{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SHYSJ3B47C3URE4TWLQW2CSMEV","short_pith_number":"pith:SHYSJ3B4","schema_version":"1.0","canonical_sha256":"91f124ec3cf8b7489393b2e16d0a4c25770abb95afb80ecd48a15d926bd45649","source":{"kind":"arxiv","id":"2411.15488","version":1},"attestation_state":"computed","paper":{"title":"Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Heyan Huang, Rong-Cheng Tu, Tian Lan, Xian-Ling Mao, Yuehao Zhao, Zi-Ao Ma","submitted_at":"2024-11-23T08:06:06Z","abstract_excerpt":"Driven by the remarkable progress in diffusion models, text-to-image generation has made significant strides, creating a pressing demand for automatic quality evaluation of generated images. Current state-of-the-art automatic evaluation methods heavily rely on Multi-modal Large Language Models (MLLMs), particularly powerful commercial models like GPT-4o. While these models are highly effective, their substantial costs limit scalability in large-scale evaluations. Adopting open-source MLLMs is an alternative; however, their performance falls short due to significant limitations in processing mu"},"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":"2411.15488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-23T08:06:06Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"085a06821e094a89040edd84f4b709082b70cfdc6991a9f785454c6f327efc24","abstract_canon_sha256":"bf6b10018d8899619f0f48dbda733668fdd328d5cba2f9830156c420abe872a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:35.682462Z","signature_b64":"MdeLDTmqzvQXODGa3dr1vANnyf5CTiMeTjpZ0jbyC3RStq52loMhOdbt/mo4rCHnR1QkSmz894APy6a45WEwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91f124ec3cf8b7489393b2e16d0a4c25770abb95afb80ecd48a15d926bd45649","last_reissued_at":"2026-07-05T09:39:35.682045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:35.682045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Heyan Huang, Rong-Cheng Tu, Tian Lan, Xian-Ling Mao, Yuehao Zhao, Zi-Ao Ma","submitted_at":"2024-11-23T08:06:06Z","abstract_excerpt":"Driven by the remarkable progress in diffusion models, text-to-image generation has made significant strides, creating a pressing demand for automatic quality evaluation of generated images. Current state-of-the-art automatic evaluation methods heavily rely on Multi-modal Large Language Models (MLLMs), particularly powerful commercial models like GPT-4o. While these models are highly effective, their substantial costs limit scalability in large-scale evaluations. Adopting open-source MLLMs is an alternative; however, their performance falls short due to significant limitations in processing mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15488","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/2411.15488/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":"2411.15488","created_at":"2026-07-05T09:39:35.682108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15488v1","created_at":"2026-07-05T09:39:35.682108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15488","created_at":"2026-07-05T09:39:35.682108+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHYSJ3B47C3U","created_at":"2026-07-05T09:39:35.682108+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHYSJ3B47C3URE4T","created_at":"2026-07-05T09:39:35.682108+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHYSJ3B4","created_at":"2026-07-05T09:39:35.682108+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/SHYSJ3B47C3URE4TWLQW2CSMEV","json":"https://pith.science/pith/SHYSJ3B47C3URE4TWLQW2CSMEV.json","graph_json":"https://pith.science/api/pith-number/SHYSJ3B47C3URE4TWLQW2CSMEV/graph.json","events_json":"https://pith.science/api/pith-number/SHYSJ3B47C3URE4TWLQW2CSMEV/events.json","paper":"https://pith.science/paper/SHYSJ3B4"},"agent_actions":{"view_html":"https://pith.science/pith/SHYSJ3B47C3URE4TWLQW2CSMEV","download_json":"https://pith.science/pith/SHYSJ3B47C3URE4TWLQW2CSMEV.json","view_paper":"https://pith.science/paper/SHYSJ3B4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15488&json=true","fetch_graph":"https://pith.science/api/pith-number/SHYSJ3B47C3URE4TWLQW2CSMEV/graph.json","fetch_events":"https://pith.science/api/pith-number/SHYSJ3B47C3URE4TWLQW2CSMEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHYSJ3B47C3URE4TWLQW2CSMEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHYSJ3B47C3URE4TWLQW2CSMEV/action/storage_attestation","attest_author":"https://pith.science/pith/SHYSJ3B47C3URE4TWLQW2CSMEV/action/author_attestation","sign_citation":"https://pith.science/pith/SHYSJ3B47C3URE4TWLQW2CSMEV/action/citation_signature","submit_replication":"https://pith.science/pith/SHYSJ3B47C3URE4TWLQW2CSMEV/action/replication_record"}},"created_at":"2026-07-05T09:39:35.682108+00:00","updated_at":"2026-07-05T09:39:35.682108+00:00"}