{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YJQOPIAA337IUZKFJMJGUBDYSQ","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":"7ee828f8810f553a4035d292116b6ca00bebed6897ec1cfe31daa02a2ee9d05b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-16T19:13:11Z","title_canon_sha256":"fc6f820325fca49dcd8d133bd11fa7b08a4153d41bc891707b5d48881a0229a4"},"schema_version":"1.0","source":{"id":"2305.09758","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09758","created_at":"2026-07-05T07:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09758v3","created_at":"2026-07-05T07:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09758","created_at":"2026-07-05T07:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"YJQOPIAA337I","created_at":"2026-07-05T07:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"YJQOPIAA337IUZKF","created_at":"2026-07-05T07:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"YJQOPIAA","created_at":"2026-07-05T07:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:b66f39fc2345867703574df95e194cc839b35be762369df03a1621d31fca0ec7","target":"graph","created_at":"2026-07-05T07:05:08Z","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/2305.09758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aanisha Bhattacharya, Balaji Krishnamurthy, Changyou Chen, Rajiv Ratn Shah, Yaman K Singla","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-16T19:13:11Z","title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09758","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":"sha256:544f67443c54e28e785786328113e086f6db525e1566991e20822485af69f1c8","target":"record","created_at":"2026-07-05T07:05:08Z","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":"7ee828f8810f553a4035d292116b6ca00bebed6897ec1cfe31daa02a2ee9d05b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-16T19:13:11Z","title_canon_sha256":"fc6f820325fca49dcd8d133bd11fa7b08a4153d41bc891707b5d48881a0229a4"},"schema_version":"1.0","source":{"id":"2305.09758","kind":"arxiv","version":3}},"canonical_sha256":"c260e7a000defe8a65454b126a047894023e6ede153ca293c04a3de772eaec77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c260e7a000defe8a65454b126a047894023e6ede153ca293c04a3de772eaec77","first_computed_at":"2026-07-05T07:05:08.552621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:08.552621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0kh0uX2wUOgjmg+5te3kCRIJ303R2RjNvCT1D5IAvfypNL+/aPRm2NWHfcCRr+8hwH4rg6Xggo8xCNnbPQ90Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:08.553039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.09758","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:544f67443c54e28e785786328113e086f6db525e1566991e20822485af69f1c8","sha256:b66f39fc2345867703574df95e194cc839b35be762369df03a1621d31fca0ec7"],"state_sha256":"c44e691e6951b1a2988f32eaf17f427533892451c2e5406c3fd027a73c123139"}