{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D5UCU5MRHOHUKFVIPM7IH5DYVM","short_pith_number":"pith:D5UCU5MR","schema_version":"1.0","canonical_sha256":"1f682a75913b8f4516a87b3e83f478ab1bdfa2573320929ce8624caba6dbd898","source":{"kind":"arxiv","id":"2310.04914","version":2},"attestation_state":"computed","paper":{"title":"Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Anahita Bhiwandiwalla, Avinash Madasu, Vasudev Lal","submitted_at":"2023-10-07T20:57:54Z","abstract_excerpt":"Foundational multimodal models pre-trained on large scale image-text pairs or video-text pairs or both have shown strong generalization abilities on downstream tasks. However unlike image-text models, pretraining video-text models is always not feasible due to the difficulty in collecting large-scale clean and aligned data, and exponential computational costs involved in the pretraining phase. Therefore, the pertinent question to ask is: Can image-text models be adapted to video tasks and is there any benefit to using these models over pretraining directly on videos? In this work, we focus on "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.04914","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-07T20:57:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bc5724572777492cdefa73992b42ee726d03ed20a597f03188f7260ddf534482","abstract_canon_sha256":"8e6151e2ed9e10513c89b4318ae60d484ff4baa0b309273280ee8ee39873014a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:47.167717Z","signature_b64":"KdjeRqlTH+5pdFzhxanZGm+wFIdfQAxJ/rz4Nyf7gA7WS4m+BpReJ5tnXV73UX5qo+NZ3Uc1oi7zInnteHa3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f682a75913b8f4516a87b3e83f478ab1bdfa2573320929ce8624caba6dbd898","last_reissued_at":"2026-07-05T07:16:47.167186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:47.167186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Anahita Bhiwandiwalla, Avinash Madasu, Vasudev Lal","submitted_at":"2023-10-07T20:57:54Z","abstract_excerpt":"Foundational multimodal models pre-trained on large scale image-text pairs or video-text pairs or both have shown strong generalization abilities on downstream tasks. However unlike image-text models, pretraining video-text models is always not feasible due to the difficulty in collecting large-scale clean and aligned data, and exponential computational costs involved in the pretraining phase. Therefore, the pertinent question to ask is: Can image-text models be adapted to video tasks and is there any benefit to using these models over pretraining directly on videos? In this work, we focus on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04914","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/2310.04914/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.04914","created_at":"2026-07-05T07:16:47.167243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04914v2","created_at":"2026-07-05T07:16:47.167243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04914","created_at":"2026-07-05T07:16:47.167243+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5UCU5MRHOHU","created_at":"2026-07-05T07:16:47.167243+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5UCU5MRHOHUKFVI","created_at":"2026-07-05T07:16:47.167243+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5UCU5MR","created_at":"2026-07-05T07:16:47.167243+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5UCU5MRHOHUKFVIPM7IH5DYVM","json":"https://pith.science/pith/D5UCU5MRHOHUKFVIPM7IH5DYVM.json","graph_json":"https://pith.science/api/pith-number/D5UCU5MRHOHUKFVIPM7IH5DYVM/graph.json","events_json":"https://pith.science/api/pith-number/D5UCU5MRHOHUKFVIPM7IH5DYVM/events.json","paper":"https://pith.science/paper/D5UCU5MR"},"agent_actions":{"view_html":"https://pith.science/pith/D5UCU5MRHOHUKFVIPM7IH5DYVM","download_json":"https://pith.science/pith/D5UCU5MRHOHUKFVIPM7IH5DYVM.json","view_paper":"https://pith.science/paper/D5UCU5MR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04914&json=true","fetch_graph":"https://pith.science/api/pith-number/D5UCU5MRHOHUKFVIPM7IH5DYVM/graph.json","fetch_events":"https://pith.science/api/pith-number/D5UCU5MRHOHUKFVIPM7IH5DYVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5UCU5MRHOHUKFVIPM7IH5DYVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5UCU5MRHOHUKFVIPM7IH5DYVM/action/storage_attestation","attest_author":"https://pith.science/pith/D5UCU5MRHOHUKFVIPM7IH5DYVM/action/author_attestation","sign_citation":"https://pith.science/pith/D5UCU5MRHOHUKFVIPM7IH5DYVM/action/citation_signature","submit_replication":"https://pith.science/pith/D5UCU5MRHOHUKFVIPM7IH5DYVM/action/replication_record"}},"created_at":"2026-07-05T07:16:47.167243+00:00","updated_at":"2026-07-05T07:16:47.167243+00:00"}