{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WSGSFIJHYSP4SABITB3IFLVI2D","short_pith_number":"pith:WSGSFIJH","schema_version":"1.0","canonical_sha256":"b48d22a127c49fc90028987682aea8d0e6f4fbf254d993f0ff89607ebbd70f5d","source":{"kind":"arxiv","id":"2210.14896","version":4},"attestation_state":"computed","paper":{"title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Benjamin Hoover, David Munechika, Duen Horng Chau, Evan Montoya, Haoyang Yang, Zijie J. Wang","submitted_at":"2022-10-26T17:54:20Z","abstract_excerpt":"With recent advancements in diffusion models, users can generate high-quality images by writing text prompts in natural language. However, generating images with desired details requires proper prompts, and it is often unclear how a model reacts to different prompts or what the best prompts are. To help researchers tackle these critical challenges, we introduce DiffusionDB, the first large-scale text-to-image prompt dataset totaling 6.5TB, containing 14 million images generated by Stable Diffusion, 1.8 million unique prompts, and hyperparameters specified by real users. We analyze the syntacti"},"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":"2210.14896","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-26T17:54:20Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"685c6a9e6c41c6288da3288eca09c206985558980938c19ea4973c74ae073b4e","abstract_canon_sha256":"f0c9b1588b209ffbe0aef2f4884e72781dbd1f096130e50b6a0a50bc82c3e6ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:14.609807Z","signature_b64":"9KgOdlz78yYkdXYY532igux6b/ESxBiDltcmMzA1TSEsYkdAZS8Mc0dxCEhpOv9xei1t1GTqNxXjMSdp9SBdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b48d22a127c49fc90028987682aea8d0e6f4fbf254d993f0ff89607ebbd70f5d","last_reissued_at":"2026-07-05T06:28:14.609383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:14.609383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Benjamin Hoover, David Munechika, Duen Horng Chau, Evan Montoya, Haoyang Yang, Zijie J. Wang","submitted_at":"2022-10-26T17:54:20Z","abstract_excerpt":"With recent advancements in diffusion models, users can generate high-quality images by writing text prompts in natural language. However, generating images with desired details requires proper prompts, and it is often unclear how a model reacts to different prompts or what the best prompts are. To help researchers tackle these critical challenges, we introduce DiffusionDB, the first large-scale text-to-image prompt dataset totaling 6.5TB, containing 14 million images generated by Stable Diffusion, 1.8 million unique prompts, and hyperparameters specified by real users. We analyze the syntacti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14896","kind":"arxiv","version":4},"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/2210.14896/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":"2210.14896","created_at":"2026-07-05T06:28:14.609447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14896v4","created_at":"2026-07-05T06:28:14.609447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14896","created_at":"2026-07-05T06:28:14.609447+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSGSFIJHYSP4","created_at":"2026-07-05T06:28:14.609447+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSGSFIJHYSP4SABI","created_at":"2026-07-05T06:28:14.609447+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSGSFIJH","created_at":"2026-07-05T06:28:14.609447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23679","citing_title":"Semantic Browsing: Controllable Diversity for Image Generation","ref_index":185,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05829","citing_title":"Gender Artifacts from Art History to Text-to-Image Generation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01803","citing_title":"OctoT2I: A Self-Evolving Agentic Text-to-Image Router","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29569","citing_title":"LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21210","citing_title":"Toward Generalizable Forgery Detection and Reasoning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17726","citing_title":"Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21864","citing_title":"Deepfakes: we need to re-think the concept of \"real\" images","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06779","citing_title":"VASR: Variance-Aware Systematic Resampling for Reward-Guided Diffusion","ref_index":44,"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":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10522","citing_title":"SEED: A Large-Scale Benchmark for Provenance Tracing in Sequential Deepfake Facial Edits","ref_index":42,"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":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06779","citing_title":"VASR: Variance-Aware Systematic Resampling for Reward-Guided Diffusion","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14914","citing_title":"Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WSGSFIJHYSP4SABITB3IFLVI2D","json":"https://pith.science/pith/WSGSFIJHYSP4SABITB3IFLVI2D.json","graph_json":"https://pith.science/api/pith-number/WSGSFIJHYSP4SABITB3IFLVI2D/graph.json","events_json":"https://pith.science/api/pith-number/WSGSFIJHYSP4SABITB3IFLVI2D/events.json","paper":"https://pith.science/paper/WSGSFIJH"},"agent_actions":{"view_html":"https://pith.science/pith/WSGSFIJHYSP4SABITB3IFLVI2D","download_json":"https://pith.science/pith/WSGSFIJHYSP4SABITB3IFLVI2D.json","view_paper":"https://pith.science/paper/WSGSFIJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14896&json=true","fetch_graph":"https://pith.science/api/pith-number/WSGSFIJHYSP4SABITB3IFLVI2D/graph.json","fetch_events":"https://pith.science/api/pith-number/WSGSFIJHYSP4SABITB3IFLVI2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSGSFIJHYSP4SABITB3IFLVI2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSGSFIJHYSP4SABITB3IFLVI2D/action/storage_attestation","attest_author":"https://pith.science/pith/WSGSFIJHYSP4SABITB3IFLVI2D/action/author_attestation","sign_citation":"https://pith.science/pith/WSGSFIJHYSP4SABITB3IFLVI2D/action/citation_signature","submit_replication":"https://pith.science/pith/WSGSFIJHYSP4SABITB3IFLVI2D/action/replication_record"}},"created_at":"2026-07-05T06:28:14.609447+00:00","updated_at":"2026-07-05T06:28:14.609447+00:00"}