{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JFK4VRHCJAHTYIXTT7UOGI7FQO","short_pith_number":"pith:JFK4VRHC","schema_version":"1.0","canonical_sha256":"4955cac4e2480f3c22f39fe8e323e5838bbb9718eb0367a94ad89cac0126c382","source":{"kind":"arxiv","id":"1909.02950","version":2},"attestation_state":"computed","paper":{"title":"Supervised Multimodal Bitransformers for Classifying Images and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Davide Testuggine, Douwe Kiela, Ethan Perez, Hamed Firooz, Suvrat Bhooshan","submitted_at":"2019-09-06T14:59:18Z","abstract_excerpt":"Self-supervised bidirectional transformer models such as BERT have led to dramatic improvements in a wide variety of textual classification tasks. The modern digital world is increasingly multimodal, however, and textual information is often accompanied by other modalities such as images. We introduce a supervised multimodal bitransformer model that fuses information from text and image encoders, and obtain state-of-the-art performance on various multimodal classification benchmark tasks, outperforming strong baselines, including on hard test sets specifically designed to measure multimodal pe"},"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":"1909.02950","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T14:59:18Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"fb61e64a49f5b85922d94842e78bb3911aa0f2487a4572701d8d06c6629cd57f","abstract_canon_sha256":"ff4b7c885d64734a1fcea315556399895021db53b4d83c559bde36fb5b55ecdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:05.221256Z","signature_b64":"yRtSho4sNo7uaZhOxi7zIjeVCxPqYpnINu2vo/FWeADKVTSNVVpzjKykF6GOvTkZjIHHHeMJ4Emrchhxt0wACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4955cac4e2480f3c22f39fe8e323e5838bbb9718eb0367a94ad89cac0126c382","last_reissued_at":"2026-07-05T01:51:05.220800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:05.220800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supervised Multimodal Bitransformers for Classifying Images and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Davide Testuggine, Douwe Kiela, Ethan Perez, Hamed Firooz, Suvrat Bhooshan","submitted_at":"2019-09-06T14:59:18Z","abstract_excerpt":"Self-supervised bidirectional transformer models such as BERT have led to dramatic improvements in a wide variety of textual classification tasks. The modern digital world is increasingly multimodal, however, and textual information is often accompanied by other modalities such as images. We introduce a supervised multimodal bitransformer model that fuses information from text and image encoders, and obtain state-of-the-art performance on various multimodal classification benchmark tasks, outperforming strong baselines, including on hard test sets specifically designed to measure multimodal pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02950","kind":"arxiv","version":2},"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/1909.02950/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":"1909.02950","created_at":"2026-07-05T01:51:05.220858+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02950v2","created_at":"2026-07-05T01:51:05.220858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02950","created_at":"2026-07-05T01:51:05.220858+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFK4VRHCJAHT","created_at":"2026-07-05T01:51:05.220858+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFK4VRHCJAHTYIXT","created_at":"2026-07-05T01:51:05.220858+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFK4VRHC","created_at":"2026-07-05T01:51:05.220858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09907","citing_title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2510.15946","citing_title":"Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"1910.03771","citing_title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","ref_index":160,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04080","citing_title":"Connecting online criminal behavior with machine learning: Using authorship attribution to analyze and link potential online traffickers","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFK4VRHCJAHTYIXTT7UOGI7FQO","json":"https://pith.science/pith/JFK4VRHCJAHTYIXTT7UOGI7FQO.json","graph_json":"https://pith.science/api/pith-number/JFK4VRHCJAHTYIXTT7UOGI7FQO/graph.json","events_json":"https://pith.science/api/pith-number/JFK4VRHCJAHTYIXTT7UOGI7FQO/events.json","paper":"https://pith.science/paper/JFK4VRHC"},"agent_actions":{"view_html":"https://pith.science/pith/JFK4VRHCJAHTYIXTT7UOGI7FQO","download_json":"https://pith.science/pith/JFK4VRHCJAHTYIXTT7UOGI7FQO.json","view_paper":"https://pith.science/paper/JFK4VRHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02950&json=true","fetch_graph":"https://pith.science/api/pith-number/JFK4VRHCJAHTYIXTT7UOGI7FQO/graph.json","fetch_events":"https://pith.science/api/pith-number/JFK4VRHCJAHTYIXTT7UOGI7FQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFK4VRHCJAHTYIXTT7UOGI7FQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFK4VRHCJAHTYIXTT7UOGI7FQO/action/storage_attestation","attest_author":"https://pith.science/pith/JFK4VRHCJAHTYIXTT7UOGI7FQO/action/author_attestation","sign_citation":"https://pith.science/pith/JFK4VRHCJAHTYIXTT7UOGI7FQO/action/citation_signature","submit_replication":"https://pith.science/pith/JFK4VRHCJAHTYIXTT7UOGI7FQO/action/replication_record"}},"created_at":"2026-07-05T01:51:05.220858+00:00","updated_at":"2026-07-05T01:51:05.220858+00:00"}