{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J7C24QFTMTG7HIXEQVVB52ELBS","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":"e036e3509faf0b6dfcedc2651c54c7b48524320d0c94d206d96ceb2023af2b52","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-07T13:43:44Z","title_canon_sha256":"a4e8b4c681e39af46b4bce45a12e3f484d14cb942622811a033fd36576b718f2"},"schema_version":"1.0","source":{"id":"2307.03601","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03601","created_at":"2026-07-05T11:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03601v5","created_at":"2026-07-05T11:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03601","created_at":"2026-07-05T11:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"J7C24QFTMTG7","created_at":"2026-07-05T11:20:01Z"},{"alias_kind":"pith_short_16","alias_value":"J7C24QFTMTG7HIXE","created_at":"2026-07-05T11:20:01Z"},{"alias_kind":"pith_short_8","alias_value":"J7C24QFT","created_at":"2026-07-05T11:20:01Z"}],"graph_snapshots":[{"event_id":"sha256:291f5ec2f6ef6aa98d802f37f4107f322993d3e950d65f81aebd1fd0f0e098fd","target":"graph","created_at":"2026-07-05T11:20:01Z","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/2307.03601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual instruction tuning large language model(LLM) on image-text pairs has achieved general-purpose vision-language abilities. However, the lack of region-text pairs limits their advancements to fine-grained multimodal understanding. In this paper, we propose spatial instruction tuning, which introduces the reference to the region-of-interest(RoI) in the instruction. Before sending to LLM, the reference is replaced by RoI features and interleaved with language embeddings as a sequence. Our model GPT4RoI, trained on 7 region-text pair datasets, brings an unprecedented interactive and conversat","authors_text":"Kai Chen, Min Xiao, Peize Sun, Ping Luo, Shilong Zhang, Shoufa Chen, Wenqi Shao, Wenwei Zhang, Yu Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-07T13:43:44Z","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03601","kind":"arxiv","version":5},"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":"sha256:34e202c6c6908f8e72c49843286bc093ae154c4116148cfc0812d78d747c72b4","target":"record","created_at":"2026-07-05T11:20:01Z","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":"e036e3509faf0b6dfcedc2651c54c7b48524320d0c94d206d96ceb2023af2b52","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-07T13:43:44Z","title_canon_sha256":"a4e8b4c681e39af46b4bce45a12e3f484d14cb942622811a033fd36576b718f2"},"schema_version":"1.0","source":{"id":"2307.03601","kind":"arxiv","version":5}},"canonical_sha256":"4fc5ae40b364cdf3a2e4856a1ee88b0caf5268289f9a5e4dc7e8c7bf466f1a25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fc5ae40b364cdf3a2e4856a1ee88b0caf5268289f9a5e4dc7e8c7bf466f1a25","first_computed_at":"2026-07-05T11:20:01.417942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:01.417942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m7KTNPfTSpROjTq62bMb77JS1hgkk/bx7oksSTRP5KRcZPk33O3Dn5rGE878CwhdFzyO6lguWyskyiuGYAxPDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:01.418497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.03601","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34e202c6c6908f8e72c49843286bc093ae154c4116148cfc0812d78d747c72b4","sha256:291f5ec2f6ef6aa98d802f37f4107f322993d3e950d65f81aebd1fd0f0e098fd"],"state_sha256":"e494c4df70a247c46d0e1ca889399de0892c9743335ce8d65c2d3de4a2416c3d"}