{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F4IT654TPM7MXM4FMFASHB3E35","short_pith_number":"pith:F4IT654T","schema_version":"1.0","canonical_sha256":"2f113f77937b3ecbb3856141238764df5d7b36b899bed2d35e1bc4972d9e67e9","source":{"kind":"arxiv","id":"2411.19103","version":1},"attestation_state":"computed","paper":{"title":"VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Daeyoung Kim, Jeongho Ju, Sunyoung Park, Youngjune Kim","submitted_at":"2024-11-28T12:38:42Z","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"},"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":"2411.19103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T12:38:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"13a8861725ec1ea2daa9876d28f77a09eebad30aad892d99541e5cf66316309f","abstract_canon_sha256":"57b4950fd9e78b9bc7b7ef94a1635f021f5073a9c9eb82c41a790b6a1287c471"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:57.225488Z","signature_b64":"GPkNOpcYDVO4TbHnscwt/R7U1Z9XLu+GJWWfXicv/ndzVHdIcc5h2KZfONJhDNJ9AKHtROPfgwlW+TxCkFGsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f113f77937b3ecbb3856141238764df5d7b36b899bed2d35e1bc4972d9e67e9","last_reissued_at":"2026-07-05T09:41:57.224994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:57.224994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Daeyoung Kim, Jeongho Ju, Sunyoung Park, Youngjune Kim","submitted_at":"2024-11-28T12:38:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19103","kind":"arxiv","version":1},"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/2411.19103/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":"2411.19103","created_at":"2026-07-05T09:41:57.225052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19103v1","created_at":"2026-07-05T09:41:57.225052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19103","created_at":"2026-07-05T09:41:57.225052+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4IT654TPM7M","created_at":"2026-07-05T09:41:57.225052+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4IT654TPM7MXM4F","created_at":"2026-07-05T09:41:57.225052+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4IT654T","created_at":"2026-07-05T09:41:57.225052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11490","citing_title":"Anthropogenic Regional Adaptation in Multimodal Vision-Language Model","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4IT654TPM7MXM4FMFASHB3E35","json":"https://pith.science/pith/F4IT654TPM7MXM4FMFASHB3E35.json","graph_json":"https://pith.science/api/pith-number/F4IT654TPM7MXM4FMFASHB3E35/graph.json","events_json":"https://pith.science/api/pith-number/F4IT654TPM7MXM4FMFASHB3E35/events.json","paper":"https://pith.science/paper/F4IT654T"},"agent_actions":{"view_html":"https://pith.science/pith/F4IT654TPM7MXM4FMFASHB3E35","download_json":"https://pith.science/pith/F4IT654TPM7MXM4FMFASHB3E35.json","view_paper":"https://pith.science/paper/F4IT654T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19103&json=true","fetch_graph":"https://pith.science/api/pith-number/F4IT654TPM7MXM4FMFASHB3E35/graph.json","fetch_events":"https://pith.science/api/pith-number/F4IT654TPM7MXM4FMFASHB3E35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4IT654TPM7MXM4FMFASHB3E35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4IT654TPM7MXM4FMFASHB3E35/action/storage_attestation","attest_author":"https://pith.science/pith/F4IT654TPM7MXM4FMFASHB3E35/action/author_attestation","sign_citation":"https://pith.science/pith/F4IT654TPM7MXM4FMFASHB3E35/action/citation_signature","submit_replication":"https://pith.science/pith/F4IT654TPM7MXM4FMFASHB3E35/action/replication_record"}},"created_at":"2026-07-05T09:41:57.225052+00:00","updated_at":"2026-07-05T09:41:57.225052+00:00"}