{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:J4HQU52OFLD6A5PKHJXVSA5SW4","short_pith_number":"pith:J4HQU52O","schema_version":"1.0","canonical_sha256":"4f0f0a774e2ac7e075ea3a6f5903b2b7054790568bf1f9d8d2d8fa3681834461","source":{"kind":"arxiv","id":"1908.02265","version":1},"attestation_state":"computed","paper":{"title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Devi Parikh, Dhruv Batra, Jiasen Lu, Stefan Lee","submitted_at":"2019-08-06T17:33:52Z","abstract_excerpt":"We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, pro-cessing both visual and textual inputs in separate streams that interact through co-attentional transformer layers. We pretrain our model through two proxy tasks on the large, automatically collected Conceptual Captions dataset and then transfer it to multiple established vision-and-language tasks -- visual question answering, visual commonsense reasoning, referring"},"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":"1908.02265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T17:33:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"af884a273c34948e37f1617bcfbe8996de53d5dea8320754c422fba468da915d","abstract_canon_sha256":"cfac8e11e9223823f8ef7da42d350fea7abba01470a3c33c2be2b405c3f8c7a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:52.576933Z","signature_b64":"Rd6vx8AvS9GQF5dYKpXaD674qUbCkeAw72Q9esrMXB0C0kQejThejfASmQ11EUPdz0CvRb26yk+wYv6pvFCBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f0f0a774e2ac7e075ea3a6f5903b2b7054790568bf1f9d8d2d8fa3681834461","last_reissued_at":"2026-07-04T23:51:52.576434Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:52.576434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Devi Parikh, Dhruv Batra, Jiasen Lu, Stefan Lee","submitted_at":"2019-08-06T17:33:52Z","abstract_excerpt":"We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, pro-cessing both visual and textual inputs in separate streams that interact through co-attentional transformer layers. We pretrain our model through two proxy tasks on the large, automatically collected Conceptual Captions dataset and then transfer it to multiple established vision-and-language tasks -- visual question answering, visual commonsense reasoning, referring"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02265","kind":"arxiv","version":1},"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/1908.02265/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":"1908.02265","created_at":"2026-07-04T23:51:52.576500+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.02265v1","created_at":"2026-07-04T23:51:52.576500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02265","created_at":"2026-07-04T23:51:52.576500+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4HQU52OFLD6","created_at":"2026-07-04T23:51:52.576500+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4HQU52OFLD6A5PK","created_at":"2026-07-04T23:51:52.576500+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4HQU52O","created_at":"2026-07-04T23:51:52.576500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11074","citing_title":"Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24020","citing_title":"Machine Intelligence that Understands Visual and Linguistic Information and Interacts with Humans and Environments","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27886","citing_title":"A Comparison of Fusion Techniques for Multi-Modal Human Activity Recognition on the HARMES Dataset","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26179","citing_title":"KG-TRACE: A Neuro-Symbolic Framework for Mechanistic Grounding in Antimicrobial Resistance Prediction","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"1908.03557","citing_title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2201.10005","citing_title":"Text and Code Embeddings by Contrastive Pre-Training","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07338","citing_title":"Appear2Meaning: A Cross-Cultural Benchmark for Structured Cultural Metadata Inference from Images","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4","json":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4.json","graph_json":"https://pith.science/api/pith-number/J4HQU52OFLD6A5PKHJXVSA5SW4/graph.json","events_json":"https://pith.science/api/pith-number/J4HQU52OFLD6A5PKHJXVSA5SW4/events.json","paper":"https://pith.science/paper/J4HQU52O"},"agent_actions":{"view_html":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4","download_json":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4.json","view_paper":"https://pith.science/paper/J4HQU52O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.02265&json=true","fetch_graph":"https://pith.science/api/pith-number/J4HQU52OFLD6A5PKHJXVSA5SW4/graph.json","fetch_events":"https://pith.science/api/pith-number/J4HQU52OFLD6A5PKHJXVSA5SW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/action/storage_attestation","attest_author":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/action/author_attestation","sign_citation":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/action/citation_signature","submit_replication":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/action/replication_record"}},"created_at":"2026-07-04T23:51:52.576500+00:00","updated_at":"2026-07-04T23:51:52.576500+00:00"}