{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:467N55WQN33V6MJCXYNB3DVLUN","short_pith_number":"pith:467N55WQ","schema_version":"1.0","canonical_sha256":"e7bedef6d06ef75f3122be1a1d8eaba3517ef581a3328d68c804923452ad9cfe","source":{"kind":"arxiv","id":"2312.14867","version":2},"attestation_state":"computed","paper":{"title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Cong Wei, Dongfu Jiang, Max Ku, Wenhu Chen, Xiang Yue","submitted_at":"2023-12-22T17:45:19Z","abstract_excerpt":"In the rapidly advancing field of conditional image generation research, challenges such as limited explainability lie in effectively evaluating the performance and capabilities of various models. This paper introduces VIEScore, a Visual Instruction-guided Explainable metric for evaluating any conditional image generation tasks. VIEScore leverages general knowledge from Multimodal Large Language Models (MLLMs) as the backbone and does not require training or fine-tuning. We evaluate VIEScore on seven prominent tasks in conditional image tasks and found: (1) VIEScore (GPT4-o) achieves a high Sp"},"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":"2312.14867","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T17:45:19Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"798e600d660c1b6cea18327277e1b88b1bc6ed0c967bb4c9477e8f4e634176ee","abstract_canon_sha256":"a2a2065da1cecdfaa570eee06322052adf5f963c035d590e897f60329fe0ffd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:17.230864Z","signature_b64":"PbwXfFEMUtJXMkiyR1nLTpcEplIMHynDSrPZILiCZnIFmf8mdA+i12aR+r3WXqNyQ9bmOlPOmOlLabXTksRuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7bedef6d06ef75f3122be1a1d8eaba3517ef581a3328d68c804923452ad9cfe","last_reissued_at":"2026-07-05T08:26:17.230389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:17.230389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Cong Wei, Dongfu Jiang, Max Ku, Wenhu Chen, Xiang Yue","submitted_at":"2023-12-22T17:45:19Z","abstract_excerpt":"In the rapidly advancing field of conditional image generation research, challenges such as limited explainability lie in effectively evaluating the performance and capabilities of various models. This paper introduces VIEScore, a Visual Instruction-guided Explainable metric for evaluating any conditional image generation tasks. VIEScore leverages general knowledge from Multimodal Large Language Models (MLLMs) as the backbone and does not require training or fine-tuning. We evaluate VIEScore on seven prominent tasks in conditional image tasks and found: (1) VIEScore (GPT4-o) achieves a high Sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14867","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/2312.14867/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":"2312.14867","created_at":"2026-07-05T08:26:17.230447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14867v2","created_at":"2026-07-05T08:26:17.230447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14867","created_at":"2026-07-05T08:26:17.230447+00:00"},{"alias_kind":"pith_short_12","alias_value":"467N55WQN33V","created_at":"2026-07-05T08:26:17.230447+00:00"},{"alias_kind":"pith_short_16","alias_value":"467N55WQN33V6MJC","created_at":"2026-07-05T08:26:17.230447+00:00"},{"alias_kind":"pith_short_8","alias_value":"467N55WQ","created_at":"2026-07-05T08:26:17.230447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26872","citing_title":"SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01985","citing_title":"MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01022","citing_title":"ProductWebGen: Benchmarking Multimodal Product Webpage Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20278","citing_title":"ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26872","citing_title":"SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04300","citing_title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20278","citing_title":"ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2406.03520","citing_title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2504.20690","citing_title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24625","citing_title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/467N55WQN33V6MJCXYNB3DVLUN","json":"https://pith.science/pith/467N55WQN33V6MJCXYNB3DVLUN.json","graph_json":"https://pith.science/api/pith-number/467N55WQN33V6MJCXYNB3DVLUN/graph.json","events_json":"https://pith.science/api/pith-number/467N55WQN33V6MJCXYNB3DVLUN/events.json","paper":"https://pith.science/paper/467N55WQ"},"agent_actions":{"view_html":"https://pith.science/pith/467N55WQN33V6MJCXYNB3DVLUN","download_json":"https://pith.science/pith/467N55WQN33V6MJCXYNB3DVLUN.json","view_paper":"https://pith.science/paper/467N55WQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14867&json=true","fetch_graph":"https://pith.science/api/pith-number/467N55WQN33V6MJCXYNB3DVLUN/graph.json","fetch_events":"https://pith.science/api/pith-number/467N55WQN33V6MJCXYNB3DVLUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/467N55WQN33V6MJCXYNB3DVLUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/467N55WQN33V6MJCXYNB3DVLUN/action/storage_attestation","attest_author":"https://pith.science/pith/467N55WQN33V6MJCXYNB3DVLUN/action/author_attestation","sign_citation":"https://pith.science/pith/467N55WQN33V6MJCXYNB3DVLUN/action/citation_signature","submit_replication":"https://pith.science/pith/467N55WQN33V6MJCXYNB3DVLUN/action/replication_record"}},"created_at":"2026-07-05T08:26:17.230447+00:00","updated_at":"2026-07-05T08:26:17.230447+00:00"}