{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F4IT654TPM7MXM4FMFASHB3E35","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":"57b4950fd9e78b9bc7b7ef94a1635f021f5073a9c9eb82c41a790b6a1287c471","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T12:38:42Z","title_canon_sha256":"13a8861725ec1ea2daa9876d28f77a09eebad30aad892d99541e5cf66316309f"},"schema_version":"1.0","source":{"id":"2411.19103","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19103","created_at":"2026-07-05T09:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19103v1","created_at":"2026-07-05T09:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19103","created_at":"2026-07-05T09:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"F4IT654TPM7M","created_at":"2026-07-05T09:41:57Z"},{"alias_kind":"pith_short_16","alias_value":"F4IT654TPM7MXM4F","created_at":"2026-07-05T09:41:57Z"},{"alias_kind":"pith_short_8","alias_value":"F4IT654T","created_at":"2026-07-05T09:41:57Z"}],"graph_snapshots":[{"event_id":"sha256:006b9d5b2a51444a4ebe0b862cc46e7056759befa19fab1bfa79a02b6bd8928d","target":"graph","created_at":"2026-07-05T09:41:57Z","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/2411.19103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce an open-source Korean-English vision-language model (VLM), VARCO-VISION. We incorporate a step-by-step training strategy that allows a model learn both linguistic and visual information while preserving the backbone model's knowledge. Our model demonstrates outstanding performance in diverse settings requiring bilingual image-text understanding and generation abilities compared to models of similar size. VARCO-VISION is also capable of grounding, referring, and OCR, expanding its usage and potential applications for real-world scenarios. In addition to the model, we","authors_text":"Daeyoung Kim, Jeongho Ju, Sunyoung Park, Youngjune Kim","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T12:38:42Z","title":"VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19103","kind":"arxiv","version":1},"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":"sha256:11eb7b24fb6a0e240cd6fde53e434e5e50dd556557f13da0963874927c751c76","target":"record","created_at":"2026-07-05T09:41:57Z","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":"57b4950fd9e78b9bc7b7ef94a1635f021f5073a9c9eb82c41a790b6a1287c471","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T12:38:42Z","title_canon_sha256":"13a8861725ec1ea2daa9876d28f77a09eebad30aad892d99541e5cf66316309f"},"schema_version":"1.0","source":{"id":"2411.19103","kind":"arxiv","version":1}},"canonical_sha256":"2f113f77937b3ecbb3856141238764df5d7b36b899bed2d35e1bc4972d9e67e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f113f77937b3ecbb3856141238764df5d7b36b899bed2d35e1bc4972d9e67e9","first_computed_at":"2026-07-05T09:41:57.224994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:57.224994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GPkNOpcYDVO4TbHnscwt/R7U1Z9XLu+GJWWfXicv/ndzVHdIcc5h2KZfONJhDNJ9AKHtROPfgwlW+TxCkFGsAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:57.225488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19103","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11eb7b24fb6a0e240cd6fde53e434e5e50dd556557f13da0963874927c751c76","sha256:006b9d5b2a51444a4ebe0b862cc46e7056759befa19fab1bfa79a02b6bd8928d"],"state_sha256":"700a70ad0e507876cdf3e2c79a05d2e7852c2686d22a1074fbe3f77f13adebba"}