{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HSWUOZRDQPOEIZDTWDIYH2J7NU","short_pith_number":"pith:HSWUOZRD","schema_version":"1.0","canonical_sha256":"3cad47662383dc446473b0d183e93f6d03b965485354e6585a9547e5e01ede70","source":{"kind":"arxiv","id":"2311.16090","version":1},"attestation_state":"computed","paper":{"title":"Self-correcting LLM-controlled Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyi Li, Joseph E. Gonzalez, Long Lian, Trevor Darrell, Tsung-Han Wu","submitted_at":"2023-11-27T18:56:37Z","abstract_excerpt":"Text-to-image generation has witnessed significant progress with the advent of diffusion models. Despite the ability to generate photorealistic images, current text-to-image diffusion models still often struggle to accurately interpret and follow complex input text prompts. In contrast to existing models that aim to generate images only with their best effort, we introduce Self-correcting LLM-controlled Diffusion (SLD). SLD is a framework that generates an image from the input prompt, assesses its alignment with the prompt, and performs self-corrections on the inaccuracies in the generated ima"},"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":"2311.16090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T18:56:37Z","cross_cats_sorted":[],"title_canon_sha256":"d678fbb30d99ddab819679f22d1eae0535212d4b3f2a7bce336d140e59cbea30","abstract_canon_sha256":"0cd35c88bf005b83fc87a7a6167dcb2587003d521087e72871110c0b4a29cd8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:20.172732Z","signature_b64":"6Xv7kFvOTczyjN6SkBvhTkV6va20FYbSWsdLmOMYExXA+ixu2+YvUMM1KS4le3TOAP/n93g/8lnz5kcBFnNKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cad47662383dc446473b0d183e93f6d03b965485354e6585a9547e5e01ede70","last_reissued_at":"2026-07-05T07:17:20.172231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:20.172231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-correcting LLM-controlled Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyi Li, Joseph E. Gonzalez, Long Lian, Trevor Darrell, Tsung-Han Wu","submitted_at":"2023-11-27T18:56:37Z","abstract_excerpt":"Text-to-image generation has witnessed significant progress with the advent of diffusion models. Despite the ability to generate photorealistic images, current text-to-image diffusion models still often struggle to accurately interpret and follow complex input text prompts. In contrast to existing models that aim to generate images only with their best effort, we introduce Self-correcting LLM-controlled Diffusion (SLD). SLD is a framework that generates an image from the input prompt, assesses its alignment with the prompt, and performs self-corrections on the inaccuracies in the generated ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16090","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/2311.16090/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":"2311.16090","created_at":"2026-07-05T07:17:20.172292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16090v1","created_at":"2026-07-05T07:17:20.172292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16090","created_at":"2026-07-05T07:17:20.172292+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSWUOZRDQPOE","created_at":"2026-07-05T07:17:20.172292+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSWUOZRDQPOEIZDT","created_at":"2026-07-05T07:17:20.172292+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSWUOZRD","created_at":"2026-07-05T07:17:20.172292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17749","citing_title":"Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSWUOZRDQPOEIZDTWDIYH2J7NU","json":"https://pith.science/pith/HSWUOZRDQPOEIZDTWDIYH2J7NU.json","graph_json":"https://pith.science/api/pith-number/HSWUOZRDQPOEIZDTWDIYH2J7NU/graph.json","events_json":"https://pith.science/api/pith-number/HSWUOZRDQPOEIZDTWDIYH2J7NU/events.json","paper":"https://pith.science/paper/HSWUOZRD"},"agent_actions":{"view_html":"https://pith.science/pith/HSWUOZRDQPOEIZDTWDIYH2J7NU","download_json":"https://pith.science/pith/HSWUOZRDQPOEIZDTWDIYH2J7NU.json","view_paper":"https://pith.science/paper/HSWUOZRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16090&json=true","fetch_graph":"https://pith.science/api/pith-number/HSWUOZRDQPOEIZDTWDIYH2J7NU/graph.json","fetch_events":"https://pith.science/api/pith-number/HSWUOZRDQPOEIZDTWDIYH2J7NU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSWUOZRDQPOEIZDTWDIYH2J7NU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSWUOZRDQPOEIZDTWDIYH2J7NU/action/storage_attestation","attest_author":"https://pith.science/pith/HSWUOZRDQPOEIZDTWDIYH2J7NU/action/author_attestation","sign_citation":"https://pith.science/pith/HSWUOZRDQPOEIZDTWDIYH2J7NU/action/citation_signature","submit_replication":"https://pith.science/pith/HSWUOZRDQPOEIZDTWDIYH2J7NU/action/replication_record"}},"created_at":"2026-07-05T07:17:20.172292+00:00","updated_at":"2026-07-05T07:17:20.172292+00:00"}