{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PEJSR36ZZGUI7WCCW4NGMD3LEN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"24883c4c5112fe938849b1d6cd2412cbc04271201be3e09675b0f26bef2426d7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T09:27:53Z","title_canon_sha256":"cb4098208912fc668f784bd13d3cf65e9dae0579e18458512781e70c5590fa1f"},"schema_version":"1.0","source":{"id":"2211.12112","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.12112","created_at":"2026-07-05T05:18:13Z"},{"alias_kind":"arxiv_version","alias_value":"2211.12112v1","created_at":"2026-07-05T05:18:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12112","created_at":"2026-07-05T05:18:13Z"},{"alias_kind":"pith_short_12","alias_value":"PEJSR36ZZGUI","created_at":"2026-07-05T05:18:13Z"},{"alias_kind":"pith_short_16","alias_value":"PEJSR36ZZGUI7WCC","created_at":"2026-07-05T05:18:13Z"},{"alias_kind":"pith_short_8","alias_value":"PEJSR36Z","created_at":"2026-07-05T05:18:13Z"}],"graph_snapshots":[{"event_id":"sha256:2336f8a236863e5524eced11eafa83b7e63fc074b318ee297a352a2f747f489a","target":"graph","created_at":"2026-07-05T05:18:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.12112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We provide a new multi-task benchmark for evaluating text-to-image models. We perform a human evaluation comparing the most common open-source (Stable Diffusion) and commercial (DALL-E 2) models. Twenty computer science AI graduate students evaluated the two models, on three tasks, at three difficulty levels, across ten prompts each, providing 3,600 ratings. Text-to-image generation has seen rapid progress to the point that many recent models have demonstrated their ability to create realistic high-resolution images for various prompts. However, current text-to-image methods and the broader bo","authors_text":"Alexander E. Siemenn, Armando Solar-Lezama, Arvind Raghavan, Bryan A. Plummer, Gregory Hunter, Iddo Drori, Kate Saenko, Keith Tyser, Ori Kerret, Saisamrit Surbehera, Tonio Buonassisi, Vitali Petsiuk, Yann Hicke, Zad Chin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T09:27:53Z","title":"Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12112","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0e6952770cd060b413d8fcc10d4b409e5d27a4daa3c5d328100ea8ac01c57785","target":"record","created_at":"2026-07-05T05:18:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"24883c4c5112fe938849b1d6cd2412cbc04271201be3e09675b0f26bef2426d7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T09:27:53Z","title_canon_sha256":"cb4098208912fc668f784bd13d3cf65e9dae0579e18458512781e70c5590fa1f"},"schema_version":"1.0","source":{"id":"2211.12112","kind":"arxiv","version":1}},"canonical_sha256":"791328efd9c9a88fd842b71a660f6b236ab004390f9ae5446c85e8d7e9392634","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"791328efd9c9a88fd842b71a660f6b236ab004390f9ae5446c85e8d7e9392634","first_computed_at":"2026-07-05T05:18:13.405345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:13.405345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vxvzKXtZH1ymLleFEkrsKaEz3V9/9tHiSY9iMetM9SnvHF14BPYH1tDJ0eUA30u7V70ybmdcKgVTX5asV7i3Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:13.405832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.12112","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e6952770cd060b413d8fcc10d4b409e5d27a4daa3c5d328100ea8ac01c57785","sha256:2336f8a236863e5524eced11eafa83b7e63fc074b318ee297a352a2f747f489a"],"state_sha256":"28d8ea1a91180001e1e0951744a637ac5a7ba4891cb2881dc63be9ba8831bd12"}