{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZYTAPYSC2TCIMOFIMRMIAHR3HG","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":"9d08d1aea34bc27006cbf08bf99983d5a35121f72abcb8ed87b598a57f90f6aa","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-22T16:55:04Z","title_canon_sha256":"f172fd4ec3481cf4290bf19bacdb4b4f6b9d723a5cf013793f321e357d471781"},"schema_version":"1.0","source":{"id":"2208.10442","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.10442","created_at":"2026-07-05T04:53:30Z"},{"alias_kind":"arxiv_version","alias_value":"2208.10442v2","created_at":"2026-07-05T04:53:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10442","created_at":"2026-07-05T04:53:30Z"},{"alias_kind":"pith_short_12","alias_value":"ZYTAPYSC2TCI","created_at":"2026-07-05T04:53:30Z"},{"alias_kind":"pith_short_16","alias_value":"ZYTAPYSC2TCIMOFI","created_at":"2026-07-05T04:53:30Z"},{"alias_kind":"pith_short_8","alias_value":"ZYTAPYSC","created_at":"2026-07-05T04:53:30Z"}],"graph_snapshots":[{"event_id":"sha256:b01d562c49e7a15d57e0ecfc4a6e5cfca1efd2e30e2d815a2809980fc4eb8bb3","target":"graph","created_at":"2026-07-05T04:53:30Z","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/2208.10442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language tasks. Specifically, we advance the big convergence from three aspects: backbone architecture, pretraining task, and model scaling up. We introduce Multiway Transformers for general-purpose modeling, where the modular architecture enables both deep fusion and modality-specific encoding. Based on the shared backbone, we perform masked \"language\" model","authors_text":"Furu Wei, Hangbo Bao, Johan Bjorck, Kriti Aggarwal, Li Dong, Owais Khan Mohammed, Qiang Liu, Saksham Singhal, Subhojit Som, Wenhui Wang, Zhiliang Peng","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-22T16:55:04Z","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10442","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":"sha256:57cd2e5708ec56238a518b37ccbbe2351fbba64f8028b5ce012cffe1bac91247","target":"record","created_at":"2026-07-05T04:53:30Z","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":"9d08d1aea34bc27006cbf08bf99983d5a35121f72abcb8ed87b598a57f90f6aa","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-22T16:55:04Z","title_canon_sha256":"f172fd4ec3481cf4290bf19bacdb4b4f6b9d723a5cf013793f321e357d471781"},"schema_version":"1.0","source":{"id":"2208.10442","kind":"arxiv","version":2}},"canonical_sha256":"ce2607e242d4c48638a86458801e3b3993a1bdc054f381c7e9f11dda2498a8dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce2607e242d4c48638a86458801e3b3993a1bdc054f381c7e9f11dda2498a8dd","first_computed_at":"2026-07-05T04:53:30.025098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:53:30.025098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q1KOsSESMtnamqT5DVWVezLI+3AhYCpxb+dkQGR+w3wNNb3icZlLH7Ec8gPbq+ssFTekSueQXBTvrQXRhXQWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:53:30.025499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.10442","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57cd2e5708ec56238a518b37ccbbe2351fbba64f8028b5ce012cffe1bac91247","sha256:b01d562c49e7a15d57e0ecfc4a6e5cfca1efd2e30e2d815a2809980fc4eb8bb3"],"state_sha256":"30693ee15a5df7a5312aba3fb18ff18b47ffd016f79bee5694497087379e1114"}