{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PFJFKA2FYAAJFNTQ32DFKHBJS3","short_pith_number":"pith:PFJFKA2F","schema_version":"1.0","canonical_sha256":"7952550345c00092b670de86551c2996d8b3a0f1cb7f3e964b7517679a85e40d","source":{"kind":"arxiv","id":"2305.15328","version":2},"attestation_state":"computed","paper":{"title":"Visual Programming for Text-to-Image Generation and Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhay Zala, Jaemin Cho, Mohit Bansal","submitted_at":"2023-05-24T16:42:17Z","abstract_excerpt":"As large language models have demonstrated impressive performance in many domains, recent works have adopted language models (LMs) as controllers of visual modules for vision-and-language tasks. While existing work focuses on equipping LMs with visual understanding, we propose two novel interpretable/explainable visual programming frameworks for text-to-image (T2I) generation and evaluation. First, we introduce VPGen, an interpretable step-by-step T2I generation framework that decomposes T2I generation into three steps: object/count generation, layout generation, and image generation. We emplo"},"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":"2305.15328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T16:42:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"0acd3265f5cd64a30ceb65c8b3577428f325122721fda2c81f150b5ab816c3da","abstract_canon_sha256":"8afbb6e45c23a4c060b86f48d80118ca550b79da576725ce8e92376fb4a2e0e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:43.506781Z","signature_b64":"6eL6rJasKcHr9MqfFhYIeXDyZ60IdCxpq7LYO+UdboDCZnardWHjxosY01SZQQoU1Py8fJWn1Z/avtop8p0RCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7952550345c00092b670de86551c2996d8b3a0f1cb7f3e964b7517679a85e40d","last_reissued_at":"2026-07-05T07:05:43.506251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:43.506251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Programming for Text-to-Image Generation and Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhay Zala, Jaemin Cho, Mohit Bansal","submitted_at":"2023-05-24T16:42:17Z","abstract_excerpt":"As large language models have demonstrated impressive performance in many domains, recent works have adopted language models (LMs) as controllers of visual modules for vision-and-language tasks. While existing work focuses on equipping LMs with visual understanding, we propose two novel interpretable/explainable visual programming frameworks for text-to-image (T2I) generation and evaluation. First, we introduce VPGen, an interpretable step-by-step T2I generation framework that decomposes T2I generation into three steps: object/count generation, layout generation, and image generation. We emplo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15328","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/2305.15328/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":"2305.15328","created_at":"2026-07-05T07:05:43.506312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15328v2","created_at":"2026-07-05T07:05:43.506312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15328","created_at":"2026-07-05T07:05:43.506312+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFJFKA2FYAAJ","created_at":"2026-07-05T07:05:43.506312+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFJFKA2FYAAJFNTQ","created_at":"2026-07-05T07:05:43.506312+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFJFKA2F","created_at":"2026-07-05T07:05:43.506312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.05135","citing_title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFJFKA2FYAAJFNTQ32DFKHBJS3","json":"https://pith.science/pith/PFJFKA2FYAAJFNTQ32DFKHBJS3.json","graph_json":"https://pith.science/api/pith-number/PFJFKA2FYAAJFNTQ32DFKHBJS3/graph.json","events_json":"https://pith.science/api/pith-number/PFJFKA2FYAAJFNTQ32DFKHBJS3/events.json","paper":"https://pith.science/paper/PFJFKA2F"},"agent_actions":{"view_html":"https://pith.science/pith/PFJFKA2FYAAJFNTQ32DFKHBJS3","download_json":"https://pith.science/pith/PFJFKA2FYAAJFNTQ32DFKHBJS3.json","view_paper":"https://pith.science/paper/PFJFKA2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15328&json=true","fetch_graph":"https://pith.science/api/pith-number/PFJFKA2FYAAJFNTQ32DFKHBJS3/graph.json","fetch_events":"https://pith.science/api/pith-number/PFJFKA2FYAAJFNTQ32DFKHBJS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFJFKA2FYAAJFNTQ32DFKHBJS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFJFKA2FYAAJFNTQ32DFKHBJS3/action/storage_attestation","attest_author":"https://pith.science/pith/PFJFKA2FYAAJFNTQ32DFKHBJS3/action/author_attestation","sign_citation":"https://pith.science/pith/PFJFKA2FYAAJFNTQ32DFKHBJS3/action/citation_signature","submit_replication":"https://pith.science/pith/PFJFKA2FYAAJFNTQ32DFKHBJS3/action/replication_record"}},"created_at":"2026-07-05T07:05:43.506312+00:00","updated_at":"2026-07-05T07:05:43.506312+00:00"}