{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OPJ5UZAQEVGBCCWXQHEG3XDGHP","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":"31151350f85cd88a20cbc54f0f13875cc4f96b1ca0d5852eefd434d46e6ca20e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T18:19:51Z","title_canon_sha256":"63e6e6491dabdefe62eb11340e225fccf31970d01aa09223b31a429bf18a657b"},"schema_version":"1.0","source":{"id":"2508.01008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01008","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01008v1","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01008","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"pith_short_12","alias_value":"OPJ5UZAQEVGB","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"pith_short_16","alias_value":"OPJ5UZAQEVGBCCWX","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"pith_short_8","alias_value":"OPJ5UZAQ","created_at":"2026-07-05T11:47:31Z"}],"graph_snapshots":[{"event_id":"sha256:3e3bd32045c15552df0229124723effe469ab8002e983a0e272ecee257828a0c","target":"graph","created_at":"2026-07-05T11:47:31Z","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/2508.01008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present ROVI, a high-quality synthetic dataset for instance-grounded text-to-image generation, created by labeling 1M curated web images. Our key innovation is a strategy called re-captioning, focusing on the pre-detection stage, where a VLM (Vision-Language Model) generates comprehensive visual descriptions that are then processed by an LLM (Large Language Model) to extract a flat list of potential categories for OVDs (Open-Vocabulary Detectors) to detect. This approach yields a global prompt inherently linked to instance annotations while capturing secondary visual elements humans typical","authors_text":"Cihang Peng, Kun Zhou, Qiming Hou, Zhong Ren","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T18:19:51Z","title":"ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01008","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":"sha256:89136c0e3452c470e3cf6666a2d15611e1151bbe56d40aaf8eb22cfbb6ef71e5","target":"record","created_at":"2026-07-05T11:47:31Z","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":"31151350f85cd88a20cbc54f0f13875cc4f96b1ca0d5852eefd434d46e6ca20e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T18:19:51Z","title_canon_sha256":"63e6e6491dabdefe62eb11340e225fccf31970d01aa09223b31a429bf18a657b"},"schema_version":"1.0","source":{"id":"2508.01008","kind":"arxiv","version":1}},"canonical_sha256":"73d3da6410254c110ad781c86ddc663bc7d2eaf26fd87a1d41577023f1f53f58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73d3da6410254c110ad781c86ddc663bc7d2eaf26fd87a1d41577023f1f53f58","first_computed_at":"2026-07-05T11:47:31.682756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:31.682756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LJwLWOiv6Ox7enY20RuL6uKTV+L8baH6wqJiihGygeSJQzHtMDGrKT5AHgjD89ocOULQywdvaf3RPGS5GJNfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:31.683221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89136c0e3452c470e3cf6666a2d15611e1151bbe56d40aaf8eb22cfbb6ef71e5","sha256:3e3bd32045c15552df0229124723effe469ab8002e983a0e272ecee257828a0c"],"state_sha256":"1a2f6b465dd93fce2d06d90de58a0641d134cc4e377eafb20189157b12f54091"}