{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MRWVMQVFZAK6CWCETFYYZ7IDKV","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":"9c7f165cf5943c591d7ba2fbb22601ff9e8affcf4fbf265f84f18d4fa4240a9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T19:23:53Z","title_canon_sha256":"2109292c5574a1b6560586a54ff35bac94b5ecb3bbc8267c1067a04244b0e12a"},"schema_version":"1.0","source":{"id":"2405.19465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19465","created_at":"2026-07-05T08:25:07Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19465v1","created_at":"2026-07-05T08:25:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19465","created_at":"2026-07-05T08:25:07Z"},{"alias_kind":"pith_short_12","alias_value":"MRWVMQVFZAK6","created_at":"2026-07-05T08:25:07Z"},{"alias_kind":"pith_short_16","alias_value":"MRWVMQVFZAK6CWCE","created_at":"2026-07-05T08:25:07Z"},{"alias_kind":"pith_short_8","alias_value":"MRWVMQVF","created_at":"2026-07-05T08:25:07Z"}],"graph_snapshots":[{"event_id":"sha256:d17bdbc65abcb91f8c5a87484d69da1495fb34ae29ecfec534e9864b0c05c99a","target":"graph","created_at":"2026-07-05T08:25:07Z","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/2405.19465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. To date, most state-of-the-art TVR methods learn image-to-video transfer learning based on large-scale pre-trained visionlanguage models (e.g., CLIP). However, fully fine-tuning these pre-trained models for TVR incurs prohibitively expensive computation costs. To this end, we propose to conduct efficient text-video Retrieval with a sparse-andcorrelated AdaPter (RAP), i.e., fine-tuning the pre-trained model with a few parameterized layers. To accommodate the text-video scenario, we equip our RAP with ","authors_text":"Can Zhang, Ge Li, Haoran Tang, Jinfa Huang, Li Yuan, Long Chen, Meng Cao, Peng Jin, Ruyang Liu, Xiaodan Liang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T19:23:53Z","title":"RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19465","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":"sha256:548bbb99a2c804e5ea486fddfb35e026f5abc8d88aff0e2891fc759e759b282f","target":"record","created_at":"2026-07-05T08:25:07Z","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":"9c7f165cf5943c591d7ba2fbb22601ff9e8affcf4fbf265f84f18d4fa4240a9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T19:23:53Z","title_canon_sha256":"2109292c5574a1b6560586a54ff35bac94b5ecb3bbc8267c1067a04244b0e12a"},"schema_version":"1.0","source":{"id":"2405.19465","kind":"arxiv","version":1}},"canonical_sha256":"646d5642a5c815e1584499718cfd035575f1c8f342adfe82ed5cbf96bb16a851","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"646d5642a5c815e1584499718cfd035575f1c8f342adfe82ed5cbf96bb16a851","first_computed_at":"2026-07-05T08:25:07.894542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:07.894542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G4Xfvskw+uHYPSsLYGl73cvHI8tCJMp9QQ8+++9D6Glykg3aXQ+XRWg8a1zDma1gKGN1EioUchB9V9dvDzoWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:07.895012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:548bbb99a2c804e5ea486fddfb35e026f5abc8d88aff0e2891fc759e759b282f","sha256:d17bdbc65abcb91f8c5a87484d69da1495fb34ae29ecfec534e9864b0c05c99a"],"state_sha256":"ac722318dd77ba6f6c437a8c974e049d892cdda2ef781508d6b32b608fb0ded0"}