{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3THH3WOECJ62IWTD2D3WRE4CSW","short_pith_number":"pith:3THH3WOE","schema_version":"1.0","canonical_sha256":"dcce7dd9c4127da45a63d0f768938295900a06b24c4c19c0826763acf4119dac","source":{"kind":"arxiv","id":"2202.04053","version":3},"attestation_state":"computed","paper":{"title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhay Zala, Jaemin Cho, Mohit Bansal","submitted_at":"2022-02-08T18:36:52Z","abstract_excerpt":"Recently, DALL-E, a multimodal transformer language model, and its variants, including diffusion models, have shown high-quality text-to-image generation capabilities. However, despite the realistic image generation results, there has not been a detailed analysis of how to evaluate such models. In this work, we investigate the visual reasoning capabilities and social biases of different text-to-image models, covering both multimodal transformer language models and diffusion models. First, we measure three visual reasoning skills: object recognition, object counting, and spatial relation unders"},"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":"2202.04053","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-08T18:36:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"187a85497242044c6309dd69d35cf6556f59b3895c33a6517a7eb0ea9bf19c99","abstract_canon_sha256":"6cd37e5d6eacc6012604f236877fa5147bd6ddd028eac7d2bfe7db49eab154b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:20.041348Z","signature_b64":"3YoOw/zdkR3gEwJ1QJLWSbD4f8YBJZazMrh7/a0Fxeh5oz8b62d1PwAdciEmfd+GZyLaQu8WfMtVzx15GzjPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcce7dd9c4127da45a63d0f768938295900a06b24c4c19c0826763acf4119dac","last_reissued_at":"2026-07-05T06:46:20.040899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:20.040899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhay Zala, Jaemin Cho, Mohit Bansal","submitted_at":"2022-02-08T18:36:52Z","abstract_excerpt":"Recently, DALL-E, a multimodal transformer language model, and its variants, including diffusion models, have shown high-quality text-to-image generation capabilities. However, despite the realistic image generation results, there has not been a detailed analysis of how to evaluate such models. In this work, we investigate the visual reasoning capabilities and social biases of different text-to-image models, covering both multimodal transformer language models and diffusion models. First, we measure three visual reasoning skills: object recognition, object counting, and spatial relation unders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04053","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/2202.04053/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":"2202.04053","created_at":"2026-07-05T06:46:20.040966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.04053v3","created_at":"2026-07-05T06:46:20.040966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04053","created_at":"2026-07-05T06:46:20.040966+00:00"},{"alias_kind":"pith_short_12","alias_value":"3THH3WOECJ62","created_at":"2026-07-05T06:46:20.040966+00:00"},{"alias_kind":"pith_short_16","alias_value":"3THH3WOECJ62IWTD","created_at":"2026-07-05T06:46:20.040966+00:00"},{"alias_kind":"pith_short_8","alias_value":"3THH3WOE","created_at":"2026-07-05T06:46:20.040966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2204.03458","citing_title":"Video Diffusion Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2205.11487","citing_title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21036","citing_title":"Who Defines Fairness? Target-Based Prompting for Demographic Representation in Generative Models","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3THH3WOECJ62IWTD2D3WRE4CSW","json":"https://pith.science/pith/3THH3WOECJ62IWTD2D3WRE4CSW.json","graph_json":"https://pith.science/api/pith-number/3THH3WOECJ62IWTD2D3WRE4CSW/graph.json","events_json":"https://pith.science/api/pith-number/3THH3WOECJ62IWTD2D3WRE4CSW/events.json","paper":"https://pith.science/paper/3THH3WOE"},"agent_actions":{"view_html":"https://pith.science/pith/3THH3WOECJ62IWTD2D3WRE4CSW","download_json":"https://pith.science/pith/3THH3WOECJ62IWTD2D3WRE4CSW.json","view_paper":"https://pith.science/paper/3THH3WOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.04053&json=true","fetch_graph":"https://pith.science/api/pith-number/3THH3WOECJ62IWTD2D3WRE4CSW/graph.json","fetch_events":"https://pith.science/api/pith-number/3THH3WOECJ62IWTD2D3WRE4CSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3THH3WOECJ62IWTD2D3WRE4CSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3THH3WOECJ62IWTD2D3WRE4CSW/action/storage_attestation","attest_author":"https://pith.science/pith/3THH3WOECJ62IWTD2D3WRE4CSW/action/author_attestation","sign_citation":"https://pith.science/pith/3THH3WOECJ62IWTD2D3WRE4CSW/action/citation_signature","submit_replication":"https://pith.science/pith/3THH3WOECJ62IWTD2D3WRE4CSW/action/replication_record"}},"created_at":"2026-07-05T06:46:20.040966+00:00","updated_at":"2026-07-05T06:46:20.040966+00:00"}