{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VTKGCTJYXYOHDCOQ2JNX4OIYHD","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":"a8b5348d17b4ee578d19f246764747331861f280414a3fe6c74c3f35cd3c90d8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T17:54:32Z","title_canon_sha256":"8e0290b4ee08b909c911351f522a62d66ec2450b7f83f2970f5046f1a4478a29"},"schema_version":"1.0","source":{"id":"2303.15430","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15430","created_at":"2026-07-05T05:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15430v2","created_at":"2026-07-05T05:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15430","created_at":"2026-07-05T05:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"VTKGCTJYXYOH","created_at":"2026-07-05T05:56:04Z"},{"alias_kind":"pith_short_16","alias_value":"VTKGCTJYXYOHDCOQ","created_at":"2026-07-05T05:56:04Z"},{"alias_kind":"pith_short_8","alias_value":"VTKGCTJY","created_at":"2026-07-05T05:56:04Z"}],"graph_snapshots":[{"event_id":"sha256:c8147122abebb2e3b1a771df344d35a26a1ccea2c08bb7344dc0954a4c838450","target":"graph","created_at":"2026-07-05T05:56:04Z","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/2303.15430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained large language models have recently achieved ground-breaking performance in a wide variety of language understanding tasks. However, the same model can not be applied to multimodal behavior understanding tasks (e.g., video sentiment/humor detection) unless non-verbal features (e.g., acoustic and visual) can be integrated with language. Jointly modeling multiple modalities significantly increases the model complexity, and makes the training process data-hungry. While an enormous amount of text data is available via the web, collecting large-scale multimodal behavioral video datasets","authors_text":"Ehsan Hoque, Iftekhar Naim, Md Kamrul Hasan, Md Saiful Islam, Mohammed Ibrahim Khan, Sangwu Lee, Wasifur Rahman","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T17:54:32Z","title":"TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15430","kind":"arxiv","version":2},"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:a4ba59e52a23a7c63b2cda4808adb5c91a06945b6c8866acac85045aa699f334","target":"record","created_at":"2026-07-05T05:56:04Z","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":"a8b5348d17b4ee578d19f246764747331861f280414a3fe6c74c3f35cd3c90d8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T17:54:32Z","title_canon_sha256":"8e0290b4ee08b909c911351f522a62d66ec2450b7f83f2970f5046f1a4478a29"},"schema_version":"1.0","source":{"id":"2303.15430","kind":"arxiv","version":2}},"canonical_sha256":"acd4614d38be1c7189d0d25b7e391838cc67b62484fd9a16a0fc91f0dfd0c599","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acd4614d38be1c7189d0d25b7e391838cc67b62484fd9a16a0fc91f0dfd0c599","first_computed_at":"2026-07-05T05:56:04.236005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:04.236005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ypZdEKGTfQxG4i5zFLKDMFrQyW/xWoVxhYorTWqYsv1popnlnqJbNhnN0XHFyrdj7S2hr8qrWHW3spr8flYXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:04.236514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.15430","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4ba59e52a23a7c63b2cda4808adb5c91a06945b6c8866acac85045aa699f334","sha256:c8147122abebb2e3b1a771df344d35a26a1ccea2c08bb7344dc0954a4c838450"],"state_sha256":"b4912d5f8f2c50361697b9220eed031f89e186ebd1a0ab2055139d74dc20668c"}