{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JWEDMMPE46WZVG6ROTX2RF5XA2","short_pith_number":"pith:JWEDMMPE","schema_version":"1.0","canonical_sha256":"4d883631e4e7ad9a9bd174efa897b706b0da080abe3be91c3f9a6db367cc33f3","source":{"kind":"arxiv","id":"2406.13743","version":3},"attestation_state":"computed","paper":{"title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Baiqi Li, Deepak Pathak, Deva Ramanan, Graham Neubig, Jiayao Li, Kewen Wu, Pengchuan Zhang, Tiffany Ling, Xide Xia, Yixin Fei, Zhiqiu Lin","submitted_at":"2024-06-19T18:00:07Z","abstract_excerpt":"While text-to-visual models now produce photo-realistic images and videos, they struggle with compositional text prompts involving attributes, relationships, and higher-order reasoning such as logic and comparison. In this work, we conduct an extensive human study on GenAI-Bench to evaluate the performance of leading image and video generation models in various aspects of compositional text-to-visual generation. We also compare automated evaluation metrics against our collected human ratings and find that VQAScore -- a metric measuring the likelihood that a VQA model views an image as accurate"},"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":"2406.13743","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-19T18:00:07Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"987188c0d95ce261e5d58305830851b227a5aef146daec34ab5b481cc544c363","abstract_canon_sha256":"1d385151d393b57ac9944aef4b86d40dfc4e96098be15b9757ff3bf704cb9f46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:17.477073Z","signature_b64":"CfTXkvsdwp48+TD3ookvqOU12hyjEQg82z10ZNz3uKj1zWD4inQB7W/fUkYTnVQpeS/14LSV5VsM8xMM1FQ2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d883631e4e7ad9a9bd174efa897b706b0da080abe3be91c3f9a6db367cc33f3","last_reissued_at":"2026-07-05T09:30:17.476574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:17.476574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Baiqi Li, Deepak Pathak, Deva Ramanan, Graham Neubig, Jiayao Li, Kewen Wu, Pengchuan Zhang, Tiffany Ling, Xide Xia, Yixin Fei, Zhiqiu Lin","submitted_at":"2024-06-19T18:00:07Z","abstract_excerpt":"While text-to-visual models now produce photo-realistic images and videos, they struggle with compositional text prompts involving attributes, relationships, and higher-order reasoning such as logic and comparison. In this work, we conduct an extensive human study on GenAI-Bench to evaluate the performance of leading image and video generation models in various aspects of compositional text-to-visual generation. We also compare automated evaluation metrics against our collected human ratings and find that VQAScore -- a metric measuring the likelihood that a VQA model views an image as accurate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13743","kind":"arxiv","version":3},"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/2406.13743/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":"2406.13743","created_at":"2026-07-05T09:30:17.476633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13743v3","created_at":"2026-07-05T09:30:17.476633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13743","created_at":"2026-07-05T09:30:17.476633+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWEDMMPE46WZ","created_at":"2026-07-05T09:30:17.476633+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWEDMMPE46WZVG6R","created_at":"2026-07-05T09:30:17.476633+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWEDMMPE","created_at":"2026-07-05T09:30:17.476633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05382","citing_title":"Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24888","citing_title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","ref_index":163,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26738","citing_title":"Do Image Editing Models Understand Lighting?","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21498","citing_title":"Balancing Performance and Diversity in GRPO Autoregressive Text-to-Image Post-Training","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01312","citing_title":"KathaTrace: Diagnosing Semantic Trajectory Collapse in Generated Visual Narratives","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28091","citing_title":"Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation","ref_index":8,"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":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17602","citing_title":"AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17602","citing_title":"AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18324","citing_title":"Improved Baselines with Representation Autoencoders","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19111","citing_title":"FAGER: Factually Grounded Evaluation and Refinement of Text-to-Image Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2603.00166","citing_title":"Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07265","citing_title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20329","citing_title":"Image Generators are Generalist Vision Learners","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13974","citing_title":"Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13062","citing_title":"Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06170","citing_title":"DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20329","citing_title":"Image Generators are Generalist Vision Learners","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20157","citing_title":"HumanScore: Benchmarking Human Motions in Generated Videos","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08641","citing_title":"On Semiotic-Grounded Interpretive Evaluation of Generative Art","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15742","citing_title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWEDMMPE46WZVG6ROTX2RF5XA2","json":"https://pith.science/pith/JWEDMMPE46WZVG6ROTX2RF5XA2.json","graph_json":"https://pith.science/api/pith-number/JWEDMMPE46WZVG6ROTX2RF5XA2/graph.json","events_json":"https://pith.science/api/pith-number/JWEDMMPE46WZVG6ROTX2RF5XA2/events.json","paper":"https://pith.science/paper/JWEDMMPE"},"agent_actions":{"view_html":"https://pith.science/pith/JWEDMMPE46WZVG6ROTX2RF5XA2","download_json":"https://pith.science/pith/JWEDMMPE46WZVG6ROTX2RF5XA2.json","view_paper":"https://pith.science/paper/JWEDMMPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13743&json=true","fetch_graph":"https://pith.science/api/pith-number/JWEDMMPE46WZVG6ROTX2RF5XA2/graph.json","fetch_events":"https://pith.science/api/pith-number/JWEDMMPE46WZVG6ROTX2RF5XA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWEDMMPE46WZVG6ROTX2RF5XA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWEDMMPE46WZVG6ROTX2RF5XA2/action/storage_attestation","attest_author":"https://pith.science/pith/JWEDMMPE46WZVG6ROTX2RF5XA2/action/author_attestation","sign_citation":"https://pith.science/pith/JWEDMMPE46WZVG6ROTX2RF5XA2/action/citation_signature","submit_replication":"https://pith.science/pith/JWEDMMPE46WZVG6ROTX2RF5XA2/action/replication_record"}},"created_at":"2026-07-05T09:30:17.476633+00:00","updated_at":"2026-07-05T09:30:17.476633+00:00"}