{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PGNSOGP2T67MR3AZ2XWDGPJABU","short_pith_number":"pith:PGNSOGP2","schema_version":"1.0","canonical_sha256":"799b2719fa9fbec8ec19d5ec333d200d000ad9e89a4de8adbc15f5fadcde0bf3","source":{"kind":"arxiv","id":"2303.11897","version":3},"attestation_state":"computed","paper":{"title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benlin Liu, Jungo Kasai, Mari Ostendorf, Noah A Smith, Ranjay Krishna, Yizhong Wang, Yushi Hu","submitted_at":"2023-03-21T14:41:02Z","abstract_excerpt":"Despite thousands of researchers, engineers, and artists actively working on improving text-to-image generation models, systems often fail to produce images that accurately align with the text inputs. We introduce TIFA (Text-to-Image Faithfulness evaluation with question Answering), an automatic evaluation metric that measures the faithfulness of a generated image to its text input via visual question answering (VQA). Specifically, given a text input, we automatically generate several question-answer pairs using a language model. We calculate image faithfulness by checking whether existing VQA"},"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":"2303.11897","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-21T14:41:02Z","cross_cats_sorted":[],"title_canon_sha256":"95ab3d0e50c3293c192d1164c62acd9b2a2a7492a2eb12fb84ae0b4685587217","abstract_canon_sha256":"e0e6925feeeb72d9432740a23904122f1aa12e116f08dde2472b53cd39a352be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:20.212442Z","signature_b64":"cAXpojzgY3oSVQoJGKC8kYEgA9Vc0T1V2Trgbp5wM4qqj/VVzSbHbrzdbP3tzbmohoUwZFuEUUahYUU5qQYkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"799b2719fa9fbec8ec19d5ec333d200d000ad9e89a4de8adbc15f5fadcde0bf3","last_reissued_at":"2026-07-05T06:42:20.211993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:20.211993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benlin Liu, Jungo Kasai, Mari Ostendorf, Noah A Smith, Ranjay Krishna, Yizhong Wang, Yushi Hu","submitted_at":"2023-03-21T14:41:02Z","abstract_excerpt":"Despite thousands of researchers, engineers, and artists actively working on improving text-to-image generation models, systems often fail to produce images that accurately align with the text inputs. We introduce TIFA (Text-to-Image Faithfulness evaluation with question Answering), an automatic evaluation metric that measures the faithfulness of a generated image to its text input via visual question answering (VQA). Specifically, given a text input, we automatically generate several question-answer pairs using a language model. We calculate image faithfulness by checking whether existing VQA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11897","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/2303.11897/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":"2303.11897","created_at":"2026-07-05T06:42:20.212050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11897v3","created_at":"2026-07-05T06:42:20.212050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11897","created_at":"2026-07-05T06:42:20.212050+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGNSOGP2T67M","created_at":"2026-07-05T06:42:20.212050+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGNSOGP2T67MR3AZ","created_at":"2026-07-05T06:42:20.212050+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGNSOGP2","created_at":"2026-07-05T06:42:20.212050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00402","citing_title":"The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models","ref_index":11,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":57,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08409","citing_title":"Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2404.12390","citing_title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2311.12983","citing_title":"GAIA: a benchmark for General AI Assistants","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24052","citing_title":"QEVA: A Reference-Free Evaluation Metric for Narrative Video Summarization with Multimodal Question Answering","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGNSOGP2T67MR3AZ2XWDGPJABU","json":"https://pith.science/pith/PGNSOGP2T67MR3AZ2XWDGPJABU.json","graph_json":"https://pith.science/api/pith-number/PGNSOGP2T67MR3AZ2XWDGPJABU/graph.json","events_json":"https://pith.science/api/pith-number/PGNSOGP2T67MR3AZ2XWDGPJABU/events.json","paper":"https://pith.science/paper/PGNSOGP2"},"agent_actions":{"view_html":"https://pith.science/pith/PGNSOGP2T67MR3AZ2XWDGPJABU","download_json":"https://pith.science/pith/PGNSOGP2T67MR3AZ2XWDGPJABU.json","view_paper":"https://pith.science/paper/PGNSOGP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11897&json=true","fetch_graph":"https://pith.science/api/pith-number/PGNSOGP2T67MR3AZ2XWDGPJABU/graph.json","fetch_events":"https://pith.science/api/pith-number/PGNSOGP2T67MR3AZ2XWDGPJABU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGNSOGP2T67MR3AZ2XWDGPJABU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGNSOGP2T67MR3AZ2XWDGPJABU/action/storage_attestation","attest_author":"https://pith.science/pith/PGNSOGP2T67MR3AZ2XWDGPJABU/action/author_attestation","sign_citation":"https://pith.science/pith/PGNSOGP2T67MR3AZ2XWDGPJABU/action/citation_signature","submit_replication":"https://pith.science/pith/PGNSOGP2T67MR3AZ2XWDGPJABU/action/replication_record"}},"created_at":"2026-07-05T06:42:20.212050+00:00","updated_at":"2026-07-05T06:42:20.212050+00:00"}