{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LKDHHONDOG5JUIZNHDPVUZ54OB","short_pith_number":"pith:LKDHHOND","schema_version":"1.0","canonical_sha256":"5a8673b9a371ba9a232d38df5a67bc70521c94e28886fa45500c5b240d04c14f","source":{"kind":"arxiv","id":"2311.15773","version":3},"attestation_state":"computed","paper":{"title":"Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Shiwei Zhang, Siteng Huang, Yu Liu, Yutong Feng, Yuyuan Li","submitted_at":"2023-11-27T12:48:33Z","abstract_excerpt":"Diffusion models have recently achieved remarkable progress in generating realistic images. However, challenges remain in accurately understanding and synthesizing the layout requirements in the textual prompts. To align the generated image with layout instructions, we present a training-free layout calibration system SimM that intervenes in the generative process on the fly during inference time. Specifically, following a \"check-locate-rectify\" pipeline, the system first analyses the prompt to generate the target layout and compares it with the intermediate outputs to automatically detect err"},"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":"2311.15773","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T12:48:33Z","cross_cats_sorted":[],"title_canon_sha256":"a50a7b44147a9678e643c7a79c68e304fc098ca199f306e049123e794d6779ac","abstract_canon_sha256":"eb26b42122368f8c06b2e09525ef60b54686e6b25f445fd88ccac74a3faf0518"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:57.863837Z","signature_b64":"eNZ8z4bgKYsPXB7JEdNzAQM9SOWPcVeDJVc90aVZXe4s+SLM1GFhT9A0Dh253teXKEo/WiIbYBi39pHyHj0tCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a8673b9a371ba9a232d38df5a67bc70521c94e28886fa45500c5b240d04c14f","last_reissued_at":"2026-07-05T07:59:57.863345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:57.863345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Shiwei Zhang, Siteng Huang, Yu Liu, Yutong Feng, Yuyuan Li","submitted_at":"2023-11-27T12:48:33Z","abstract_excerpt":"Diffusion models have recently achieved remarkable progress in generating realistic images. However, challenges remain in accurately understanding and synthesizing the layout requirements in the textual prompts. To align the generated image with layout instructions, we present a training-free layout calibration system SimM that intervenes in the generative process on the fly during inference time. Specifically, following a \"check-locate-rectify\" pipeline, the system first analyses the prompt to generate the target layout and compares it with the intermediate outputs to automatically detect err"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15773","kind":"arxiv","version":3},"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/2311.15773/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":"2311.15773","created_at":"2026-07-05T07:59:57.863406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15773v3","created_at":"2026-07-05T07:59:57.863406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15773","created_at":"2026-07-05T07:59:57.863406+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKDHHONDOG5J","created_at":"2026-07-05T07:59:57.863406+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKDHHONDOG5JUIZN","created_at":"2026-07-05T07:59:57.863406+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKDHHOND","created_at":"2026-07-05T07:59:57.863406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11594","citing_title":"VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LKDHHONDOG5JUIZNHDPVUZ54OB","json":"https://pith.science/pith/LKDHHONDOG5JUIZNHDPVUZ54OB.json","graph_json":"https://pith.science/api/pith-number/LKDHHONDOG5JUIZNHDPVUZ54OB/graph.json","events_json":"https://pith.science/api/pith-number/LKDHHONDOG5JUIZNHDPVUZ54OB/events.json","paper":"https://pith.science/paper/LKDHHOND"},"agent_actions":{"view_html":"https://pith.science/pith/LKDHHONDOG5JUIZNHDPVUZ54OB","download_json":"https://pith.science/pith/LKDHHONDOG5JUIZNHDPVUZ54OB.json","view_paper":"https://pith.science/paper/LKDHHOND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15773&json=true","fetch_graph":"https://pith.science/api/pith-number/LKDHHONDOG5JUIZNHDPVUZ54OB/graph.json","fetch_events":"https://pith.science/api/pith-number/LKDHHONDOG5JUIZNHDPVUZ54OB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKDHHONDOG5JUIZNHDPVUZ54OB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKDHHONDOG5JUIZNHDPVUZ54OB/action/storage_attestation","attest_author":"https://pith.science/pith/LKDHHONDOG5JUIZNHDPVUZ54OB/action/author_attestation","sign_citation":"https://pith.science/pith/LKDHHONDOG5JUIZNHDPVUZ54OB/action/citation_signature","submit_replication":"https://pith.science/pith/LKDHHONDOG5JUIZNHDPVUZ54OB/action/replication_record"}},"created_at":"2026-07-05T07:59:57.863406+00:00","updated_at":"2026-07-05T07:59:57.863406+00:00"}