{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QRHKK4SYV2PSVMQ465MYF7AEQZ","short_pith_number":"pith:QRHKK4SY","schema_version":"1.0","canonical_sha256":"844ea57258ae9f2ab21cf75982fc04866154f362263d00e631d921b0ff80cbb6","source":{"kind":"arxiv","id":"2606.06113","version":1},"attestation_state":"computed","paper":{"title":"Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqian Yu, Chun Yuan, Feng Lu, Haoxiang Cao, Hao Yu, Huaisong Zhang, Jiahe Wang, Wendong Zhang, Xinrui Chen, Yuxuan Zhang","submitted_at":"2026-06-04T13:03:16Z","abstract_excerpt":"Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality. While recent dense-feedback methods move beyond scalar supervision, their heatmap-centric representations still formulate diagnosis as pixel-field regression, making it difficult to localize variable-cardinality defects and bind semantic reasons to individual failures. To"},"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":"2606.06113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T13:03:16Z","cross_cats_sorted":[],"title_canon_sha256":"1e2efa3dd838f4e6a3ecc5ce6053823c83ea17c3e57f562c8640178f557dc155","abstract_canon_sha256":"caf305bd5bfd248524046a6787532cf133711623c87b19fc4bbae75020e441b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:33.851683Z","signature_b64":"YWfIqv/k1SwJCnyNj2Dr0EHsp1/heTpqYQipOtdZ78ENX7I3YXaUm6+MAgXYeVqYMbD8T8d+7SwRV9QqBFZPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"844ea57258ae9f2ab21cf75982fc04866154f362263d00e631d921b0ff80cbb6","last_reissued_at":"2026-06-05T01:15:33.851234Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:33.851234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqian Yu, Chun Yuan, Feng Lu, Haoxiang Cao, Hao Yu, Huaisong Zhang, Jiahe Wang, Wendong Zhang, Xinrui Chen, Yuxuan Zhang","submitted_at":"2026-06-04T13:03:16Z","abstract_excerpt":"Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality. While recent dense-feedback methods move beyond scalar supervision, their heatmap-centric representations still formulate diagnosis as pixel-field regression, making it difficult to localize variable-cardinality defects and bind semantic reasons to individual failures. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06113","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/2606.06113/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":"2606.06113","created_at":"2026-06-05T01:15:33.851306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06113v1","created_at":"2026-06-05T01:15:33.851306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06113","created_at":"2026-06-05T01:15:33.851306+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRHKK4SYV2PS","created_at":"2026-06-05T01:15:33.851306+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRHKK4SYV2PSVMQ4","created_at":"2026-06-05T01:15:33.851306+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRHKK4SY","created_at":"2026-06-05T01:15:33.851306+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/QRHKK4SYV2PSVMQ465MYF7AEQZ","json":"https://pith.science/pith/QRHKK4SYV2PSVMQ465MYF7AEQZ.json","graph_json":"https://pith.science/api/pith-number/QRHKK4SYV2PSVMQ465MYF7AEQZ/graph.json","events_json":"https://pith.science/api/pith-number/QRHKK4SYV2PSVMQ465MYF7AEQZ/events.json","paper":"https://pith.science/paper/QRHKK4SY"},"agent_actions":{"view_html":"https://pith.science/pith/QRHKK4SYV2PSVMQ465MYF7AEQZ","download_json":"https://pith.science/pith/QRHKK4SYV2PSVMQ465MYF7AEQZ.json","view_paper":"https://pith.science/paper/QRHKK4SY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06113&json=true","fetch_graph":"https://pith.science/api/pith-number/QRHKK4SYV2PSVMQ465MYF7AEQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QRHKK4SYV2PSVMQ465MYF7AEQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRHKK4SYV2PSVMQ465MYF7AEQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRHKK4SYV2PSVMQ465MYF7AEQZ/action/storage_attestation","attest_author":"https://pith.science/pith/QRHKK4SYV2PSVMQ465MYF7AEQZ/action/author_attestation","sign_citation":"https://pith.science/pith/QRHKK4SYV2PSVMQ465MYF7AEQZ/action/citation_signature","submit_replication":"https://pith.science/pith/QRHKK4SYV2PSVMQ465MYF7AEQZ/action/replication_record"}},"created_at":"2026-06-05T01:15:33.851306+00:00","updated_at":"2026-06-05T01:15:33.851306+00:00"}