{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SKPUVW2MEWADEF4QOJMNVNN77P","short_pith_number":"pith:SKPUVW2M","schema_version":"1.0","canonical_sha256":"929f4adb4c25803217907258dab5bffbcfb693d5a06ccf1abcc95cfacf021c66","source":{"kind":"arxiv","id":"2305.10843","version":2},"attestation_state":"computed","paper":{"title":"X-IQE: eXplainable Image Quality Evaluation for Text-to-Image Generation with Visual Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chris Ding, Li Liu, Yixiong Chen","submitted_at":"2023-05-18T09:56:44Z","abstract_excerpt":"This paper introduces a novel explainable image quality evaluation approach called X-IQE, which leverages visual large language models (LLMs) to evaluate text-to-image generation methods by generating textual explanations. X-IQE utilizes a hierarchical Chain of Thought (CoT) to enable MiniGPT-4 to produce self-consistent, unbiased texts that are highly correlated with human evaluation. It offers several advantages, including the ability to distinguish between real and generated images, evaluate text-image alignment, and assess image aesthetics without requiring model training or fine-tuning. X"},"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":"2305.10843","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T09:56:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6bcd5d6b1e569558b8a94d70dced67aaee593eda6a65b240dc770edb22dcd4a7","abstract_canon_sha256":"f1f71d8e1f887adb179f0fbc83983b8d77e0acab14d05da4d7e414c2c5985b1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:10.522747Z","signature_b64":"2zjrq+KPMBpJ7E+cTo4mlKR99HmtQ8EWS0zBV4t404m5ZdU/G+hZKZCrCTqwTMkCSZG/3PDT+VmawUvKmtRCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"929f4adb4c25803217907258dab5bffbcfb693d5a06ccf1abcc95cfacf021c66","last_reissued_at":"2026-07-05T06:14:10.522341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:10.522341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-IQE: eXplainable Image Quality Evaluation for Text-to-Image Generation with Visual Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chris Ding, Li Liu, Yixiong Chen","submitted_at":"2023-05-18T09:56:44Z","abstract_excerpt":"This paper introduces a novel explainable image quality evaluation approach called X-IQE, which leverages visual large language models (LLMs) to evaluate text-to-image generation methods by generating textual explanations. X-IQE utilizes a hierarchical Chain of Thought (CoT) to enable MiniGPT-4 to produce self-consistent, unbiased texts that are highly correlated with human evaluation. It offers several advantages, including the ability to distinguish between real and generated images, evaluate text-image alignment, and assess image aesthetics without requiring model training or fine-tuning. X"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10843","kind":"arxiv","version":2},"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/2305.10843/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":"2305.10843","created_at":"2026-07-05T06:14:10.522398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10843v2","created_at":"2026-07-05T06:14:10.522398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10843","created_at":"2026-07-05T06:14:10.522398+00:00"},{"alias_kind":"pith_short_12","alias_value":"SKPUVW2MEWAD","created_at":"2026-07-05T06:14:10.522398+00:00"},{"alias_kind":"pith_short_16","alias_value":"SKPUVW2MEWADEF4Q","created_at":"2026-07-05T06:14:10.522398+00:00"},{"alias_kind":"pith_short_8","alias_value":"SKPUVW2M","created_at":"2026-07-05T06:14:10.522398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.11349","citing_title":"Image Score: Learning and Evaluating Human Preferences for Mercari Search","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2312.17090","citing_title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24953","citing_title":"ViPO: Visual Preference Optimization at Scale","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SKPUVW2MEWADEF4QOJMNVNN77P","json":"https://pith.science/pith/SKPUVW2MEWADEF4QOJMNVNN77P.json","graph_json":"https://pith.science/api/pith-number/SKPUVW2MEWADEF4QOJMNVNN77P/graph.json","events_json":"https://pith.science/api/pith-number/SKPUVW2MEWADEF4QOJMNVNN77P/events.json","paper":"https://pith.science/paper/SKPUVW2M"},"agent_actions":{"view_html":"https://pith.science/pith/SKPUVW2MEWADEF4QOJMNVNN77P","download_json":"https://pith.science/pith/SKPUVW2MEWADEF4QOJMNVNN77P.json","view_paper":"https://pith.science/paper/SKPUVW2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10843&json=true","fetch_graph":"https://pith.science/api/pith-number/SKPUVW2MEWADEF4QOJMNVNN77P/graph.json","fetch_events":"https://pith.science/api/pith-number/SKPUVW2MEWADEF4QOJMNVNN77P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SKPUVW2MEWADEF4QOJMNVNN77P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SKPUVW2MEWADEF4QOJMNVNN77P/action/storage_attestation","attest_author":"https://pith.science/pith/SKPUVW2MEWADEF4QOJMNVNN77P/action/author_attestation","sign_citation":"https://pith.science/pith/SKPUVW2MEWADEF4QOJMNVNN77P/action/citation_signature","submit_replication":"https://pith.science/pith/SKPUVW2MEWADEF4QOJMNVNN77P/action/replication_record"}},"created_at":"2026-07-05T06:14:10.522398+00:00","updated_at":"2026-07-05T06:14:10.522398+00:00"}