{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2YXYLPCCYBMJXO4XMSZDHJ7JT4","short_pith_number":"pith:2YXYLPCC","schema_version":"1.0","canonical_sha256":"d62f85bc42c0589bbb9764b233a7e99f0ae50b89e2c6d8cb3a3df33eec64035c","source":{"kind":"arxiv","id":"2206.01127","version":2},"attestation_state":"computed","paper":{"title":"VL-BEiT: Generative Vision-Language Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Furu Wei, Hangbo Bao, Li Dong, Wenhui Wang","submitted_at":"2022-06-02T16:14:19Z","abstract_excerpt":"We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with a shared Transformer. Specifically, we perform masked vision-language modeling on image-text pairs, masked language modeling on texts, and masked image modeling on images. VL-BEiT is learned from scratch with one unified pretraining task, one shared backbone, and one-stage training. Our method is conceptually simple and empirically effective. Experimental r"},"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":"2206.01127","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:14:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9ef19ff3a59679e11e5ea56400679745af3449d1c3eec34790136761409476de","abstract_canon_sha256":"5246154307357154a71adf795f573162fb62427f06f8fec6948294372acdf26e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:21.303570Z","signature_b64":"wIr6snQR+QTNPUiy+asVyf0z6TqhE1JmJ8mARtLPiWpYD6xIPUpFjsx1iDo8WNlDE8Q72Qn82HNFNrd4SSY5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d62f85bc42c0589bbb9764b233a7e99f0ae50b89e2c6d8cb3a3df33eec64035c","last_reissued_at":"2026-07-05T04:54:21.303130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:21.303130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VL-BEiT: Generative Vision-Language Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Furu Wei, Hangbo Bao, Li Dong, Wenhui Wang","submitted_at":"2022-06-02T16:14:19Z","abstract_excerpt":"We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with a shared Transformer. Specifically, we perform masked vision-language modeling on image-text pairs, masked language modeling on texts, and masked image modeling on images. VL-BEiT is learned from scratch with one unified pretraining task, one shared backbone, and one-stage training. Our method is conceptually simple and empirically effective. Experimental r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01127","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/2206.01127/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":"2206.01127","created_at":"2026-07-05T04:54:21.303186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.01127v2","created_at":"2026-07-05T04:54:21.303186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01127","created_at":"2026-07-05T04:54:21.303186+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YXYLPCCYBMJ","created_at":"2026-07-05T04:54:21.303186+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YXYLPCCYBMJXO4X","created_at":"2026-07-05T04:54:21.303186+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YXYLPCC","created_at":"2026-07-05T04:54:21.303186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00809","citing_title":"Let ViT Speak: Generative Language-Image Pre-training","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00809","citing_title":"Let ViT Speak: Generative Language-Image Pre-training","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4","json":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4.json","graph_json":"https://pith.science/api/pith-number/2YXYLPCCYBMJXO4XMSZDHJ7JT4/graph.json","events_json":"https://pith.science/api/pith-number/2YXYLPCCYBMJXO4XMSZDHJ7JT4/events.json","paper":"https://pith.science/paper/2YXYLPCC"},"agent_actions":{"view_html":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4","download_json":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4.json","view_paper":"https://pith.science/paper/2YXYLPCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.01127&json=true","fetch_graph":"https://pith.science/api/pith-number/2YXYLPCCYBMJXO4XMSZDHJ7JT4/graph.json","fetch_events":"https://pith.science/api/pith-number/2YXYLPCCYBMJXO4XMSZDHJ7JT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/action/storage_attestation","attest_author":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/action/author_attestation","sign_citation":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/action/citation_signature","submit_replication":"https://pith.science/pith/2YXYLPCCYBMJXO4XMSZDHJ7JT4/action/replication_record"}},"created_at":"2026-07-05T04:54:21.303186+00:00","updated_at":"2026-07-05T04:54:21.303186+00:00"}