{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QX4Y5H2OG7OOSRJYHP5PERGGJU","short_pith_number":"pith:QX4Y5H2O","schema_version":"1.0","canonical_sha256":"85f98e9f4e37dce945383bfaf244c64d158c57c843b0eddc9e97a46deedf49d5","source":{"kind":"arxiv","id":"2305.11116","version":1},"attestation_state":"computed","paper":{"title":"LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"William Yang Wang, Xianjun Yang, Xin Eric Wang, Xiujun Li, Yujie Lu","submitted_at":"2023-05-18T16:57:57Z","abstract_excerpt":"Existing automatic evaluation on text-to-image synthesis can only provide an image-text matching score, without considering the object-level compositionality, which results in poor correlation with human judgments. In this work, we propose LLMScore, a new framework that offers evaluation scores with multi-granularity compositionality. LLMScore leverages the large language models (LLMs) to evaluate text-to-image models. Initially, it transforms the image into image-level and object-level visual descriptions. Then an evaluation instruction is fed into the LLMs to measure the alignment between th"},"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":"2305.11116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T16:57:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fb316d68895187e7acb73eeafa5431370e3b28a0307dc5dfac400d634bcf6e00","abstract_canon_sha256":"c5bed0a242b90060f80581055dfd9cd24f830cc6fe3b40f55b4d302d1c061aae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:30.568143Z","signature_b64":"MBFzO24WZ0FCTw60TXgoS0g9zXlrcypeopdZqR0DyldE/7P0syGYQPQ8YyKKuKnJzfGqnpYj9A/IzU6UUke6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85f98e9f4e37dce945383bfaf244c64d158c57c843b0eddc9e97a46deedf49d5","last_reissued_at":"2026-07-05T06:11:30.567688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:30.567688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"William Yang Wang, Xianjun Yang, Xin Eric Wang, Xiujun Li, Yujie Lu","submitted_at":"2023-05-18T16:57:57Z","abstract_excerpt":"Existing automatic evaluation on text-to-image synthesis can only provide an image-text matching score, without considering the object-level compositionality, which results in poor correlation with human judgments. In this work, we propose LLMScore, a new framework that offers evaluation scores with multi-granularity compositionality. LLMScore leverages the large language models (LLMs) to evaluate text-to-image models. Initially, it transforms the image into image-level and object-level visual descriptions. Then an evaluation instruction is fed into the LLMs to measure the alignment between th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11116","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/2305.11116/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":"2305.11116","created_at":"2026-07-05T06:11:30.567750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11116v1","created_at":"2026-07-05T06:11:30.567750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11116","created_at":"2026-07-05T06:11:30.567750+00:00"},{"alias_kind":"pith_short_12","alias_value":"QX4Y5H2OG7OO","created_at":"2026-07-05T06:11:30.567750+00:00"},{"alias_kind":"pith_short_16","alias_value":"QX4Y5H2OG7OOSRJY","created_at":"2026-07-05T06:11:30.567750+00:00"},{"alias_kind":"pith_short_8","alias_value":"QX4Y5H2O","created_at":"2026-07-05T06:11:30.567750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.05722","citing_title":"Evaluating Hallucination in Text-to-Image Diffusion Models with Scene-Graph based Question-Answering Agent","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QX4Y5H2OG7OOSRJYHP5PERGGJU","json":"https://pith.science/pith/QX4Y5H2OG7OOSRJYHP5PERGGJU.json","graph_json":"https://pith.science/api/pith-number/QX4Y5H2OG7OOSRJYHP5PERGGJU/graph.json","events_json":"https://pith.science/api/pith-number/QX4Y5H2OG7OOSRJYHP5PERGGJU/events.json","paper":"https://pith.science/paper/QX4Y5H2O"},"agent_actions":{"view_html":"https://pith.science/pith/QX4Y5H2OG7OOSRJYHP5PERGGJU","download_json":"https://pith.science/pith/QX4Y5H2OG7OOSRJYHP5PERGGJU.json","view_paper":"https://pith.science/paper/QX4Y5H2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11116&json=true","fetch_graph":"https://pith.science/api/pith-number/QX4Y5H2OG7OOSRJYHP5PERGGJU/graph.json","fetch_events":"https://pith.science/api/pith-number/QX4Y5H2OG7OOSRJYHP5PERGGJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QX4Y5H2OG7OOSRJYHP5PERGGJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QX4Y5H2OG7OOSRJYHP5PERGGJU/action/storage_attestation","attest_author":"https://pith.science/pith/QX4Y5H2OG7OOSRJYHP5PERGGJU/action/author_attestation","sign_citation":"https://pith.science/pith/QX4Y5H2OG7OOSRJYHP5PERGGJU/action/citation_signature","submit_replication":"https://pith.science/pith/QX4Y5H2OG7OOSRJYHP5PERGGJU/action/replication_record"}},"created_at":"2026-07-05T06:11:30.567750+00:00","updated_at":"2026-07-05T06:11:30.567750+00:00"}