{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P3CC5WS6SUYO6HXPOZVKJBBO7O","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":"b03b96f20e228747f883e7f005f6764b8b438c4b984b42e04194b44c6876a5a0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T07:11:41Z","title_canon_sha256":"a7dc228a3447c02358747d16f87730966a0af3f15c34932d214c7a03e929f0ee"},"schema_version":"1.0","source":{"id":"2312.16862","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16862","created_at":"2026-07-05T08:34:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16862v3","created_at":"2026-07-05T08:34:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16862","created_at":"2026-07-05T08:34:58Z"},{"alias_kind":"pith_short_12","alias_value":"P3CC5WS6SUYO","created_at":"2026-07-05T08:34:58Z"},{"alias_kind":"pith_short_16","alias_value":"P3CC5WS6SUYO6HXP","created_at":"2026-07-05T08:34:58Z"},{"alias_kind":"pith_short_8","alias_value":"P3CC5WS6","created_at":"2026-07-05T08:34:58Z"}],"graph_snapshots":[{"event_id":"sha256:616a9234cb838dd7c4c5fcacf758f29f4331fddf9157bee5a0138c2d3b721060","target":"graph","created_at":"2026-07-05T08:34:58Z","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/2312.16862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, multimodal large language models (MLLMs) such as GPT-4V have demonstrated remarkable advancements, excelling in a variety of vision-language tasks. Despite their prowess, the closed-source nature and computational demands of such models limit their accessibility and applicability. This study introduces TinyGPT-V, a novel open-source MLLM, designed for efficient training and inference across various vision-language tasks, including image captioning (IC) and visual question answering (VQA). Leveraging a compact yet powerful architecture, TinyGPT-V integrates the Phi-2 language m","authors_text":"Lichao Sun, Weiran Huang, Yanfang Ye, Zhaoxu Li, Zhengqing Yuan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T07:11:41Z","title":"TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16862","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":"sha256:42a20e355aa51c2ab41c1ac6c748bd2469e3983507cda3b88652f2c1f892a334","target":"record","created_at":"2026-07-05T08:34:58Z","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":"b03b96f20e228747f883e7f005f6764b8b438c4b984b42e04194b44c6876a5a0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T07:11:41Z","title_canon_sha256":"a7dc228a3447c02358747d16f87730966a0af3f15c34932d214c7a03e929f0ee"},"schema_version":"1.0","source":{"id":"2312.16862","kind":"arxiv","version":3}},"canonical_sha256":"7ec42eda5e9530ef1eef766aa4842efb94601d20c44ea5429f372981c40795e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ec42eda5e9530ef1eef766aa4842efb94601d20c44ea5429f372981c40795e1","first_computed_at":"2026-07-05T08:34:58.455202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:58.455202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HCIIShNPcfP83apBnsIhvo43xB0JMHyRNV9IKd2CyazkAEYOQ36Fb1pxv+tI9VxCnJuLpeanxGCBKvPgrvyaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:58.455693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16862","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42a20e355aa51c2ab41c1ac6c748bd2469e3983507cda3b88652f2c1f892a334","sha256:616a9234cb838dd7c4c5fcacf758f29f4331fddf9157bee5a0138c2d3b721060"],"state_sha256":"89816180640559f0b5171fb9186fed891c054775d1d7d8e52d940199482eedc8"}