{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OPJ5UZAQEVGBCCWXQHEG3XDGHP","short_pith_number":"pith:OPJ5UZAQ","schema_version":"1.0","canonical_sha256":"73d3da6410254c110ad781c86ddc663bc7d2eaf26fd87a1d41577023f1f53f58","source":{"kind":"arxiv","id":"2508.01008","version":1},"attestation_state":"computed","paper":{"title":"ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Peng, Kun Zhou, Qiming Hou, Zhong Ren","submitted_at":"2025-08-01T18:19:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.01008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T18:19:51Z","cross_cats_sorted":[],"title_canon_sha256":"63e6e6491dabdefe62eb11340e225fccf31970d01aa09223b31a429bf18a657b","abstract_canon_sha256":"31151350f85cd88a20cbc54f0f13875cc4f96b1ca0d5852eefd434d46e6ca20e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:31.683221Z","signature_b64":"LJwLWOiv6Ox7enY20RuL6uKTV+L8baH6wqJiihGygeSJQzHtMDGrKT5AHgjD89ocOULQywdvaf3RPGS5GJNfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73d3da6410254c110ad781c86ddc663bc7d2eaf26fd87a1d41577023f1f53f58","last_reissued_at":"2026-07-05T11:47:31.682756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:31.682756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Peng, Kun Zhou, Qiming Hou, Zhong Ren","submitted_at":"2025-08-01T18:19:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01008","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.01008/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.01008","created_at":"2026-07-05T11:47:31.682813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01008v1","created_at":"2026-07-05T11:47:31.682813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01008","created_at":"2026-07-05T11:47:31.682813+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPJ5UZAQEVGB","created_at":"2026-07-05T11:47:31.682813+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPJ5UZAQEVGBCCWX","created_at":"2026-07-05T11:47:31.682813+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPJ5UZAQ","created_at":"2026-07-05T11:47:31.682813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPJ5UZAQEVGBCCWXQHEG3XDGHP","json":"https://pith.science/pith/OPJ5UZAQEVGBCCWXQHEG3XDGHP.json","graph_json":"https://pith.science/api/pith-number/OPJ5UZAQEVGBCCWXQHEG3XDGHP/graph.json","events_json":"https://pith.science/api/pith-number/OPJ5UZAQEVGBCCWXQHEG3XDGHP/events.json","paper":"https://pith.science/paper/OPJ5UZAQ"},"agent_actions":{"view_html":"https://pith.science/pith/OPJ5UZAQEVGBCCWXQHEG3XDGHP","download_json":"https://pith.science/pith/OPJ5UZAQEVGBCCWXQHEG3XDGHP.json","view_paper":"https://pith.science/paper/OPJ5UZAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01008&json=true","fetch_graph":"https://pith.science/api/pith-number/OPJ5UZAQEVGBCCWXQHEG3XDGHP/graph.json","fetch_events":"https://pith.science/api/pith-number/OPJ5UZAQEVGBCCWXQHEG3XDGHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPJ5UZAQEVGBCCWXQHEG3XDGHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPJ5UZAQEVGBCCWXQHEG3XDGHP/action/storage_attestation","attest_author":"https://pith.science/pith/OPJ5UZAQEVGBCCWXQHEG3XDGHP/action/author_attestation","sign_citation":"https://pith.science/pith/OPJ5UZAQEVGBCCWXQHEG3XDGHP/action/citation_signature","submit_replication":"https://pith.science/pith/OPJ5UZAQEVGBCCWXQHEG3XDGHP/action/replication_record"}},"created_at":"2026-07-05T11:47:31.682813+00:00","updated_at":"2026-07-05T11:47:31.682813+00:00"}