{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E7FGVK7TESLPH7RIUHVEUJN5GW","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":"3335f07c053f6fdfc6c1c545c3c483ff57eb4f69f48e7e4f945835ed2c943fba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T09:39:17Z","title_canon_sha256":"3626107022ef331e60795f5ff0ba0c02d1030f782f0c3216ddf50141473ba3e4"},"schema_version":"1.0","source":{"id":"2310.08166","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08166","created_at":"2026-07-05T07:07:17Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08166v3","created_at":"2026-07-05T07:07:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08166","created_at":"2026-07-05T07:07:17Z"},{"alias_kind":"pith_short_12","alias_value":"E7FGVK7TESLP","created_at":"2026-07-05T07:07:17Z"},{"alias_kind":"pith_short_16","alias_value":"E7FGVK7TESLPH7RI","created_at":"2026-07-05T07:07:17Z"},{"alias_kind":"pith_short_8","alias_value":"E7FGVK7T","created_at":"2026-07-05T07:07:17Z"}],"graph_snapshots":[{"event_id":"sha256:e4d0e0214ef780f9a64203afa202d84af2a3cf29e9d3bd0d9c4d2c1c751ca49a","target":"graph","created_at":"2026-07-05T07:07:17Z","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/2310.08166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements enlarge the capabilities of large language models (LLMs) in zero-shot image-to-text generation and understanding by integrating multi-modal inputs. However, such success is typically limited to English scenarios due to the lack of large-scale and high-quality non-English multi-modal resources, making it extremely difficult to establish competitive counterparts in other languages. In this paper, we introduce the Ziya-Visual series, a set of bilingual large-scale vision-language models (LVLMs) designed to incorporate visual semantics into LLM for multi-modal dialogue. Compose","authors_text":"Dixiang Zhang, Jiaxing Zhang, Junyu Lu, Pingjian Zhang, Ruyi Gan, Xiaojun Wu, Xinyu Gao, Yan Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T09:39:17Z","title":"Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08166","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":"sha256:9c44efc59858c408f36e09a475bc0b5c1af6e32b4370bb339b8abd39f71f14d3","target":"record","created_at":"2026-07-05T07:07:17Z","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":"3335f07c053f6fdfc6c1c545c3c483ff57eb4f69f48e7e4f945835ed2c943fba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T09:39:17Z","title_canon_sha256":"3626107022ef331e60795f5ff0ba0c02d1030f782f0c3216ddf50141473ba3e4"},"schema_version":"1.0","source":{"id":"2310.08166","kind":"arxiv","version":3}},"canonical_sha256":"27ca6aabf32496f3fe28a1ea4a25bd358aca42186c0b36f8d85a8761d2f62f23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27ca6aabf32496f3fe28a1ea4a25bd358aca42186c0b36f8d85a8761d2f62f23","first_computed_at":"2026-07-05T07:07:17.862087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:17.862087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YymMufTFE0ht+rrQcd/H73iw3R5yr8/TGrzUOnbCDmqpy/FrKR1KEywVDR7NWq5o4sBWLbRWWnGwZUhx2SIFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:17.862604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08166","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c44efc59858c408f36e09a475bc0b5c1af6e32b4370bb339b8abd39f71f14d3","sha256:e4d0e0214ef780f9a64203afa202d84af2a3cf29e9d3bd0d9c4d2c1c751ca49a"],"state_sha256":"f2c819ba2bf76f7629aac8ac23312fde5347030567f7af6514c4422c0f8501bc"}