"agent_actions":{"view_html":"https://pith.science/pith/EBKDNYYCIRPYOHA26VUIOK5Z35","download_json":"https://pith.science/pith/EBKDNYYCIRPYOHA26VUIOK5Z35.json","view_paper":"https://pith.science/paper/EBKDNYYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.07285&json=true","fetch_graph":"https://pith.science/api/pith-number/EBKDNYYCIRPYOHA26VUIOK5Z35/graph.json","fetch_events":"https://pith.science/api/pith-number/EBKDNYYCIRPYOHA26VUIOK5Z35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBKDNYYCIRPYOHA26VUIOK5Z35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBKDNYYCIRPYOHA26VUIOK5Z35/action/storage_attestation","attest_author":"https://pith.science/pith/EBKDNYYCIRPYOHA26VUIOK5Z35/action/author_attestation","sign_citation":"https://pith.science/pith/EBKDNYYCIRPYOHA26VUIOK5Z35/action/citation_signature","submit_replication":"https://pith.science/pith/EBKDNYYCIRPYOHA26VUIOK5Z35/action/replication_record"}},"created_at":"2026-07-05T05:00:01.970602+00:00","updated_at":"2026-07-05T05:00:01.970602+00:00"}