{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WA7UUH6MA4HZP72PFR4PQ2PLDK","short_pith_number":"pith:WA7UUH6M","canonical_record":{"source":{"id":"2211.12764","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-23T08:20:29Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9a38d7ef444652808d9bd1aeb2458d2cdcfc5bb953c014dac0f1d0ae8c3eb305","abstract_canon_sha256":"048bd9250c9c87d708f8009d11496567717208a0350676126b47f67c0bd3bb74"},"schema_version":"1.0"},"canonical_sha256":"b03f4a1fcc070f97ff4f2c78f869eb1ab57bbec02eaf719e035c2f7b5fd2c013","source":{"kind":"arxiv","id":"2211.12764","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.12764","created_at":"2026-07-05T05:53:34Z"},{"alias_kind":"arxiv_version","alias_value":"2211.12764v3","created_at":"2026-07-05T05:53:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12764","created_at":"2026-07-05T05:53:34Z"},{"alias_kind":"pith_short_12","alias_value":"WA7UUH6MA4HZ","created_at":"2026-07-05T05:53:34Z"},{"alias_kind":"pith_short_16","alias_value":"WA7UUH6MA4HZP72P","created_at":"2026-07-05T05:53:34Z"},{"alias_kind":"pith_short_8","alias_value":"WA7UUH6M","created_at":"2026-07-05T05:53:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WA7UUH6MA4HZP72PFR4PQ2PLDK","target":"record","payload":{"canonical_record":{"source":{"id":"2211.12764","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-23T08:20:29Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9a38d7ef444652808d9bd1aeb2458d2cdcfc5bb953c014dac0f1d0ae8c3eb305","abstract_canon_sha256":"048bd9250c9c87d708f8009d11496567717208a0350676126b47f67c0bd3bb74"},"schema_version":"1.0"},"canonical_sha256":"b03f4a1fcc070f97ff4f2c78f869eb1ab57bbec02eaf719e035c2f7b5fd2c013","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:34.738524Z","signature_b64":"fIXWhM1IWL3sblXtTsPEhekYoF/GZC4upcuUWgqjYBVbA+3ZOO0f5/4u16mLeUvOEA/P/DSMs2fJFK/249oTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b03f4a1fcc070f97ff4f2c78f869eb1ab57bbec02eaf719e035c2f7b5fd2c013","last_reissued_at":"2026-07-05T05:53:34.738119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:34.738119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.12764","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:53:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uX32rc+mmo6Y+1IzTC/JvKcWjDUThjYQLW48ByZfgottBgoayeTJv+pVuOTyagGmKUo9EkZSA8Wne0b8/zl2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:41:59.220170Z"},"content_sha256":"47fb1eb744f3daa59f38f5c2f64b1819a4455ec005925169254973b33855a5dc","schema_version":"1.0","event_id":"sha256:47fb1eb744f3daa59f38f5c2f64b1819a4455ec005925169254973b33855a5dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WA7UUH6MA4HZP72PFR4PQ2PLDK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Biao Gong, Donglin Wang, Jianwen Jiang, Siteng Huang, Yiliang Lv, Yulin Pan, Yuyuan Li","submitted_at":"2022-11-23T08:20:29Z","abstract_excerpt":"Many recent studies leverage the pre-trained CLIP for text-video cross-modal retrieval by tuning the backbone with additional heavy modules, which not only brings huge computational burdens with much more parameters, but also leads to the knowledge forgetting from upstream models. In this work, we propose the VoP: Text-Video Co-operative Prompt Tuning for efficient tuning on the text-video retrieval task. The proposed VoP is an end-to-end framework with both video & text prompts introducing, which can be regarded as a powerful baseline with only 0.1% trainable parameters. Further, based on the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12764","kind":"arxiv","version":3},"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/2211.12764/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":"2026-07-05T05:53:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5n++6/aqxAEjxw7gHofqDKbWLtuGUvTvm2/cFMJSmHnU5HwBfgySRUqGQZ718kymQQURygB++kIhmtKbeXi7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:41:59.220831Z"},"content_sha256":"c908005f3e29c89651972bbdba09da9a8af40683381ef229b04d99321d246dc9","schema_version":"1.0","event_id":"sha256:c908005f3e29c89651972bbdba09da9a8af40683381ef229b04d99321d246dc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WA7UUH6MA4HZP72PFR4PQ2PLDK/bundle.json","state_url":"https://pith.science/pith/WA7UUH6MA4HZP72PFR4PQ2PLDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WA7UUH6MA4HZP72PFR4PQ2PLDK/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":"2026-07-05T15:41:59Z","links":{"resolver":"https://pith.science/pith/WA7UUH6MA4HZP72PFR4PQ2PLDK","bundle":"https://pith.science/pith/WA7UUH6MA4HZP72PFR4PQ2PLDK/bundle.json","state":"https://pith.science/pith/WA7UUH6MA4HZP72PFR4PQ2PLDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WA7UUH6MA4HZP72PFR4PQ2PLDK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WA7UUH6MA4HZP72PFR4PQ2PLDK","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":"048bd9250c9c87d708f8009d11496567717208a0350676126b47f67c0bd3bb74","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-23T08:20:29Z","title_canon_sha256":"9a38d7ef444652808d9bd1aeb2458d2cdcfc5bb953c014dac0f1d0ae8c3eb305"},"schema_version":"1.0","source":{"id":"2211.12764","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.12764","created_at":"2026-07-05T05:53:34Z"},{"alias_kind":"arxiv_version","alias_value":"2211.12764v3","created_at":"2026-07-05T05:53:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12764","created_at":"2026-07-05T05:53:34Z"},{"alias_kind":"pith_short_12","alias_value":"WA7UUH6MA4HZ","created_at":"2026-07-05T05:53:34Z"},{"alias_kind":"pith_short_16","alias_value":"WA7UUH6MA4HZP72P","created_at":"2026-07-05T05:53:34Z"},{"alias_kind":"pith_short_8","alias_value":"WA7UUH6M","created_at":"2026-07-05T05:53:34Z"}],"graph_snapshots":[{"event_id":"sha256:c908005f3e29c89651972bbdba09da9a8af40683381ef229b04d99321d246dc9","target":"graph","created_at":"2026-07-05T05:53:34Z","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/2211.12764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many recent studies leverage the pre-trained CLIP for text-video cross-modal retrieval by tuning the backbone with additional heavy modules, which not only brings huge computational burdens with much more parameters, but also leads to the knowledge forgetting from upstream models. In this work, we propose the VoP: Text-Video Co-operative Prompt Tuning for efficient tuning on the text-video retrieval task. The proposed VoP is an end-to-end framework with both video & text prompts introducing, which can be regarded as a powerful baseline with only 0.1% trainable parameters. Further, based on the","authors_text":"Biao Gong, Donglin Wang, Jianwen Jiang, Siteng Huang, Yiliang Lv, Yulin Pan, Yuyuan Li","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-23T08:20:29Z","title":"VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12764","kind":"arxiv","version":3},"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":"sha256:47fb1eb744f3daa59f38f5c2f64b1819a4455ec005925169254973b33855a5dc","target":"record","created_at":"2026-07-05T05:53:34Z","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":"048bd9250c9c87d708f8009d11496567717208a0350676126b47f67c0bd3bb74","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-23T08:20:29Z","title_canon_sha256":"9a38d7ef444652808d9bd1aeb2458d2cdcfc5bb953c014dac0f1d0ae8c3eb305"},"schema_version":"1.0","source":{"id":"2211.12764","kind":"arxiv","version":3}},"canonical_sha256":"b03f4a1fcc070f97ff4f2c78f869eb1ab57bbec02eaf719e035c2f7b5fd2c013","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b03f4a1fcc070f97ff4f2c78f869eb1ab57bbec02eaf719e035c2f7b5fd2c013","first_computed_at":"2026-07-05T05:53:34.738119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:53:34.738119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fIXWhM1IWL3sblXtTsPEhekYoF/GZC4upcuUWgqjYBVbA+3ZOO0f5/4u16mLeUvOEA/P/DSMs2fJFK/249oTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:53:34.738524Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.12764","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47fb1eb744f3daa59f38f5c2f64b1819a4455ec005925169254973b33855a5dc","sha256:c908005f3e29c89651972bbdba09da9a8af40683381ef229b04d99321d246dc9"],"state_sha256":"a3c9fca678b781b7f3779bbc80cfafda7d5b60a66917f8a6ca6667652f434370"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ku6llDGfzOeq89HbNtp/I6D3+BS2YIIqulq7F2fCW1L2NzRxPsslV0ZOKou46cSYsQPJsac+ntKzBcCE/eMIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:41:59.223855Z","bundle_sha256":"30093cfd2610825aae539ea1d3fe0d8aca1fc94caf1b669de9951dfe6b8a4305"}}