{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J3XSTYHNAZQHLCJAFCE7HQV4RV","short_pith_number":"pith:J3XSTYHN","schema_version":"1.0","canonical_sha256":"4eef29e0ed06607589202889f3c2bc8d44fae8cf3fec5ccb3d7ef7062ebc2a7c","source":{"kind":"arxiv","id":"2406.03070","version":2},"attestation_state":"computed","paper":{"title":"A-Bench: Are LMMs Masters at Evaluating AI-generated Images?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunyi Li, Guangtao Zhai, Haoning Wu, Weisi Lin, Wei Sun, Xiaohong Liu, Xiongkuo Min, Yingjie Zhou, Zicheng Zhang, Zijian Chen","submitted_at":"2024-06-05T08:55:02Z","abstract_excerpt":"How to accurately and efficiently assess AI-generated images (AIGIs) remains a critical challenge for generative models. Given the high costs and extensive time commitments required for user studies, many researchers have turned towards employing large multi-modal models (LMMs) as AIGI evaluators, the precision and validity of which are still questionable. Furthermore, traditional benchmarks often utilize mostly natural-captured content rather than AIGIs to test the abilities of LMMs, leading to a noticeable gap for AIGIs. Therefore, we introduce A-Bench in this paper, a benchmark designed 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":"2406.03070","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T08:55:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5a9f604732974c548841247f83d94ea08997dce448a619fbb8999a97f5295fc","abstract_canon_sha256":"e21f14d1b697e7f1f160284d5f896f306c409cb1b402303612a55fa55b2a23e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:40.980448Z","signature_b64":"EgBZ1qenHKG82rVBwLoGdyIQurzOmKwyVihSxW3KSVXcmTY6rY3BELK0gKT1lw1HAkWUx+7wCOmmuoDJ1ea+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eef29e0ed06607589202889f3c2bc8d44fae8cf3fec5ccb3d7ef7062ebc2a7c","last_reissued_at":"2026-07-05T10:10:40.979981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:40.979981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A-Bench: Are LMMs Masters at Evaluating AI-generated Images?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunyi Li, Guangtao Zhai, Haoning Wu, Weisi Lin, Wei Sun, Xiaohong Liu, Xiongkuo Min, Yingjie Zhou, Zicheng Zhang, Zijian Chen","submitted_at":"2024-06-05T08:55:02Z","abstract_excerpt":"How to accurately and efficiently assess AI-generated images (AIGIs) remains a critical challenge for generative models. Given the high costs and extensive time commitments required for user studies, many researchers have turned towards employing large multi-modal models (LMMs) as AIGI evaluators, the precision and validity of which are still questionable. Furthermore, traditional benchmarks often utilize mostly natural-captured content rather than AIGIs to test the abilities of LMMs, leading to a noticeable gap for AIGIs. Therefore, we introduce A-Bench in this paper, a benchmark designed to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03070","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/2406.03070/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":"2406.03070","created_at":"2026-07-05T10:10:40.980049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03070v2","created_at":"2026-07-05T10:10:40.980049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03070","created_at":"2026-07-05T10:10:40.980049+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3XSTYHNAZQH","created_at":"2026-07-05T10:10:40.980049+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3XSTYHNAZQHLCJA","created_at":"2026-07-05T10:10:40.980049+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3XSTYHN","created_at":"2026-07-05T10:10:40.980049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03401","citing_title":"Towards Characterizing Scientific Image Utility and Upgradability","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21210","citing_title":"Toward Generalizable Forgery Detection and Reasoning","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04225","citing_title":"Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3XSTYHNAZQHLCJAFCE7HQV4RV","json":"https://pith.science/pith/J3XSTYHNAZQHLCJAFCE7HQV4RV.json","graph_json":"https://pith.science/api/pith-number/J3XSTYHNAZQHLCJAFCE7HQV4RV/graph.json","events_json":"https://pith.science/api/pith-number/J3XSTYHNAZQHLCJAFCE7HQV4RV/events.json","paper":"https://pith.science/paper/J3XSTYHN"},"agent_actions":{"view_html":"https://pith.science/pith/J3XSTYHNAZQHLCJAFCE7HQV4RV","download_json":"https://pith.science/pith/J3XSTYHNAZQHLCJAFCE7HQV4RV.json","view_paper":"https://pith.science/paper/J3XSTYHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03070&json=true","fetch_graph":"https://pith.science/api/pith-number/J3XSTYHNAZQHLCJAFCE7HQV4RV/graph.json","fetch_events":"https://pith.science/api/pith-number/J3XSTYHNAZQHLCJAFCE7HQV4RV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3XSTYHNAZQHLCJAFCE7HQV4RV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3XSTYHNAZQHLCJAFCE7HQV4RV/action/storage_attestation","attest_author":"https://pith.science/pith/J3XSTYHNAZQHLCJAFCE7HQV4RV/action/author_attestation","sign_citation":"https://pith.science/pith/J3XSTYHNAZQHLCJAFCE7HQV4RV/action/citation_signature","submit_replication":"https://pith.science/pith/J3XSTYHNAZQHLCJAFCE7HQV4RV/action/replication_record"}},"created_at":"2026-07-05T10:10:40.980049+00:00","updated_at":"2026-07-05T10:10:40.980049+00:00"}