{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6MUSKKKKOHK537LHBRPLDO3J7U","short_pith_number":"pith:6MUSKKKK","schema_version":"1.0","canonical_sha256":"f32925294a71d5ddfd670c5eb1bb69fd1daefdae82cbcf4760f2174536d28453","source":{"kind":"arxiv","id":"2305.18295","version":5},"attestation_state":"computed","paper":{"title":"RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxiao Liu, Guanglu Song, Ping Luo, Qiushan Guo, Yu Liu, Zeyue Xue, Zhuofan Zong","submitted_at":"2023-05-29T17:59:41Z","abstract_excerpt":"Text-to-image generation has recently witnessed remarkable achievements. We introduce a text-conditional image diffusion model, termed RAPHAEL, to generate highly artistic images, which accurately portray the text prompts, encompassing multiple nouns, adjectives, and verbs. This is achieved by stacking tens of mixture-of-experts (MoEs) layers, i.e., space-MoE and time-MoE layers, enabling billions of diffusion paths (routes) from the network input to the output. Each path intuitively functions as a \"painter\" for depicting a particular textual concept onto a specified image region at a diffusio"},"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":"2305.18295","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-29T17:59:41Z","cross_cats_sorted":[],"title_canon_sha256":"414f9548bfc9f1570f12daff51864dc80da9cd95f645e3206017302ebc50e8a1","abstract_canon_sha256":"1c982770daa279744218c95b482e8df38276719486ff4cea87aea5134f813295"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:01.257347Z","signature_b64":"KgaNPKuYH/feVEnas2M7IwJ2kSxQ/oKjPjXeMO3yX9hqbRBATJIJsbPGrf83CVjcH/TP4qZUd/UgtNRpB/LfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f32925294a71d5ddfd670c5eb1bb69fd1daefdae82cbcf4760f2174536d28453","last_reissued_at":"2026-07-05T07:54:01.256823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:01.256823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxiao Liu, Guanglu Song, Ping Luo, Qiushan Guo, Yu Liu, Zeyue Xue, Zhuofan Zong","submitted_at":"2023-05-29T17:59:41Z","abstract_excerpt":"Text-to-image generation has recently witnessed remarkable achievements. We introduce a text-conditional image diffusion model, termed RAPHAEL, to generate highly artistic images, which accurately portray the text prompts, encompassing multiple nouns, adjectives, and verbs. This is achieved by stacking tens of mixture-of-experts (MoEs) layers, i.e., space-MoE and time-MoE layers, enabling billions of diffusion paths (routes) from the network input to the output. Each path intuitively functions as a \"painter\" for depicting a particular textual concept onto a specified image region at a diffusio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18295","kind":"arxiv","version":5},"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/2305.18295/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":"2305.18295","created_at":"2026-07-05T07:54:01.256888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18295v5","created_at":"2026-07-05T07:54:01.256888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18295","created_at":"2026-07-05T07:54:01.256888+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MUSKKKKOHK5","created_at":"2026-07-05T07:54:01.256888+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MUSKKKKOHK537LH","created_at":"2026-07-05T07:54:01.256888+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MUSKKKK","created_at":"2026-07-05T07:54:01.256888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.06525","citing_title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2308.06721","citing_title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MUSKKKKOHK537LHBRPLDO3J7U","json":"https://pith.science/pith/6MUSKKKKOHK537LHBRPLDO3J7U.json","graph_json":"https://pith.science/api/pith-number/6MUSKKKKOHK537LHBRPLDO3J7U/graph.json","events_json":"https://pith.science/api/pith-number/6MUSKKKKOHK537LHBRPLDO3J7U/events.json","paper":"https://pith.science/paper/6MUSKKKK"},"agent_actions":{"view_html":"https://pith.science/pith/6MUSKKKKOHK537LHBRPLDO3J7U","download_json":"https://pith.science/pith/6MUSKKKKOHK537LHBRPLDO3J7U.json","view_paper":"https://pith.science/paper/6MUSKKKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18295&json=true","fetch_graph":"https://pith.science/api/pith-number/6MUSKKKKOHK537LHBRPLDO3J7U/graph.json","fetch_events":"https://pith.science/api/pith-number/6MUSKKKKOHK537LHBRPLDO3J7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MUSKKKKOHK537LHBRPLDO3J7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MUSKKKKOHK537LHBRPLDO3J7U/action/storage_attestation","attest_author":"https://pith.science/pith/6MUSKKKKOHK537LHBRPLDO3J7U/action/author_attestation","sign_citation":"https://pith.science/pith/6MUSKKKKOHK537LHBRPLDO3J7U/action/citation_signature","submit_replication":"https://pith.science/pith/6MUSKKKKOHK537LHBRPLDO3J7U/action/replication_record"}},"created_at":"2026-07-05T07:54:01.256888+00:00","updated_at":"2026-07-05T07:54:01.256888+00:00"}