{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YJQOPIAA337IUZKFJMJGUBDYSQ","short_pith_number":"pith:YJQOPIAA","schema_version":"1.0","canonical_sha256":"c260e7a000defe8a65454b126a047894023e6ede153ca293c04a3de772eaec77","source":{"kind":"arxiv","id":"2305.09758","version":3},"attestation_state":"computed","paper":{"title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aanisha Bhattacharya, Balaji Krishnamurthy, Changyou Chen, Rajiv Ratn Shah, Yaman K Singla","submitted_at":"2023-05-16T19:13:11Z","abstract_excerpt":"Multimedia content, such as advertisements and story videos, exhibit a rich blend of creativity and multiple modalities. They incorporate elements like text, visuals, audio, and storytelling techniques, employing devices like emotions, symbolism, and slogans to convey meaning. There is a dearth of large annotated training datasets in the multimedia domain hindering the development of supervised learning models with satisfactory performance for real-world applications. On the other hand, the rise of large language models (LLMs) has witnessed remarkable zero-shot performance in various natural l"},"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":"2305.09758","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-16T19:13:11Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fc6f820325fca49dcd8d133bd11fa7b08a4153d41bc891707b5d48881a0229a4","abstract_canon_sha256":"7ee828f8810f553a4035d292116b6ca00bebed6897ec1cfe31daa02a2ee9d05b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:08.553039Z","signature_b64":"0kh0uX2wUOgjmg+5te3kCRIJ303R2RjNvCT1D5IAvfypNL+/aPRm2NWHfcCRr+8hwH4rg6Xggo8xCNnbPQ90Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c260e7a000defe8a65454b126a047894023e6ede153ca293c04a3de772eaec77","last_reissued_at":"2026-07-05T07:05:08.552621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:08.552621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aanisha Bhattacharya, Balaji Krishnamurthy, Changyou Chen, Rajiv Ratn Shah, Yaman K Singla","submitted_at":"2023-05-16T19:13:11Z","abstract_excerpt":"Multimedia content, such as advertisements and story videos, exhibit a rich blend of creativity and multiple modalities. They incorporate elements like text, visuals, audio, and storytelling techniques, employing devices like emotions, symbolism, and slogans to convey meaning. There is a dearth of large annotated training datasets in the multimedia domain hindering the development of supervised learning models with satisfactory performance for real-world applications. On the other hand, the rise of large language models (LLMs) has witnessed remarkable zero-shot performance in various natural l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09758","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/2305.09758/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":"2305.09758","created_at":"2026-07-05T07:05:08.552685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.09758v3","created_at":"2026-07-05T07:05:08.552685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09758","created_at":"2026-07-05T07:05:08.552685+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJQOPIAA337I","created_at":"2026-07-05T07:05:08.552685+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJQOPIAA337IUZKF","created_at":"2026-07-05T07:05:08.552685+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJQOPIAA","created_at":"2026-07-05T07:05:08.552685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08158","citing_title":"How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJQOPIAA337IUZKFJMJGUBDYSQ","json":"https://pith.science/pith/YJQOPIAA337IUZKFJMJGUBDYSQ.json","graph_json":"https://pith.science/api/pith-number/YJQOPIAA337IUZKFJMJGUBDYSQ/graph.json","events_json":"https://pith.science/api/pith-number/YJQOPIAA337IUZKFJMJGUBDYSQ/events.json","paper":"https://pith.science/paper/YJQOPIAA"},"agent_actions":{"view_html":"https://pith.science/pith/YJQOPIAA337IUZKFJMJGUBDYSQ","download_json":"https://pith.science/pith/YJQOPIAA337IUZKFJMJGUBDYSQ.json","view_paper":"https://pith.science/paper/YJQOPIAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.09758&json=true","fetch_graph":"https://pith.science/api/pith-number/YJQOPIAA337IUZKFJMJGUBDYSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YJQOPIAA337IUZKFJMJGUBDYSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJQOPIAA337IUZKFJMJGUBDYSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJQOPIAA337IUZKFJMJGUBDYSQ/action/storage_attestation","attest_author":"https://pith.science/pith/YJQOPIAA337IUZKFJMJGUBDYSQ/action/author_attestation","sign_citation":"https://pith.science/pith/YJQOPIAA337IUZKFJMJGUBDYSQ/action/citation_signature","submit_replication":"https://pith.science/pith/YJQOPIAA337IUZKFJMJGUBDYSQ/action/replication_record"}},"created_at":"2026-07-05T07:05:08.552685+00:00","updated_at":"2026-07-05T07:05:08.552685+00:00"}