{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SRPENPEE62EMRZM5K5OJN7ESNQ","short_pith_number":"pith:SRPENPEE","schema_version":"1.0","canonical_sha256":"945e46bc84f688c8e59d575c96fc926c2ae5983de5ac97e1cda5afc6a8e6aa82","source":{"kind":"arxiv","id":"2507.09595","version":1},"attestation_state":"computed","paper":{"title":"Demystifying Flux Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Or Greenberg","submitted_at":"2025-07-13T11:51:53Z","abstract_excerpt":"FLUX.1 is a diffusion-based text-to-image generation model developed by Black Forest Labs, designed to achieve faithful text-image alignment while maintaining high image quality and diversity. FLUX is considered state-of-the-art in text-to-image generation, outperforming popular models such as Midjourney, DALL-E 3, Stable Diffusion 3 (SD3), and SDXL. Although publicly available as open source, the authors have not released official technical documentation detailing the model's architecture or training setup. This report summarizes an extensive reverse-engineering effort aimed at demystifying F"},"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":"2507.09595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T11:51:53Z","cross_cats_sorted":[],"title_canon_sha256":"01892880a526de391680e469f61589e15eaf9df34e989e206fd988d60299e37a","abstract_canon_sha256":"e56c0ad4a0b37f5900d9672ebe868c5008eec858a67215e554398ef51e6d180e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:36.492810Z","signature_b64":"a4LcjrLmkT2ZAO6sVjYkftHyk2aTo0/TBGniu7XpCio469r4ZvhWNDFKnVFIKhICu/N7iKceQFXA59G4WyQxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"945e46bc84f688c8e59d575c96fc926c2ae5983de5ac97e1cda5afc6a8e6aa82","last_reissued_at":"2026-07-05T11:36:36.492355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:36.492355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Demystifying Flux Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Or Greenberg","submitted_at":"2025-07-13T11:51:53Z","abstract_excerpt":"FLUX.1 is a diffusion-based text-to-image generation model developed by Black Forest Labs, designed to achieve faithful text-image alignment while maintaining high image quality and diversity. FLUX is considered state-of-the-art in text-to-image generation, outperforming popular models such as Midjourney, DALL-E 3, Stable Diffusion 3 (SD3), and SDXL. Although publicly available as open source, the authors have not released official technical documentation detailing the model's architecture or training setup. This report summarizes an extensive reverse-engineering effort aimed at demystifying F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09595","kind":"arxiv","version":1},"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/2507.09595/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":"2507.09595","created_at":"2026-07-05T11:36:36.492412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09595v1","created_at":"2026-07-05T11:36:36.492412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09595","created_at":"2026-07-05T11:36:36.492412+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRPENPEE62EM","created_at":"2026-07-05T11:36:36.492412+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRPENPEE62EMRZM5","created_at":"2026-07-05T11:36:36.492412+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRPENPEE","created_at":"2026-07-05T11:36:36.492412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05737","citing_title":"Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21611","citing_title":"UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16603","citing_title":"Controlla: Learning Controllability via Graph-Constrained Latent Geometry","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19532","citing_title":"Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09691","citing_title":"CAGE: Bridging the Accuracy-Aesthetics Gap in Educational Diagrams via Code-Anchored Generative Enhancement","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRPENPEE62EMRZM5K5OJN7ESNQ","json":"https://pith.science/pith/SRPENPEE62EMRZM5K5OJN7ESNQ.json","graph_json":"https://pith.science/api/pith-number/SRPENPEE62EMRZM5K5OJN7ESNQ/graph.json","events_json":"https://pith.science/api/pith-number/SRPENPEE62EMRZM5K5OJN7ESNQ/events.json","paper":"https://pith.science/paper/SRPENPEE"},"agent_actions":{"view_html":"https://pith.science/pith/SRPENPEE62EMRZM5K5OJN7ESNQ","download_json":"https://pith.science/pith/SRPENPEE62EMRZM5K5OJN7ESNQ.json","view_paper":"https://pith.science/paper/SRPENPEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09595&json=true","fetch_graph":"https://pith.science/api/pith-number/SRPENPEE62EMRZM5K5OJN7ESNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SRPENPEE62EMRZM5K5OJN7ESNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRPENPEE62EMRZM5K5OJN7ESNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRPENPEE62EMRZM5K5OJN7ESNQ/action/storage_attestation","attest_author":"https://pith.science/pith/SRPENPEE62EMRZM5K5OJN7ESNQ/action/author_attestation","sign_citation":"https://pith.science/pith/SRPENPEE62EMRZM5K5OJN7ESNQ/action/citation_signature","submit_replication":"https://pith.science/pith/SRPENPEE62EMRZM5K5OJN7ESNQ/action/replication_record"}},"created_at":"2026-07-05T11:36:36.492412+00:00","updated_at":"2026-07-05T11:36:36.492412+00:00"}