{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DOV3UWJYXKBFCP4GBEPDOPXY3Z","short_pith_number":"pith:DOV3UWJY","schema_version":"1.0","canonical_sha256":"1babba5938ba82513f86091e373ef8de7419b834eb45bca9198daf72ea6f3e24","source":{"kind":"arxiv","id":"2305.01569","version":2},"attestation_state":"computed","paper":{"title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Joe Penna, Omer Levy, Shahbuland Matiana, Uriel Singer, Yuval Kirstain","submitted_at":"2023-05-02T16:18:11Z","abstract_excerpt":"The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address this issue, we create a web app that enables text-to-image users to generate images and specify their preferences. Using this web app we build Pick-a-Pic, a large, open dataset of text-to-image prompts and real users' preferences over generated images. We leverage this dataset to train a CLIP-based scoring function, PickScore, which exhibits superhuman performance on the task of predicting human preferences. Then, we t"},"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":"2305.01569","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-02T16:18:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50f1238391c7446b624cbf0ea725913333896874426b936d179f22c9124b9d1e","abstract_canon_sha256":"a7bc9c0f2ceb73907ffff84141592721ac9c7f7a50512d64c4b03f5da5b93fc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:54.601560Z","signature_b64":"jWhSo0BozuEtGK1NBfz+3Tuw916XPtEHXBWEZLFspY95op8DcXqk2S/ZseiiIuYV63CUYo4u/vIBOq4JDZ1/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1babba5938ba82513f86091e373ef8de7419b834eb45bca9198daf72ea6f3e24","last_reissued_at":"2026-07-05T07:15:54.600989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:54.600989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Joe Penna, Omer Levy, Shahbuland Matiana, Uriel Singer, Yuval Kirstain","submitted_at":"2023-05-02T16:18:11Z","abstract_excerpt":"The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address this issue, we create a web app that enables text-to-image users to generate images and specify their preferences. Using this web app we build Pick-a-Pic, a large, open dataset of text-to-image prompts and real users' preferences over generated images. We leverage this dataset to train a CLIP-based scoring function, PickScore, which exhibits superhuman performance on the task of predicting human preferences. Then, we t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01569","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/2305.01569/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":"2305.01569","created_at":"2026-07-05T07:15:54.601060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01569v2","created_at":"2026-07-05T07:15:54.601060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01569","created_at":"2026-07-05T07:15:54.601060+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOV3UWJYXKBF","created_at":"2026-07-05T07:15:54.601060+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOV3UWJYXKBFCP4G","created_at":"2026-07-05T07:15:54.601060+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOV3UWJY","created_at":"2026-07-05T07:15:54.601060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09076","citing_title":"Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27771","citing_title":"NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17352","citing_title":"Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15357","citing_title":"MaskAttn-SDXL: Controllable Region-Level Text-To-Image Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":266,"is_internal_anchor":false},{"citing_arxiv_id":"2309.17400","citing_title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.14186","citing_title":"Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26503","citing_title":"Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23536","citing_title":"$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23540","citing_title":"Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06583","citing_title":"Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04494","citing_title":"Towards General Preference Alignment: Diffusion Models at Nash Equilibrium","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2306.09341","citing_title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2307.01952","citing_title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26348","citing_title":"ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOV3UWJYXKBFCP4GBEPDOPXY3Z","json":"https://pith.science/pith/DOV3UWJYXKBFCP4GBEPDOPXY3Z.json","graph_json":"https://pith.science/api/pith-number/DOV3UWJYXKBFCP4GBEPDOPXY3Z/graph.json","events_json":"https://pith.science/api/pith-number/DOV3UWJYXKBFCP4GBEPDOPXY3Z/events.json","paper":"https://pith.science/paper/DOV3UWJY"},"agent_actions":{"view_html":"https://pith.science/pith/DOV3UWJYXKBFCP4GBEPDOPXY3Z","download_json":"https://pith.science/pith/DOV3UWJYXKBFCP4GBEPDOPXY3Z.json","view_paper":"https://pith.science/paper/DOV3UWJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01569&json=true","fetch_graph":"https://pith.science/api/pith-number/DOV3UWJYXKBFCP4GBEPDOPXY3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/DOV3UWJYXKBFCP4GBEPDOPXY3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOV3UWJYXKBFCP4GBEPDOPXY3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOV3UWJYXKBFCP4GBEPDOPXY3Z/action/storage_attestation","attest_author":"https://pith.science/pith/DOV3UWJYXKBFCP4GBEPDOPXY3Z/action/author_attestation","sign_citation":"https://pith.science/pith/DOV3UWJYXKBFCP4GBEPDOPXY3Z/action/citation_signature","submit_replication":"https://pith.science/pith/DOV3UWJYXKBFCP4GBEPDOPXY3Z/action/replication_record"}},"created_at":"2026-07-05T07:15:54.601060+00:00","updated_at":"2026-07-05T07:15:54.601060+00:00"}