{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JFK4VRHCJAHTYIXTT7UOGI7FQO","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":"ff4b7c885d64734a1fcea315556399895021db53b4d83c559bde36fb5b55ecdb","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T14:59:18Z","title_canon_sha256":"fb61e64a49f5b85922d94842e78bb3911aa0f2487a4572701d8d06c6629cd57f"},"schema_version":"1.0","source":{"id":"1909.02950","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02950","created_at":"2026-07-05T01:51:05Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02950v2","created_at":"2026-07-05T01:51:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02950","created_at":"2026-07-05T01:51:05Z"},{"alias_kind":"pith_short_12","alias_value":"JFK4VRHCJAHT","created_at":"2026-07-05T01:51:05Z"},{"alias_kind":"pith_short_16","alias_value":"JFK4VRHCJAHTYIXT","created_at":"2026-07-05T01:51:05Z"},{"alias_kind":"pith_short_8","alias_value":"JFK4VRHC","created_at":"2026-07-05T01:51:05Z"}],"graph_snapshots":[{"event_id":"sha256:b44917b866fe5834f0c29163ef60ecf9a45fd6558450ddb6fd2fea27ca9975db","target":"graph","created_at":"2026-07-05T01:51:05Z","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/1909.02950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Davide Testuggine, Douwe Kiela, Ethan Perez, Hamed Firooz, Suvrat Bhooshan","cross_cats":["cs.CV","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T14:59:18Z","title":"Supervised Multimodal Bitransformers for Classifying Images and Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02950","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":"sha256:1c4c1aaefeb30a999768c89050c85e942191e879029cda8334b29fa7cae2d9dd","target":"record","created_at":"2026-07-05T01:51:05Z","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":"ff4b7c885d64734a1fcea315556399895021db53b4d83c559bde36fb5b55ecdb","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T14:59:18Z","title_canon_sha256":"fb61e64a49f5b85922d94842e78bb3911aa0f2487a4572701d8d06c6629cd57f"},"schema_version":"1.0","source":{"id":"1909.02950","kind":"arxiv","version":2}},"canonical_sha256":"4955cac4e2480f3c22f39fe8e323e5838bbb9718eb0367a94ad89cac0126c382","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4955cac4e2480f3c22f39fe8e323e5838bbb9718eb0367a94ad89cac0126c382","first_computed_at":"2026-07-05T01:51:05.220800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:05.220800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yRtSho4sNo7uaZhOxi7zIjeVCxPqYpnINu2vo/FWeADKVTSNVVpzjKykF6GOvTkZjIHHHeMJ4Emrchhxt0wACg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:05.221256Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.02950","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c4c1aaefeb30a999768c89050c85e942191e879029cda8334b29fa7cae2d9dd","sha256:b44917b866fe5834f0c29163ef60ecf9a45fd6558450ddb6fd2fea27ca9975db"],"state_sha256":"15f0e8ed25035d61251c2ce74ad0da534dffd11b86c5974ef32aaab36f9b5728"}