{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UYJKVUTDIUQ2CBRKC67GCNBR7L","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":"fe3dde449cb407ad1b2c8ec67b0bcfa95b2cac7dadc11cdca75b9aec43f51717","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-15T22:51:21Z","title_canon_sha256":"07e717d4b2b4eaab1e2e9fb59e58be77b61a6fcbfb0234f2ff32f0492f02a146"},"schema_version":"1.0","source":{"id":"1908.05787","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05787","created_at":"2026-07-05T01:53:17Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05787v3","created_at":"2026-07-05T01:53:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05787","created_at":"2026-07-05T01:53:17Z"},{"alias_kind":"pith_short_12","alias_value":"UYJKVUTDIUQ2","created_at":"2026-07-05T01:53:17Z"},{"alias_kind":"pith_short_16","alias_value":"UYJKVUTDIUQ2CBRK","created_at":"2026-07-05T01:53:17Z"},{"alias_kind":"pith_short_8","alias_value":"UYJKVUTD","created_at":"2026-07-05T01:53:17Z"}],"graph_snapshots":[{"event_id":"sha256:6379fe367235ed134d2772bb61634cbec910895d58a619ede034cd911bb5ac6b","target":"graph","created_at":"2026-07-05T01:53:17Z","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/1908.05787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Transformer-based contextual word representations, including BERT and XLNet, have shown state-of-the-art performance in multiple disciplines within NLP. Fine-tuning the trained contextual models on task-specific datasets has been the key to achieving superior performance downstream. While fine-tuning these pre-trained models is straightforward for lexical applications (applications with only language modality), it is not trivial for multimodal language (a growing area in NLP focused on modeling face-to-face communication). Pre-trained models don't have the necessary components to accept","authors_text":"Amir Zadeh, Chengfeng Mao, Ehsan Hoque, Louis-Philippe Morency, Md. Kamrul Hasan, Sangwu Lee, Wasifur Rahman","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-15T22:51:21Z","title":"Integrating Multimodal Information in Large Pretrained Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05787","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":"sha256:2656b2f88075355b9f2283a680b7b7cd6ada2ac48b13899684a3e3941dcc3a25","target":"record","created_at":"2026-07-05T01:53:17Z","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":"fe3dde449cb407ad1b2c8ec67b0bcfa95b2cac7dadc11cdca75b9aec43f51717","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-15T22:51:21Z","title_canon_sha256":"07e717d4b2b4eaab1e2e9fb59e58be77b61a6fcbfb0234f2ff32f0492f02a146"},"schema_version":"1.0","source":{"id":"1908.05787","kind":"arxiv","version":3}},"canonical_sha256":"a612aad2634521a1062a17be613431faf9c7d52f3f1a4d26976ebe21b094c9a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a612aad2634521a1062a17be613431faf9c7d52f3f1a4d26976ebe21b094c9a6","first_computed_at":"2026-07-05T01:53:17.941846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:17.941846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SubJ0YZnaenEGqBm489/59X1+PW8hv9dXGKECLsGxsnBpbJZkBNl7a3hQsEWlnx+oynnvJ+smTQqjkWu8H6jBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:17.942309Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05787","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2656b2f88075355b9f2283a680b7b7cd6ada2ac48b13899684a3e3941dcc3a25","sha256:6379fe367235ed134d2772bb61634cbec910895d58a619ede034cd911bb5ac6b"],"state_sha256":"035d2444a0779b68c32641adf9e7077fd41bc53def43477a7fd1e4bf632df279"}