{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2YXYLPCCYBMJXO4XMSZDHJ7JT4","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":"5246154307357154a71adf795f573162fb62427f06f8fec6948294372acdf26e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:14:19Z","title_canon_sha256":"9ef19ff3a59679e11e5ea56400679745af3449d1c3eec34790136761409476de"},"schema_version":"1.0","source":{"id":"2206.01127","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01127","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01127v2","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01127","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"pith_short_12","alias_value":"2YXYLPCCYBMJ","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"pith_short_16","alias_value":"2YXYLPCCYBMJXO4X","created_at":"2026-07-05T04:54:21Z"},{"alias_kind":"pith_short_8","alias_value":"2YXYLPCC","created_at":"2026-07-05T04:54:21Z"}],"graph_snapshots":[{"event_id":"sha256:810dbd82bd3e2bb3d12f1a0fc6b7b5b747ecae713c0a077c349b736b882a1f6e","target":"graph","created_at":"2026-07-05T04:54:21Z","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/2206.01127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Furu Wei, Hangbo Bao, Li Dong, Wenhui Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:14:19Z","title":"VL-BEiT: Generative Vision-Language Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01127","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":"sha256:19ff7f4381a72620b263fb94dfb4385dd2868e40e4105d0225901777ca65d809","target":"record","created_at":"2026-07-05T04:54:21Z","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":"5246154307357154a71adf795f573162fb62427f06f8fec6948294372acdf26e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:14:19Z","title_canon_sha256":"9ef19ff3a59679e11e5ea56400679745af3449d1c3eec34790136761409476de"},"schema_version":"1.0","source":{"id":"2206.01127","kind":"arxiv","version":2}},"canonical_sha256":"d62f85bc42c0589bbb9764b233a7e99f0ae50b89e2c6d8cb3a3df33eec64035c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d62f85bc42c0589bbb9764b233a7e99f0ae50b89e2c6d8cb3a3df33eec64035c","first_computed_at":"2026-07-05T04:54:21.303130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:54:21.303130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wIr6snQR+QTNPUiy+asVyf0z6TqhE1JmJ8mARtLPiWpYD6xIPUpFjsx1iDo8WNlDE8Q72Qn82HNFNrd4SSY5AA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:54:21.303570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.01127","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19ff7f4381a72620b263fb94dfb4385dd2868e40e4105d0225901777ca65d809","sha256:810dbd82bd3e2bb3d12f1a0fc6b7b5b747ecae713c0a077c349b736b882a1f6e"],"state_sha256":"2d24e5c2ec62f806433a7387edb84556ada708ec2c1bac7f970d172021af45b5"}