{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HYGANCHPDMCQKP342C4JCMOF27","short_pith_number":"pith:HYGANCHP","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"},"canonical_sha256":"3e0c0688ef1b05053f7cd0b89131c5d7c3d482277a022e9dc3946de5850a755f","source":{"kind":"arxiv","id":"2605.13223","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13223","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13223v1","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13223","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"HYGANCHPDMCQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"HYGANCHPDMCQKP34","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"HYGANCHP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HYGANCHPDMCQKP342C4JCMOF27","target":"record","payload":{"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"},"canonical_sha256":"3e0c0688ef1b05053f7cd0b89131c5d7c3d482277a022e9dc3946de5850a755f","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"},"source_kind":"arxiv","source_id":"2605.13223","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ILcqEYj5LU3/oY+vHRidtxenLe1mCi+ouELPR/1udR/9nRwKaIoj4ayeiczqgfcHsWUfd8TncjX4N8FdQw6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:38:57.328556Z"},"content_sha256":"8e5866dc9bee65c5c940d22f2c824159863482db510d93a61f75c6da41ae68d0","schema_version":"1.0","event_id":"sha256:8e5866dc9bee65c5c940d22f2c824159863482db510d93a61f75c6da41ae68d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HYGANCHPDMCQKP342C4JCMOF27","target":"graph","payload":{"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"},"verdict_id":"dfe24b60-f4ea-4214-9310-a8a75ad93df6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n08wR/DoSUT0oWJsaNY+/405NPEtfDajBRaYXpBTWfe1/tHvKmXWczlget4cqFSgQzz1uMjgV6qcAi58gCxOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:38:57.329502Z"},"content_sha256":"3372052c544cd8be63380eb1bb8f3708350c82b5965a82953e7095e7760c96ff","schema_version":"1.0","event_id":"sha256:3372052c544cd8be63380eb1bb8f3708350c82b5965a82953e7095e7760c96ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27/bundle.json","state_url":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HYGANCHPDMCQKP342C4JCMOF27/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T10:38:57Z","links":{"resolver":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27","bundle":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27/bundle.json","state":"https://pith.science/pith/HYGANCHPDMCQKP342C4JCMOF27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HYGANCHPDMCQKP342C4JCMOF27/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HYGANCHPDMCQKP342C4JCMOF27","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":"f48dc99be76d786b7067e7591278aff7cc85a90c775c74f433304598ab567605","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T09:14:31Z","title_canon_sha256":"a06e769e95f96d3128f679146f17bb33440c684b9955cca6e14c168d542af085"},"schema_version":"1.0","source":{"id":"2605.13223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13223","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13223v1","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13223","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"HYGANCHPDMCQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"HYGANCHPDMCQKP34","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"HYGANCHP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:3372052c544cd8be63380eb1bb8f3708350c82b5965a82953e7095e7760c96ff","target":"graph","created_at":"2026-05-18T03:08:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"skill-aligned annotation produces more consistent evaluation signals, with higher inter-annotator agreement and improved stability across models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Skill-aligned annotation improves inter-annotator agreement and evaluation stability in text-to-image generation compared to uniform annotation baselines."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"dda269bc01196853103c04ecda507bc591c2b09b6bbbf3a0e0a95ebf9b138334"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","authors_text":"Abdelrahman Eldesokey, Ahmad Sait, Ansar Khangeldin, Bernard Ghanem, Karen Sanchez, Merey Ramazanova, Tong Zhang","cross_cats":[],"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.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T09:14:31Z","title":"Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation"},"references":{"count":42,"internal_anchors":5,"resolved_work":42,"sample":[{"cited_arxiv_id":"2511.22699","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","work_id":"f1080a62-48e1-4255-b023-7556be57370d","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"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","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"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","year":2024},{"cited_arxiv_id":"2601.10611","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","work_id":"f0dc2969-bd90-4a5d-81df-d557352690b6","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"G. DeepMind. Nano-banana. https://deepmind.google/models/gemini-image/ flash/, 2025","work_id":"0a43bc6f-7c1c-4a5d-93d8-001740cc1b6c","year":2025}],"snapshot_sha256":"a4608d45b293e31e6ebd7b7a1ff4fe88c266a82c4f899fbdd4ba99569b366297"},"source":{"id":"2605.13223","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:09:22.571008Z","id":"dfe24b60-f4ea-4214-9310-a8a75ad93df6","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"skill-aligned annotation produces more consistent evaluation signals, with higher inter-annotator agreement and improved stability across models.","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."}},"verdict_id":"dfe24b60-f4ea-4214-9310-a8a75ad93df6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e5866dc9bee65c5c940d22f2c824159863482db510d93a61f75c6da41ae68d0","target":"record","created_at":"2026-05-18T03:08:48Z","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":"f48dc99be76d786b7067e7591278aff7cc85a90c775c74f433304598ab567605","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T09:14:31Z","title_canon_sha256":"a06e769e95f96d3128f679146f17bb33440c684b9955cca6e14c168d542af085"},"schema_version":"1.0","source":{"id":"2605.13223","kind":"arxiv","version":1}},"canonical_sha256":"3e0c0688ef1b05053f7cd0b89131c5d7c3d482277a022e9dc3946de5850a755f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e0c0688ef1b05053f7cd0b89131c5d7c3d482277a022e9dc3946de5850a755f","first_computed_at":"2026-05-18T03:08:48.327397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:48.327397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T7CNrSCtMf3cH15NtH+Z8zIEjs3vZ64KJ89ET94rlj8XIqAJV6wxx8MoZ0/KLwFXYeg8Yw/gc0pyXu9f5XOgDA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:48.328160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e5866dc9bee65c5c940d22f2c824159863482db510d93a61f75c6da41ae68d0","sha256:3372052c544cd8be63380eb1bb8f3708350c82b5965a82953e7095e7760c96ff"],"state_sha256":"da06ce1a184017c6b6397d5cf8f00375a42019fadd53624c0bfc85243edb1464"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XKmHMqZAUO2qYqfSgDRfxyiEGy6SM1vU86L2Z81scBL7r5WImrJr6JKpt1sZxG0kFhAj2hrGgNDP+EBmLuSwAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T10:38:57.336724Z","bundle_sha256":"d32ed6b1c9904cab1aa55ebf0c9c9ee52ac1487c540919b2e5c1bf6e3e58f196"}}