{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KOEIPD43MOWGDW4XADMYA2L53X","short_pith_number":"pith:KOEIPD43","canonical_record":{"source":{"id":"2304.03307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T18:00:04Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"62b0c0fec9f74e54e94c22e24a3d3384f3cc7ecbf4e9d9066ca53e9ce16c4ecf","abstract_canon_sha256":"495c63f261badd05a78071535e42d366bc894cd91e4c3916f0a9e8293bd3ddd9"},"schema_version":"1.0"},"canonical_sha256":"5388878f9b63ac61db9700d980697dddd4fc3b4d0751b63adc099c78f482cdc8","source":{"kind":"arxiv","id":"2304.03307","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03307","created_at":"2026-07-05T05:58:54Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03307v1","created_at":"2026-07-05T05:58:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03307","created_at":"2026-07-05T05:58:54Z"},{"alias_kind":"pith_short_12","alias_value":"KOEIPD43MOWG","created_at":"2026-07-05T05:58:54Z"},{"alias_kind":"pith_short_16","alias_value":"KOEIPD43MOWGDW4X","created_at":"2026-07-05T05:58:54Z"},{"alias_kind":"pith_short_8","alias_value":"KOEIPD43","created_at":"2026-07-05T05:58:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KOEIPD43MOWGDW4XADMYA2L53X","target":"record","payload":{"canonical_record":{"source":{"id":"2304.03307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T18:00:04Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"62b0c0fec9f74e54e94c22e24a3d3384f3cc7ecbf4e9d9066ca53e9ce16c4ecf","abstract_canon_sha256":"495c63f261badd05a78071535e42d366bc894cd91e4c3916f0a9e8293bd3ddd9"},"schema_version":"1.0"},"canonical_sha256":"5388878f9b63ac61db9700d980697dddd4fc3b4d0751b63adc099c78f482cdc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:54.603595Z","signature_b64":"Jr0ZEDYUGXYEAuh7n2YLuO26pzVI0W6KoDTxDc9fU7546obyUb2IHI5g5de8MFtD8cbekJ+R1Qj/u6oxTu8uCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5388878f9b63ac61db9700d980697dddd4fc3b4d0751b63adc099c78f482cdc8","last_reissued_at":"2026-07-05T05:58:54.603181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:54.603181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.03307","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:58:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wVOm4QGE7a2uo0fqRcvRaz4M5fOVHZqvkNtMU8oeQu2Rk/GddJvXbjJBjbDpqAGGdEBSnr1XWvDEmx5Ly8SGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:56:06.949528Z"},"content_sha256":"b6a84612f1e47aeccf330931f35ccf7b6904786f670a587ee04f338ec331f923","schema_version":"1.0","event_id":"sha256:b6a84612f1e47aeccf330931f35ccf7b6904786f670a587ee04f338ec331f923"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KOEIPD43MOWGDW4XADMYA2L53X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Mubarak Shah, Muzammal Naseer, Salman Khan, Syed Talal Wasim","submitted_at":"2023-04-06T18:00:04Z","abstract_excerpt":"Adopting contrastive image-text pretrained models like CLIP towards video classification has gained attention due to its cost-effectiveness and competitive performance. However, recent works in this area face a trade-off. Finetuning the pretrained model to achieve strong supervised performance results in low zero-shot generalization. Similarly, freezing the backbone to retain zero-shot capability causes significant drop in supervised accuracy. Because of this, recent works in literature typically train separate models for supervised and zero-shot action recognition. In this work, we propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03307","kind":"arxiv","version":1},"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/2304.03307/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":"2026-07-05T05:58:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JedEMXfUqpqFNH1oxAaOwpdp5KhbbNrugC1m5jxOzzfpy68Ppj2rEGDI2+ZBN+XABOkMKTHivtuZC57OQegCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:56:06.949902Z"},"content_sha256":"395e71f7218554c01d141651a0a35523d679269766e96825114a6560dd4dd19e","schema_version":"1.0","event_id":"sha256:395e71f7218554c01d141651a0a35523d679269766e96825114a6560dd4dd19e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KOEIPD43MOWGDW4XADMYA2L53X/bundle.json","state_url":"https://pith.science/pith/KOEIPD43MOWGDW4XADMYA2L53X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KOEIPD43MOWGDW4XADMYA2L53X/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":"2026-07-07T07:56:06Z","links":{"resolver":"https://pith.science/pith/KOEIPD43MOWGDW4XADMYA2L53X","bundle":"https://pith.science/pith/KOEIPD43MOWGDW4XADMYA2L53X/bundle.json","state":"https://pith.science/pith/KOEIPD43MOWGDW4XADMYA2L53X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KOEIPD43MOWGDW4XADMYA2L53X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KOEIPD43MOWGDW4XADMYA2L53X","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":"495c63f261badd05a78071535e42d366bc894cd91e4c3916f0a9e8293bd3ddd9","cross_cats_sorted":["eess.IV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T18:00:04Z","title_canon_sha256":"62b0c0fec9f74e54e94c22e24a3d3384f3cc7ecbf4e9d9066ca53e9ce16c4ecf"},"schema_version":"1.0","source":{"id":"2304.03307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03307","created_at":"2026-07-05T05:58:54Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03307v1","created_at":"2026-07-05T05:58:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03307","created_at":"2026-07-05T05:58:54Z"},{"alias_kind":"pith_short_12","alias_value":"KOEIPD43MOWG","created_at":"2026-07-05T05:58:54Z"},{"alias_kind":"pith_short_16","alias_value":"KOEIPD43MOWGDW4X","created_at":"2026-07-05T05:58:54Z"},{"alias_kind":"pith_short_8","alias_value":"KOEIPD43","created_at":"2026-07-05T05:58:54Z"}],"graph_snapshots":[{"event_id":"sha256:395e71f7218554c01d141651a0a35523d679269766e96825114a6560dd4dd19e","target":"graph","created_at":"2026-07-05T05:58:54Z","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/2304.03307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adopting contrastive image-text pretrained models like CLIP towards video classification has gained attention due to its cost-effectiveness and competitive performance. However, recent works in this area face a trade-off. Finetuning the pretrained model to achieve strong supervised performance results in low zero-shot generalization. Similarly, freezing the backbone to retain zero-shot capability causes significant drop in supervised accuracy. Because of this, recent works in literature typically train separate models for supervised and zero-shot action recognition. In this work, we propose a ","authors_text":"Fahad Shahbaz Khan, Mubarak Shah, Muzammal Naseer, Salman Khan, Syed Talal Wasim","cross_cats":["eess.IV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T18:00:04Z","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03307","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:b6a84612f1e47aeccf330931f35ccf7b6904786f670a587ee04f338ec331f923","target":"record","created_at":"2026-07-05T05:58:54Z","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":"495c63f261badd05a78071535e42d366bc894cd91e4c3916f0a9e8293bd3ddd9","cross_cats_sorted":["eess.IV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T18:00:04Z","title_canon_sha256":"62b0c0fec9f74e54e94c22e24a3d3384f3cc7ecbf4e9d9066ca53e9ce16c4ecf"},"schema_version":"1.0","source":{"id":"2304.03307","kind":"arxiv","version":1}},"canonical_sha256":"5388878f9b63ac61db9700d980697dddd4fc3b4d0751b63adc099c78f482cdc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5388878f9b63ac61db9700d980697dddd4fc3b4d0751b63adc099c78f482cdc8","first_computed_at":"2026-07-05T05:58:54.603181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:54.603181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jr0ZEDYUGXYEAuh7n2YLuO26pzVI0W6KoDTxDc9fU7546obyUb2IHI5g5de8MFtD8cbekJ+R1Qj/u6oxTu8uCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:54.603595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6a84612f1e47aeccf330931f35ccf7b6904786f670a587ee04f338ec331f923","sha256:395e71f7218554c01d141651a0a35523d679269766e96825114a6560dd4dd19e"],"state_sha256":"d4f546a27726ab9e19454b3962c9c2c49d3c45f03978b163319cc14b33ada2d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VjhIuJc+vbrDLthUsKlCn1UxCj7BGXWg0lX7HTQPeJKgJ0SIzUA3WGdF0jpRbxueBdZNp0XNpTXpEd16kR4oDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:56:06.952124Z","bundle_sha256":"6369a843471244e3217ef0454e8966a426c951eb454ddd4589872fe311480c3f"}}