{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TDBYX5XCSJ4SP2NBQHSYHUYURZ","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":"aa8643d74d0beed402e0935e82c26190c571f6d4ac1058605fb7c6d2592b619a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T17:51:58Z","title_canon_sha256":"47eded2d291f481c134100eea7ac2ad0c7bd76b242e63df4ef4e7f94a450ae8f"},"schema_version":"1.0","source":{"id":"2307.06930","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06930","created_at":"2026-07-05T08:34:04Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06930v3","created_at":"2026-07-05T08:34:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06930","created_at":"2026-07-05T08:34:04Z"},{"alias_kind":"pith_short_12","alias_value":"TDBYX5XCSJ4S","created_at":"2026-07-05T08:34:04Z"},{"alias_kind":"pith_short_16","alias_value":"TDBYX5XCSJ4SP2NB","created_at":"2026-07-05T08:34:04Z"},{"alias_kind":"pith_short_8","alias_value":"TDBYX5XC","created_at":"2026-07-05T08:34:04Z"}],"graph_snapshots":[{"event_id":"sha256:245eb985b1a46476d248d4267068cf9e2c922aa94f46672bb6805009e8291e8b","target":"graph","created_at":"2026-07-05T08:34:04Z","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/2307.06930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modular vision-language models (Vision-LLMs) align pretrained image encoders with (frozen) large language models (LLMs) and post-hoc condition LLMs to `understand' the image input. With the abundance of readily available high-quality English image-text data as well as strong monolingual English LLMs, the research focus has been on English-only Vision-LLMs. Multilingual vision-language models are still predominantly obtained via expensive end-to-end pretraining, resulting in comparatively smaller models, trained on limited multilingual image data supplemented with text-only multilingual corpora","authors_text":"Abhay Jain, Goran Glava\\v{s}, Gregor Geigle, Radu Timofte","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T17:51:58Z","title":"mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06930","kind":"arxiv","version":3},"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:d4231d2a45cfc71f2503bf0070f1e12c31f546b40ca995f27d3773300ae2dc13","target":"record","created_at":"2026-07-05T08:34:04Z","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":"aa8643d74d0beed402e0935e82c26190c571f6d4ac1058605fb7c6d2592b619a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T17:51:58Z","title_canon_sha256":"47eded2d291f481c134100eea7ac2ad0c7bd76b242e63df4ef4e7f94a450ae8f"},"schema_version":"1.0","source":{"id":"2307.06930","kind":"arxiv","version":3}},"canonical_sha256":"98c38bf6e2927927e9a181e583d3148e5c29053a24443e4c8cd5eaca8cb9500e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98c38bf6e2927927e9a181e583d3148e5c29053a24443e4c8cd5eaca8cb9500e","first_computed_at":"2026-07-05T08:34:04.434054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:04.434054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aixDkUCIa/hMZvSNaNRiNrLBnYHyn2oPib+td1lxZ7AznEJB37Jl2kxfQ8Qgp3jLT92Y79G2C+zcaV52tTuCDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:04.434498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06930","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4231d2a45cfc71f2503bf0070f1e12c31f546b40ca995f27d3773300ae2dc13","sha256:245eb985b1a46476d248d4267068cf9e2c922aa94f46672bb6805009e8291e8b"],"state_sha256":"18496787b59534650cc43b455bc00cfde0cec9ad06b81fa94f47eefed6101990"}