{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SP5YVLL7BE6DCKYYDMRRIJ2EE7","short_pith_number":"pith:SP5YVLL7","canonical_record":{"source":{"id":"2301.07868","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-19T03:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"d435bd6e518ba3aac9618eaaad751eee9067c0dc32e325d0eb50e0a0efeeaf56","abstract_canon_sha256":"25c1ac29c3b2a294958b1b0703b2feca546aaa7872f2574efa5f6677bd30b8a9"},"schema_version":"1.0"},"canonical_sha256":"93fb8aad7f093c312b181b2314274427cecbaa8eb24e12d1f9ab87cfc199286b","source":{"kind":"arxiv","id":"2301.07868","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SP5YVLL7BE6DCKYYDMRRIJ2EE7","target":"record","payload":{"canonical_record":{"source":{"id":"2301.07868","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-19T03:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"d435bd6e518ba3aac9618eaaad751eee9067c0dc32e325d0eb50e0a0efeeaf56","abstract_canon_sha256":"25c1ac29c3b2a294958b1b0703b2feca546aaa7872f2574efa5f6677bd30b8a9"},"schema_version":"1.0"},"canonical_sha256":"93fb8aad7f093c312b181b2314274427cecbaa8eb24e12d1f9ab87cfc199286b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:39.395975Z","signature_b64":"E9HhGiubw8UJpMCcCG6G3qYS9qEGdzgEeZNpM4MKHxGw1Kjm1QyOfJ2SFELmOYz4AsoHxifq04PIgh6nGl7JCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93fb8aad7f093c312b181b2314274427cecbaa8eb24e12d1f9ab87cfc199286b","last_reissued_at":"2026-07-05T08:06:39.395065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:39.395065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.07868","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kWsM4L/2cFyUgRzJBlDbHqXgx6r1Zn4oYVV8KhXIkuzlcGlc1KIn/5AnYe0iqvVRg6XMZZ1Zhol9LIDAH6yDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:42:57.152791Z"},"content_sha256":"5b93a61c5f8c35fae1757f86753b03fee601c649f38910884e4995188e023be0","schema_version":"1.0","event_id":"sha256:5b93a61c5f8c35fae1757f86753b03fee601c649f38910884e4995188e023be0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SP5YVLL7BE6DCKYYDMRRIJ2EE7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Jiashi Feng, Kai Xu, Peng Wang, Weibo Gong, Xiaohui Shen, Xiaojie Jin, Xueqing Deng, Zhao Zhang","submitted_at":"2023-01-19T03:42:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07868","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/2301.07868/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tetd/HwKr1r8sSfygZ+XvRhihTBs0bG00TWNTF+igbwZR2YOf8cm3k6jA/Wr7yjNTJi93TQ0lgP2GQEMdp2PBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:42:57.153168Z"},"content_sha256":"44da438f3d6a2f15dbe03d79a1cfa87a8a5833481b270dd6ed3a3695259576b6","schema_version":"1.0","event_id":"sha256:44da438f3d6a2f15dbe03d79a1cfa87a8a5833481b270dd6ed3a3695259576b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/bundle.json","state_url":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T07:42:57Z","links":{"resolver":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7","bundle":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/bundle.json","state":"https://pith.science/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SP5YVLL7BE6DCKYYDMRRIJ2EE7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ptXt2HzR1AJGd3HAvDUT/1jDQPBx9laGaNG8LLk8ArYiRqKsiyXJc/vm18/ipr7gfbHZ4WnvU5GRs58BZ/nMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:42:57.155613Z","bundle_sha256":"e0a12d100278e9f8d25c5d6f361e5002939c5d74537092935a2a1cafce73f0fb"}}