{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FPIGQHMJJEARWLH26H6Z4M5KO7","short_pith_number":"pith:FPIGQHMJ","schema_version":"1.0","canonical_sha256":"2bd0681d8949011b2cfaf1fd9e33aa77cef9ee2c18962f3c197a2b49549b1296","source":{"kind":"arxiv","id":"1908.07490","version":3},"attestation_state":"computed","paper":{"title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hao Tan, Mohit Bansal","submitted_at":"2019-08-20T17:05:18Z","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"},"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":"1908.07490","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-20T17:05:18Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"56f170560e62ce0c2ed9e81a55f494e660dd189074fbd5837a4189e5094fec07","abstract_canon_sha256":"c7fa23ea874f6d8c80a96482fd614e138b9d60f301f82fdb303c53583cad2e66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:50.871039Z","signature_b64":"GqrvbrllNkH9b4SRcmEs/oCPbTbC9CCUojOUPU/WoYaL0OVSf1LrgFU/jLoQNq2b7Mseb8XxqjexG4E5u5H/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bd0681d8949011b2cfaf1fd9e33aa77cef9ee2c18962f3c197a2b49549b1296","last_reissued_at":"2026-07-05T00:23:50.870545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:50.870545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hao Tan, Mohit Bansal","submitted_at":"2019-08-20T17:05:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07490","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/1908.07490/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":"1908.07490","created_at":"2026-07-05T00:23:50.870605+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07490v3","created_at":"2026-07-05T00:23:50.870605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07490","created_at":"2026-07-05T00:23:50.870605+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPIGQHMJJEAR","created_at":"2026-07-05T00:23:50.870605+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPIGQHMJJEARWLH2","created_at":"2026-07-05T00:23:50.870605+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPIGQHMJ","created_at":"2026-07-05T00:23:50.870605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06424","citing_title":"XRFormer: Multiscale Tokenization for XRF Representation Learning","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19036","citing_title":"Geometric and Stochastic Analysis of Discontinuities in Sparse Mixture-of-Experts","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10571","citing_title":"Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07032","citing_title":"Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02168","citing_title":"Disentanglement-Based Equivariant Learning for Compositional VQA","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2412.08110","citing_title":"The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21059","citing_title":"Multimodal LLMs under Pairwise Modalities","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13305","citing_title":"Boosting Team Modeling through Tempo-Relational Representation Learning","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2508.04427","citing_title":"Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06964","citing_title":"Adversarial Video Promotion Against Text-to-Video Retrieval","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2402.03766","citing_title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2303.08128","citing_title":"ViperGPT: Visual Inference via Python Execution for Reasoning","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03454","citing_title":"Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2209.06794","citing_title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2410.22313","citing_title":"Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01917","citing_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04400","citing_title":"LRM: Large Reconstruction Model for Single Image to 3D","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04504","citing_title":"SpecPL: Disentangling Spectral Granularity for Prompt Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01359","citing_title":"Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18460","citing_title":"Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06285","citing_title":"Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPIGQHMJJEARWLH26H6Z4M5KO7","json":"https://pith.science/pith/FPIGQHMJJEARWLH26H6Z4M5KO7.json","graph_json":"https://pith.science/api/pith-number/FPIGQHMJJEARWLH26H6Z4M5KO7/graph.json","events_json":"https://pith.science/api/pith-number/FPIGQHMJJEARWLH26H6Z4M5KO7/events.json","paper":"https://pith.science/paper/FPIGQHMJ"},"agent_actions":{"view_html":"https://pith.science/pith/FPIGQHMJJEARWLH26H6Z4M5KO7","download_json":"https://pith.science/pith/FPIGQHMJJEARWLH26H6Z4M5KO7.json","view_paper":"https://pith.science/paper/FPIGQHMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07490&json=true","fetch_graph":"https://pith.science/api/pith-number/FPIGQHMJJEARWLH26H6Z4M5KO7/graph.json","fetch_events":"https://pith.science/api/pith-number/FPIGQHMJJEARWLH26H6Z4M5KO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPIGQHMJJEARWLH26H6Z4M5KO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPIGQHMJJEARWLH26H6Z4M5KO7/action/storage_attestation","attest_author":"https://pith.science/pith/FPIGQHMJJEARWLH26H6Z4M5KO7/action/author_attestation","sign_citation":"https://pith.science/pith/FPIGQHMJJEARWLH26H6Z4M5KO7/action/citation_signature","submit_replication":"https://pith.science/pith/FPIGQHMJJEARWLH26H6Z4M5KO7/action/replication_record"}},"created_at":"2026-07-05T00:23:50.870605+00:00","updated_at":"2026-07-05T00:23:50.870605+00:00"}