{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5IWJHZDB2WF56MSII3B53ZFBC5","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":"ad90150fd7697afd6fd67c188c6c6aa0b58cb8b2d5f8e6339cfa794889fdd77e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T14:33:17Z","title_canon_sha256":"a0ce9042ab08f6f935e151adf523e2ad91b7facb87b669ce25a50c70aa5f89ad"},"schema_version":"1.0","source":{"id":"2409.13540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13540","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13540v1","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13540","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"5IWJHZDB2WF5","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"5IWJHZDB2WF56MSI","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"5IWJHZDB","created_at":"2026-07-05T09:09:37Z"}],"graph_snapshots":[{"event_id":"sha256:2af8cb443e7745628260b0f3c528326dbf3e27988bf2dba26b032626baea7fe6","target":"graph","created_at":"2026-07-05T09:09:37Z","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/2409.13540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown promise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. However, they heavily depend on high-quality data in the Supervised Fine-Tuning (SFT) phase. The existing approaches aim to curate high-quality data via GPT-4V, but they are not scalable due to the commercial nature of GPT-4V and the simplicity of the prompts used to instruct the model. To this end, we devised the FullAnno system, which is a data engine that can generate large-scale, high-quality, and fine-grained image annotations c","authors_text":"Errui Ding, Gang Zhang, Jingdong Wang, Jing Hao, Kun Yao, Qiang Chen, Song Chen, Yanpeng Sun, Yuxiang Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T14:33:17Z","title":"FullAnno: A Data Engine for Enhancing Image Comprehension of MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13540","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:cf61058a15d7e1b31cf53c89cbf6573b4aa86408614cd4b4ba2cb986087a629c","target":"record","created_at":"2026-07-05T09:09:37Z","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":"ad90150fd7697afd6fd67c188c6c6aa0b58cb8b2d5f8e6339cfa794889fdd77e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T14:33:17Z","title_canon_sha256":"a0ce9042ab08f6f935e151adf523e2ad91b7facb87b669ce25a50c70aa5f89ad"},"schema_version":"1.0","source":{"id":"2409.13540","kind":"arxiv","version":1}},"canonical_sha256":"ea2c93e461d58bdf324846c3dde4a1174bdcfa1199365f2dbe68cc428740b1e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea2c93e461d58bdf324846c3dde4a1174bdcfa1199365f2dbe68cc428740b1e4","first_computed_at":"2026-07-05T09:09:37.286720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:37.286720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8YT6aWanxqxlvpXMUTzadMQTdpCHvCnP5TW60MPXtU2Wsn/khXoTTS7KxeQcsJ+yGBo9RCnLSNkQRD2i7YT7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:37.287234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf61058a15d7e1b31cf53c89cbf6573b4aa86408614cd4b4ba2cb986087a629c","sha256:2af8cb443e7745628260b0f3c528326dbf3e27988bf2dba26b032626baea7fe6"],"state_sha256":"55c77e3e7763a1d09a799da2716787571800afe46e6c2bfbe8d9ca61045fb03f"}