{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SVP4GZ7LGVI4EBBUGNJT5D4G5K","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":"a251f95707be0a89b30b584d194f31294684b3d919e43ee3994a1e032e522d6a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T18:59:31Z","title_canon_sha256":"aad59ecce37cb86b27232fb7a421ea4f041be25bd8d8632a3190218ee62bb617"},"schema_version":"1.0","source":{"id":"2311.07574","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07574","created_at":"2026-07-05T07:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07574v2","created_at":"2026-07-05T07:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07574","created_at":"2026-07-05T07:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"SVP4GZ7LGVI4","created_at":"2026-07-05T07:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"SVP4GZ7LGVI4EBBU","created_at":"2026-07-05T07:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"SVP4GZ7L","created_at":"2026-07-05T07:18:12Z"}],"graph_snapshots":[{"event_id":"sha256:d7dc0780d01855867ab262bd91ed332c5d149ff6ed51548605a0754c579ee7e0","target":"graph","created_at":"2026-07-05T07:18:12Z","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/2311.07574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing visual instruction tuning methods typically prompt large language models with textual descriptions to generate instruction-following data. Despite the promising performance achieved, these descriptions are derived from image annotations, which are oftentimes coarse-grained. Furthermore, the instructions might even contradict the visual content without observing the entire visual context. To address this challenge, we introduce a fine-grained visual instruction dataset, LVIS-Instruct4V, which contains 220K visually aligned and context-aware instructions produced by prompting the powerf","authors_text":"Bo He, Junke Wang, Lingchen Meng, Yu-Gang Jiang, Zejia Weng, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T18:59:31Z","title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07574","kind":"arxiv","version":2},"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:bcd7d58f2c3885fd3464e24df0ecfe0c2b9a3b7a61b22ec587996d963ea1659d","target":"record","created_at":"2026-07-05T07:18:12Z","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":"a251f95707be0a89b30b584d194f31294684b3d919e43ee3994a1e032e522d6a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T18:59:31Z","title_canon_sha256":"aad59ecce37cb86b27232fb7a421ea4f041be25bd8d8632a3190218ee62bb617"},"schema_version":"1.0","source":{"id":"2311.07574","kind":"arxiv","version":2}},"canonical_sha256":"955fc367eb3551c2043433533e8f86eaaf94fe99c175b2e574782e135610d887","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"955fc367eb3551c2043433533e8f86eaaf94fe99c175b2e574782e135610d887","first_computed_at":"2026-07-05T07:18:12.570665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:12.570665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PmbhbTo5zKjPMd+cJ29Za3jEA85NDoffQ0Akf2Dtw/fdtzQkliG+iOoGl2uCEdK6sLCKSTEq0W+tKYO6ZVdVCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:12.571208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07574","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcd7d58f2c3885fd3464e24df0ecfe0c2b9a3b7a61b22ec587996d963ea1659d","sha256:d7dc0780d01855867ab262bd91ed332c5d149ff6ed51548605a0754c579ee7e0"],"state_sha256":"9b811377d16ebc99c5ae2ffb74ff724b250f95e3898c2a2247d0ae13f09df44e"}