{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SP5YVLL7BE6DCKYYDMRRIJ2EE7","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":"25c1ac29c3b2a294958b1b0703b2feca546aaa7872f2574efa5f6677bd30b8a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-19T03:42:56Z","title_canon_sha256":"d435bd6e518ba3aac9618eaaad751eee9067c0dc32e325d0eb50e0a0efeeaf56"},"schema_version":"1.0","source":{"id":"2301.07868","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.07868","created_at":"2026-07-05T08:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2301.07868v2","created_at":"2026-07-05T08:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07868","created_at":"2026-07-05T08:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"SP5YVLL7BE6D","created_at":"2026-07-05T08:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"SP5YVLL7BE6DCKYY","created_at":"2026-07-05T08:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"SP5YVLL7","created_at":"2026-07-05T08:06:39Z"}],"graph_snapshots":[{"event_id":"sha256:44da438f3d6a2f15dbe03d79a1cfa87a8a5833481b270dd6ed3a3695259576b6","target":"graph","created_at":"2026-07-05T08:06:39Z","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/2301.07868/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art video-text retrieval (VTR) methods typically involve fully fine-tuning a pre-trained model (e.g. CLIP) on specific datasets. However, this can result in significant storage costs in practical applications as a separate model per task must be stored. To address this issue, we present our pioneering work that enables parameter-efficient VTR using a pre-trained model, with only a small number of tunable parameters during training. Towards this goal, we propose a new method dubbed Multimodal Video Adapter (MV-Adapter) for efficiently transferring the knowledge in the pre-trained C","authors_text":"Bowen Zhang, Jiashi Feng, Kai Xu, Peng Wang, Weibo Gong, Xiaohui Shen, Xiaojie Jin, Xueqing Deng, Zhao Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-19T03:42:56Z","title":"MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07868","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":"sha256:5b93a61c5f8c35fae1757f86753b03fee601c649f38910884e4995188e023be0","target":"record","created_at":"2026-07-05T08:06:39Z","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":"25c1ac29c3b2a294958b1b0703b2feca546aaa7872f2574efa5f6677bd30b8a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-19T03:42:56Z","title_canon_sha256":"d435bd6e518ba3aac9618eaaad751eee9067c0dc32e325d0eb50e0a0efeeaf56"},"schema_version":"1.0","source":{"id":"2301.07868","kind":"arxiv","version":2}},"canonical_sha256":"93fb8aad7f093c312b181b2314274427cecbaa8eb24e12d1f9ab87cfc199286b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93fb8aad7f093c312b181b2314274427cecbaa8eb24e12d1f9ab87cfc199286b","first_computed_at":"2026-07-05T08:06:39.395065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:39.395065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E9HhGiubw8UJpMCcCG6G3qYS9qEGdzgEeZNpM4MKHxGw1Kjm1QyOfJ2SFELmOYz4AsoHxifq04PIgh6nGl7JCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:39.395975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.07868","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b93a61c5f8c35fae1757f86753b03fee601c649f38910884e4995188e023be0","sha256:44da438f3d6a2f15dbe03d79a1cfa87a8a5833481b270dd6ed3a3695259576b6"],"state_sha256":"f0bedfd690c8e2b45e40dbfbe70038c42d9ec0cd3cb4d358b7fe719a6fe2bd33"}