{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DAFSZYOINEFQ5POGAELIFITT4U","short_pith_number":"pith:DAFSZYOI","schema_version":"1.0","canonical_sha256":"180b2ce1c8690b0ebdc6011682a273e50fa4aab575fb365b162e644e4b623c32","source":{"kind":"arxiv","id":"2505.16915","version":3},"attestation_state":"computed","paper":{"title":"DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daoyuan Chen, Qirui Jiao, Xika Lin, Yaliang Li, Yilun Huang, Ying Shen","submitted_at":"2025-05-22T17:11:27Z","abstract_excerpt":"While recent Text-to-Image (T2I) models show impressive capabilities in synthesizing images from brief descriptions, they struggle with the long, detailed prompts required for professional applications. We present DetailMaster, a comprehensive benchmark for evaluating T2I capabilities on long prompts with complex compositional requirements, accompanied by an automated data construction pipeline and an evaluation workflow. Comprising expert-validated prompts averaging 284.89 tokens, our benchmark introduces four critical evaluation dimensions: Character Attributes, Structured Character Location"},"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":"2505.16915","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:11:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9c5542fe95aee17b68365bccf146849bfa506e0ac08b460e6f75f38f9f338b2","abstract_canon_sha256":"9ac5f5393a93ba7f20876cc6c1a5841ca478d21ac1c301d93b79131a4e1a9d6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:06.178096Z","signature_b64":"8+jTimDLA7fcw54DWkZIUJEiIX5o0Zr/Erotz+nn/tz3Yx3w9/lXJ8IRCL3x/rJP5cHD8xyoj8IaK3dC2mFIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"180b2ce1c8690b0ebdc6011682a273e50fa4aab575fb365b162e644e4b623c32","last_reissued_at":"2026-06-02T02:04:06.177552Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:06.177552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daoyuan Chen, Qirui Jiao, Xika Lin, Yaliang Li, Yilun Huang, Ying Shen","submitted_at":"2025-05-22T17:11:27Z","abstract_excerpt":"While recent Text-to-Image (T2I) models show impressive capabilities in synthesizing images from brief descriptions, they struggle with the long, detailed prompts required for professional applications. We present DetailMaster, a comprehensive benchmark for evaluating T2I capabilities on long prompts with complex compositional requirements, accompanied by an automated data construction pipeline and an evaluation workflow. Comprising expert-validated prompts averaging 284.89 tokens, our benchmark introduces four critical evaluation dimensions: Character Attributes, Structured Character Location"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16915","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/2505.16915/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":"2505.16915","created_at":"2026-06-02T02:04:06.177609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16915v3","created_at":"2026-06-02T02:04:06.177609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16915","created_at":"2026-06-02T02:04:06.177609+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAFSZYOINEFQ","created_at":"2026-06-02T02:04:06.177609+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAFSZYOINEFQ5POG","created_at":"2026-06-02T02:04:06.177609+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAFSZYOI","created_at":"2026-06-02T02:04:06.177609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18258","citing_title":"Long-Text-to-Image Generation via Compositional Prompt Decomposition","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAFSZYOINEFQ5POGAELIFITT4U","json":"https://pith.science/pith/DAFSZYOINEFQ5POGAELIFITT4U.json","graph_json":"https://pith.science/api/pith-number/DAFSZYOINEFQ5POGAELIFITT4U/graph.json","events_json":"https://pith.science/api/pith-number/DAFSZYOINEFQ5POGAELIFITT4U/events.json","paper":"https://pith.science/paper/DAFSZYOI"},"agent_actions":{"view_html":"https://pith.science/pith/DAFSZYOINEFQ5POGAELIFITT4U","download_json":"https://pith.science/pith/DAFSZYOINEFQ5POGAELIFITT4U.json","view_paper":"https://pith.science/paper/DAFSZYOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16915&json=true","fetch_graph":"https://pith.science/api/pith-number/DAFSZYOINEFQ5POGAELIFITT4U/graph.json","fetch_events":"https://pith.science/api/pith-number/DAFSZYOINEFQ5POGAELIFITT4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAFSZYOINEFQ5POGAELIFITT4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAFSZYOINEFQ5POGAELIFITT4U/action/storage_attestation","attest_author":"https://pith.science/pith/DAFSZYOINEFQ5POGAELIFITT4U/action/author_attestation","sign_citation":"https://pith.science/pith/DAFSZYOINEFQ5POGAELIFITT4U/action/citation_signature","submit_replication":"https://pith.science/pith/DAFSZYOINEFQ5POGAELIFITT4U/action/replication_record"}},"created_at":"2026-06-02T02:04:06.177609+00:00","updated_at":"2026-06-02T02:04:06.177609+00:00"}