{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:A7OSKEVFNZJBTCBFWD6PUALQUL","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":"0eb65c7995bfa093c780aee935a1e30b56fcc1d74d0bdc37f56a0c6fb09fbf95","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T14:04:30Z","title_canon_sha256":"41779df4b5e12c77aca5799c6b96e3f4c599b72fdab9aaa773217355728e5d34"},"schema_version":"1.0","source":{"id":"2305.07490","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07490","created_at":"2026-07-05T08:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07490v6","created_at":"2026-07-05T08:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07490","created_at":"2026-07-05T08:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"A7OSKEVFNZJB","created_at":"2026-07-05T08:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"A7OSKEVFNZJBTCBF","created_at":"2026-07-05T08:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"A7OSKEVF","created_at":"2026-07-05T08:04:31Z"}],"graph_snapshots":[{"event_id":"sha256:242c88f1b3e582bd5ce5b1dbc76d17daf4553942eda3009d4951a6273d2cb301","target":"graph","created_at":"2026-07-05T08:04:31Z","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/2305.07490/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of large language models (LLMs) has inspired an emerging research field of multimodal learning. However, a grand challenge of exploiting LLMs for multimodal learning is the size of pre-trained LLMs which are always with billions of parameters. To tackle this challenge, models such as MiniGPT-4 and LLaVA have been developed to fine-tune the pre-trained models using fewer parameters. Despite their promising performance, these models remain limited in their understanding of artistic imagery. To facilitate better artistic-understanding, in this paper, we propose ArtGPT-4, a pioneering ","authors_text":"Kun Wang, Lichao Sun, Yanfang Ye, Yunhong He, Zhengqing Yuan","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T14:04:30Z","title":"ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07490","kind":"arxiv","version":6},"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:c04a975a8c99692dba1e870eadf86ddc4be8b9ffd160461f54d951e54ea8d873","target":"record","created_at":"2026-07-05T08:04:31Z","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":"0eb65c7995bfa093c780aee935a1e30b56fcc1d74d0bdc37f56a0c6fb09fbf95","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T14:04:30Z","title_canon_sha256":"41779df4b5e12c77aca5799c6b96e3f4c599b72fdab9aaa773217355728e5d34"},"schema_version":"1.0","source":{"id":"2305.07490","kind":"arxiv","version":6}},"canonical_sha256":"07dd2512a56e52198825b0fcfa0170a2ece19827ee1ab3710a9b9aea8570d194","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07dd2512a56e52198825b0fcfa0170a2ece19827ee1ab3710a9b9aea8570d194","first_computed_at":"2026-07-05T08:04:31.716779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:31.716779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XdDDmxjEMo47V0Og441xUdp6HmmcXJQtxKMjxsIumyfzshJRvwV3Blyce1m+N1TuOHgMBxTj3GSNHwJ/0cmSDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:31.717260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07490","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c04a975a8c99692dba1e870eadf86ddc4be8b9ffd160461f54d951e54ea8d873","sha256:242c88f1b3e582bd5ce5b1dbc76d17daf4553942eda3009d4951a6273d2cb301"],"state_sha256":"975e5d96b39e701ff7485490b048ab8b6fadb4bf9dae4944a06d96b4649ed202"}