{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UYJKVUTDIUQ2CBRKC67GCNBR7L","short_pith_number":"pith:UYJKVUTD","schema_version":"1.0","canonical_sha256":"a612aad2634521a1062a17be613431faf9c7d52f3f1a4d26976ebe21b094c9a6","source":{"kind":"arxiv","id":"1908.05787","version":3},"attestation_state":"computed","paper":{"title":"Integrating Multimodal Information in Large Pretrained Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Zadeh, Chengfeng Mao, Ehsan Hoque, Louis-Philippe Morency, Md. Kamrul Hasan, Sangwu Lee, Wasifur Rahman","submitted_at":"2019-08-15T22:51:21Z","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"},"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":"1908.05787","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-15T22:51:21Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"07e717d4b2b4eaab1e2e9fb59e58be77b61a6fcbfb0234f2ff32f0492f02a146","abstract_canon_sha256":"fe3dde449cb407ad1b2c8ec67b0bcfa95b2cac7dadc11cdca75b9aec43f51717"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:17.942309Z","signature_b64":"SubJ0YZnaenEGqBm489/59X1+PW8hv9dXGKECLsGxsnBpbJZkBNl7a3hQsEWlnx+oynnvJ+smTQqjkWu8H6jBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a612aad2634521a1062a17be613431faf9c7d52f3f1a4d26976ebe21b094c9a6","last_reissued_at":"2026-07-05T01:53:17.941846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:17.941846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating Multimodal Information in Large Pretrained Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Zadeh, Chengfeng Mao, Ehsan Hoque, Louis-Philippe Morency, Md. Kamrul Hasan, Sangwu Lee, Wasifur Rahman","submitted_at":"2019-08-15T22:51:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05787","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/1908.05787/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":"1908.05787","created_at":"2026-07-05T01:53:17.941904+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05787v3","created_at":"2026-07-05T01:53:17.941904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05787","created_at":"2026-07-05T01:53:17.941904+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYJKVUTDIUQ2","created_at":"2026-07-05T01:53:17.941904+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYJKVUTDIUQ2CBRK","created_at":"2026-07-05T01:53:17.941904+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYJKVUTD","created_at":"2026-07-05T01:53:17.941904+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/UYJKVUTDIUQ2CBRKC67GCNBR7L","json":"https://pith.science/pith/UYJKVUTDIUQ2CBRKC67GCNBR7L.json","graph_json":"https://pith.science/api/pith-number/UYJKVUTDIUQ2CBRKC67GCNBR7L/graph.json","events_json":"https://pith.science/api/pith-number/UYJKVUTDIUQ2CBRKC67GCNBR7L/events.json","paper":"https://pith.science/paper/UYJKVUTD"},"agent_actions":{"view_html":"https://pith.science/pith/UYJKVUTDIUQ2CBRKC67GCNBR7L","download_json":"https://pith.science/pith/UYJKVUTDIUQ2CBRKC67GCNBR7L.json","view_paper":"https://pith.science/paper/UYJKVUTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05787&json=true","fetch_graph":"https://pith.science/api/pith-number/UYJKVUTDIUQ2CBRKC67GCNBR7L/graph.json","fetch_events":"https://pith.science/api/pith-number/UYJKVUTDIUQ2CBRKC67GCNBR7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYJKVUTDIUQ2CBRKC67GCNBR7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYJKVUTDIUQ2CBRKC67GCNBR7L/action/storage_attestation","attest_author":"https://pith.science/pith/UYJKVUTDIUQ2CBRKC67GCNBR7L/action/author_attestation","sign_citation":"https://pith.science/pith/UYJKVUTDIUQ2CBRKC67GCNBR7L/action/citation_signature","submit_replication":"https://pith.science/pith/UYJKVUTDIUQ2CBRKC67GCNBR7L/action/replication_record"}},"created_at":"2026-07-05T01:53:17.941904+00:00","updated_at":"2026-07-05T01:53:17.941904+00:00"}