{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HYGANCHPDMCQKP342C4JCMOF27","short_pith_number":"pith:HYGANCHP","schema_version":"1.0","canonical_sha256":"3e0c0688ef1b05053f7cd0b89131c5d7c3d482277a022e9dc3946de5850a755f","source":{"kind":"arxiv","id":"2605.13223","version":1},"attestation_state":"computed","paper":{"title":"Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Annotation strategies tailored to each evaluation skill produce more consistent signals and higher agreement than uniform scales across all skills in text-to-image generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Eldesokey, Ahmad Sait, Ansar Khangeldin, Bernard Ghanem, Karen Sanchez, Merey Ramazanova, Tong Zhang","submitted_at":"2026-05-13T09:14:31Z","abstract_excerpt":"Text-to-image (T2I) generation has advanced rapidly, making reliable evaluation critical as performance differences between models narrow. Existing evaluation practices typically apply uniform annotation mechanisms, such as Likert-scale or binary question answering (BQA), across heterogeneous evaluation skills, despite fundamental differences in their nature. In this work, we revisit T2I evaluation through the lens of skill-aligned annotation, where annotation strategies reflect the underlying characteristics of each evaluation skill. We systematically compare skill-aligned annotation against "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T09:14:31Z","cross_cats_sorted":[],"title_canon_sha256":"a06e769e95f96d3128f679146f17bb33440c684b9955cca6e14c168d542af085","abstract_canon_sha256":"f48dc99be76d786b7067e7591278aff7cc85a90c775c74f433304598ab567605"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:48.328160Z","signature_b64":"T7CNrSCtMf3cH15NtH+Z8zIEjs3vZ64KJ89ET94rlj8XIqAJV6wxx8MoZ0/KLwFXYeg8Yw/gc0pyXu9f5XOgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e0c0688ef1b05053f7cd0b89131c5d7c3d482277a022e9dc3946de5850a755f","last_reissued_at":"2026-05-18T03:08:48.327397Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:48.327397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Annotation strategies tailored to each evaluation skill produce more consistent signals and higher agreement than uniform scales across all skills in text-to-image generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Eldesokey, Ahmad Sait, Ansar Khangeldin, Bernard Ghanem, Karen Sanchez, Merey Ramazanova, Tong Zhang","submitted_at":"2026-05-13T09:14:31Z","abstract_excerpt":"Text-to-image (T2I) generation has advanced rapidly, making reliable evaluation critical as performance differences between models narrow. Existing evaluation practices typically apply uniform annotation mechanisms, such as Likert-scale or binary question answering (BQA), across heterogeneous evaluation skills, despite fundamental differences in their nature. In this work, we revisit T2I evaluation through the lens of skill-aligned annotation, where annotation strategies reflect the underlying characteristics of each evaluation skill. We systematically compare skill-aligned annotation against "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"skill-aligned annotation produces more consistent evaluation signals, with higher inter-annotator agreement and improved stability across models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen skill-aligned annotation strategies are fundamentally better suited to each skill's nature and that the uniform baselines provide a fair comparison without confounding factors in skill selection or annotation design.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Skill-aligned annotation improves inter-annotator agreement and evaluation stability in text-to-image generation compared to uniform annotation baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Annotation strategies tailored to each evaluation skill produce more consistent signals and higher agreement than uniform scales across all skills in text-to-image generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"dda269bc01196853103c04ecda507bc591c2b09b6bbbf3a0e0a95ebf9b138334"},"source":{"id":"2605.13223","kind":"arxiv","version":1},"verdict":{"id":"dfe24b60-f4ea-4214-9310-a8a75ad93df6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:09:22.571008Z","strongest_claim":"skill-aligned annotation produces more consistent evaluation signals, with higher inter-annotator agreement and improved stability across models.","one_line_summary":"Skill-aligned annotation improves inter-annotator agreement and evaluation stability in text-to-image generation compared to uniform annotation baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen skill-aligned annotation strategies are fundamentally better suited to each skill's nature and that the uniform baselines provide a fair comparison without confounding factors in skill selection or annotation design.","pith_extraction_headline":"Annotation strategies tailored to each evaluation skill produce more consistent signals and higher agreement than uniform scales across all skills in text-to-image generation."},"references":{"count":42,"sample":[{"doi":"","year":2025,"title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","work_id":"f1080a62-48e1-4255-b023-7556be57370d","ref_index":1,"cited_arxiv_id":"2511.22699","is_internal_anchor":true},{"doi":"","year":2024,"title":"J. Chen, J. YU, C. GE, L. Y ao, E. Xie, Z. Wang, J. Kwok, P . Luo, H. Lu, and Z. Li. Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis. In The Twelfth","work_id":"f7a143e0-8789-4955-915c-77dd726ffe92","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"J. Cho, Y . Hu, J. M. Baldridge, R. Garg, P . Anderson, R. Krishna, M. Bansal, J. Pont-Tuset, and S. Wang. Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image ge","work_id":"84a58b20-1f7c-4871-971b-da2c2932397d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","work_id":"f0dc2969-bd90-4a5d-81df-d557352690b6","ref_index":4,"cited_arxiv_id":"2601.10611","is_internal_anchor":true},{"doi":"","year":2025,"title":"G. DeepMind. Nano-banana. https://deepmind.google/models/gemini-image/ flash/, 2025","work_id":"0a43bc6f-7c1c-4a5d-93d8-001740cc1b6c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":42,"snapshot_sha256":"a4608d45b293e31e6ebd7b7a1ff4fe88c266a82c4f899fbdd4ba99569b366297","internal_anchors":5},"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":"2605.13223","created_at":"2026-05-18T03:08:48.327522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13223v1","created_at":"2026-05-18T03:08:48.327522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13223","created_at":"2026-05-18T03:08:48.327522+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYGANCHPDMCQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYGANCHPDMCQKP34","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYGANCHP","created_at":"2026-05-18T12:33:37.589309+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/HYGANCHPDMCQKP342C4JCMOF27","json":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27.json","graph_json":"https://pith.science/api/pith-number/HYGANCHPDMCQKP342C4JCMOF27/graph.json","events_json":"https://pith.science/api/pith-number/HYGANCHPDMCQKP342C4JCMOF27/events.json","paper":"https://pith.science/paper/HYGANCHP"},"agent_actions":{"view_html":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27","download_json":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27.json","view_paper":"https://pith.science/paper/HYGANCHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13223&json=true","fetch_graph":"https://pith.science/api/pith-number/HYGANCHPDMCQKP342C4JCMOF27/graph.json","fetch_events":"https://pith.science/api/pith-number/HYGANCHPDMCQKP342C4JCMOF27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27/action/storage_attestation","attest_author":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27/action/author_attestation","sign_citation":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27/action/citation_signature","submit_replication":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27/action/replication_record"}},"created_at":"2026-05-18T03:08:48.327522+00:00","updated_at":"2026-05-18T03:08:48.327522+00:00"}