{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QFLFEWDWJZWA3LGDWAJCLIKB3W","short_pith_number":"pith:QFLFEWDW","schema_version":"1.0","canonical_sha256":"81565258764e6c0dacc3b01225a141dd98a890e636d003ca3b9330f4df8afd1a","source":{"kind":"arxiv","id":"2307.06350","version":3},"attestation_state":"computed","paper":{"title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqi Duan, Enze Xie, Kaiyi Huang, Kaiyue Sun, Xihui Liu, Zhenguo Li","submitted_at":"2023-07-12T17:59:42Z","abstract_excerpt":"Despite the impressive advances in text-to-image models, they often struggle to effectively compose complex scenes with multiple objects, displaying various attributes and relationships. To address this challenge, we present T2I-CompBench++, an enhanced benchmark for compositional text-to-image generation. T2I-CompBench++ comprises 8,000 compositional text prompts categorized into four primary groups: attribute binding, object relationships, generative numeracy, and complex compositions. These are further divided into eight sub-categories, including newly introduced ones like 3D-spatial relati"},"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":"2307.06350","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-12T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"04e71aa6842207a8cfe50ec24eb1f1ea5fa417c80c68336cfbf5231da780b311","abstract_canon_sha256":"5461e2c91c9935ceedc2573ae65726403619477e2a2f6d39740339a6e71e84d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:01.970589Z","signature_b64":"Lbp/KdRAYGredxYo7wei/VS9AxUeyTGcUnM3KnT2dYjMN7sqDVTBneIIg6fR3A/1S1pML8PDuxp2e+jv9K4zDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81565258764e6c0dacc3b01225a141dd98a890e636d003ca3b9330f4df8afd1a","last_reissued_at":"2026-07-05T10:33:01.969637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:01.969637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqi Duan, Enze Xie, Kaiyi Huang, Kaiyue Sun, Xihui Liu, Zhenguo Li","submitted_at":"2023-07-12T17:59:42Z","abstract_excerpt":"Despite the impressive advances in text-to-image models, they often struggle to effectively compose complex scenes with multiple objects, displaying various attributes and relationships. To address this challenge, we present T2I-CompBench++, an enhanced benchmark for compositional text-to-image generation. T2I-CompBench++ comprises 8,000 compositional text prompts categorized into four primary groups: attribute binding, object relationships, generative numeracy, and complex compositions. These are further divided into eight sub-categories, including newly introduced ones like 3D-spatial relati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06350","kind":"arxiv","version":3},"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/2307.06350/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":"2307.06350","created_at":"2026-07-05T10:33:01.969768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.06350v3","created_at":"2026-07-05T10:33:01.969768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06350","created_at":"2026-07-05T10:33:01.969768+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFLFEWDWJZWA","created_at":"2026-07-05T10:33:01.969768+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFLFEWDWJZWA3LGD","created_at":"2026-07-05T10:33:01.969768+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFLFEWDW","created_at":"2026-07-05T10:33:01.969768+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00402","citing_title":"The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14876","citing_title":"Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2411.04996","citing_title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2403.03206","citing_title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25072","citing_title":"Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFLFEWDWJZWA3LGDWAJCLIKB3W","json":"https://pith.science/pith/QFLFEWDWJZWA3LGDWAJCLIKB3W.json","graph_json":"https://pith.science/api/pith-number/QFLFEWDWJZWA3LGDWAJCLIKB3W/graph.json","events_json":"https://pith.science/api/pith-number/QFLFEWDWJZWA3LGDWAJCLIKB3W/events.json","paper":"https://pith.science/paper/QFLFEWDW"},"agent_actions":{"view_html":"https://pith.science/pith/QFLFEWDWJZWA3LGDWAJCLIKB3W","download_json":"https://pith.science/pith/QFLFEWDWJZWA3LGDWAJCLIKB3W.json","view_paper":"https://pith.science/paper/QFLFEWDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.06350&json=true","fetch_graph":"https://pith.science/api/pith-number/QFLFEWDWJZWA3LGDWAJCLIKB3W/graph.json","fetch_events":"https://pith.science/api/pith-number/QFLFEWDWJZWA3LGDWAJCLIKB3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFLFEWDWJZWA3LGDWAJCLIKB3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFLFEWDWJZWA3LGDWAJCLIKB3W/action/storage_attestation","attest_author":"https://pith.science/pith/QFLFEWDWJZWA3LGDWAJCLIKB3W/action/author_attestation","sign_citation":"https://pith.science/pith/QFLFEWDWJZWA3LGDWAJCLIKB3W/action/citation_signature","submit_replication":"https://pith.science/pith/QFLFEWDWJZWA3LGDWAJCLIKB3W/action/replication_record"}},"created_at":"2026-07-05T10:33:01.969768+00:00","updated_at":"2026-07-05T10:33:01.969768+00:00"}