{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FPIGQHMJJEARWLH26H6Z4M5KO7","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":"c7fa23ea874f6d8c80a96482fd614e138b9d60f301f82fdb303c53583cad2e66","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-20T17:05:18Z","title_canon_sha256":"56f170560e62ce0c2ed9e81a55f494e660dd189074fbd5837a4189e5094fec07"},"schema_version":"1.0","source":{"id":"1908.07490","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.07490","created_at":"2026-07-05T00:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"1908.07490v3","created_at":"2026-07-05T00:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07490","created_at":"2026-07-05T00:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"FPIGQHMJJEAR","created_at":"2026-07-05T00:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"FPIGQHMJJEARWLH2","created_at":"2026-07-05T00:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"FPIGQHMJ","created_at":"2026-07-05T00:23:50Z"}],"graph_snapshots":[{"event_id":"sha256:08fa7710fd69b733e06335c54e63af56694d6d54cd4cd2bf4bfe6c2a43a2ccea","target":"graph","created_at":"2026-07-05T00:23:50Z","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/1908.07490/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment and relationships between these two modalities. We thus propose the LXMERT (Learning Cross-Modality Encoder Representations from Transformers) framework to learn these vision-and-language connections. In LXMERT, we build a large-scale Transformer model that consists of three encoders: an object relationship encoder, a language encoder, and a cross-modality encoder. Next, to endow our model with the capability of connecting vision and language semantics, we pre-tr","authors_text":"Hao Tan, Mohit Bansal","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-20T17:05:18Z","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07490","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":"sha256:7a485db7ce1c382b97d032ec11be59435326d3d03d83ba08275a07e77a56d38a","target":"record","created_at":"2026-07-05T00:23:50Z","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":"c7fa23ea874f6d8c80a96482fd614e138b9d60f301f82fdb303c53583cad2e66","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-20T17:05:18Z","title_canon_sha256":"56f170560e62ce0c2ed9e81a55f494e660dd189074fbd5837a4189e5094fec07"},"schema_version":"1.0","source":{"id":"1908.07490","kind":"arxiv","version":3}},"canonical_sha256":"2bd0681d8949011b2cfaf1fd9e33aa77cef9ee2c18962f3c197a2b49549b1296","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bd0681d8949011b2cfaf1fd9e33aa77cef9ee2c18962f3c197a2b49549b1296","first_computed_at":"2026-07-05T00:23:50.870545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:23:50.870545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GqrvbrllNkH9b4SRcmEs/oCPbTbC9CCUojOUPU/WoYaL0OVSf1LrgFU/jLoQNq2b7Mseb8XxqjexG4E5u5H/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:23:50.871039Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.07490","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a485db7ce1c382b97d032ec11be59435326d3d03d83ba08275a07e77a56d38a","sha256:08fa7710fd69b733e06335c54e63af56694d6d54cd4cd2bf4bfe6c2a43a2ccea"],"state_sha256":"a1322cc1f3e55a868194226f367fa94ae81f07b8b9bbe04b8735aa67a0b4344b"}