{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M7WRTU3M5E5RWGOBMFVZNB4VPP","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":"804c37e3aeeea2755078976d80a8998fc23c3af654bcb84453b37ff39d701de3","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T14:33:22Z","title_canon_sha256":"7731b875eac4f188af93a064b48c7913f113deadc764372082f90bdfb443840b"},"schema_version":"1.0","source":{"id":"2410.00741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00741","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00741v2","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00741","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"pith_short_12","alias_value":"M7WRTU3M5E5R","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"pith_short_16","alias_value":"M7WRTU3M5E5RWGOB","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"pith_short_8","alias_value":"M7WRTU3M","created_at":"2026-07-05T09:15:59Z"}],"graph_snapshots":[{"event_id":"sha256:a61bd57471b54291f0bff367915696178f573dbd5e34439201b8be9d2c268ca1","target":"graph","created_at":"2026-07-05T09:15:59Z","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/2410.00741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has been widely studied and applied in numerous applications. However, the emphasis on brief summary texts during pre-training prevents CLIP from understanding long descriptions. This issue is particularly acute regarding videos given that videos often contain abundant detailed contents. In this paper, we propose the VideoCLIP-XL (eXtra Length) model, which aims to unleash the long-description understanding capability of video CLIP models. Firstly, we establish an automatic data collection system and gather a large-scale VILD pre-training dataset ","authors_text":"Chengyu Wang, Jiapeng Wang, Jun Huang, Kunzhe Huang, Lianwen Jin","cross_cats":["cs.CV","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T14:33:22Z","title":"VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00741","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":"sha256:92c1f90c4d0d492273f7cd805c0d4d2683dcf9b0bb70d2ff991429f32373bd72","target":"record","created_at":"2026-07-05T09:15:59Z","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":"804c37e3aeeea2755078976d80a8998fc23c3af654bcb84453b37ff39d701de3","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T14:33:22Z","title_canon_sha256":"7731b875eac4f188af93a064b48c7913f113deadc764372082f90bdfb443840b"},"schema_version":"1.0","source":{"id":"2410.00741","kind":"arxiv","version":2}},"canonical_sha256":"67ed19d36ce93b1b19c1616b9687957bd42708a201b463149a5971e3533bc430","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67ed19d36ce93b1b19c1616b9687957bd42708a201b463149a5971e3533bc430","first_computed_at":"2026-07-05T09:15:59.687543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:59.687543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DC6RD7cQ0ZE0BnNRiluMHZQlInM7S2kBMjrMmF9Xj4N/1yJapETxrW5LdyG5X6T6PIVMSM3GpnbvgUQczc3WBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:59.688063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92c1f90c4d0d492273f7cd805c0d4d2683dcf9b0bb70d2ff991429f32373bd72","sha256:a61bd57471b54291f0bff367915696178f573dbd5e34439201b8be9d2c268ca1"],"state_sha256":"76f01eedd5c3d27a5c11d315ae0a67350f57c9f7f5af909d1659d145af9786f6"}