{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZFGY5NUXUDBJA444RCL7DTTBRS","short_pith_number":"pith:ZFGY5NUX","schema_version":"1.0","canonical_sha256":"c94d8eb697a0c290739c8897f1ce618cae9e33faafc8af8cbb9419c528ea0590","source":{"kind":"arxiv","id":"2308.10156","version":2},"attestation_state":"computed","paper":{"title":"SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-form Layout-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengyou Jia, Guang Dai, Jingdong Wang, Mengmeng Wang, Minnan Luo, Xiaojun Chang, Zhuohang Dang","submitted_at":"2023-08-20T04:09:12Z","abstract_excerpt":"Despite significant progress in Text-to-Image (T2I) generative models, even lengthy and complex text descriptions still struggle to convey detailed controls. In contrast, Layout-to-Image (L2I) generation, aiming to generate realistic and complex scene images from user-specified layouts, has risen to prominence. However, existing methods transform layout information into tokens or RGB images for conditional control in the generative process, leading to insufficient spatial and semantic controllability of individual instances. To address these limitations, we propose a novel Spatial-Semantic Map"},"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":"2308.10156","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T04:09:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dfea727c1c3c26f91d14f3b131f07751935b2468c734605568751958be94e08e","abstract_canon_sha256":"24e82f732f49aae9ef3bbed9a25a18fda232c13ed9222ad8ac46cb3918b3b959"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:23.781169Z","signature_b64":"Djb+qedLaAorKl0KJcxtkZpDsBFsuN/5IEItNRWR93t4IEokQgu6BfVp4x9ePDMg7iAb1l8gIcl98lO880FxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c94d8eb697a0c290739c8897f1ce618cae9e33faafc8af8cbb9419c528ea0590","last_reissued_at":"2026-07-05T07:55:23.780620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:23.780620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-form Layout-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengyou Jia, Guang Dai, Jingdong Wang, Mengmeng Wang, Minnan Luo, Xiaojun Chang, Zhuohang Dang","submitted_at":"2023-08-20T04:09:12Z","abstract_excerpt":"Despite significant progress in Text-to-Image (T2I) generative models, even lengthy and complex text descriptions still struggle to convey detailed controls. In contrast, Layout-to-Image (L2I) generation, aiming to generate realistic and complex scene images from user-specified layouts, has risen to prominence. However, existing methods transform layout information into tokens or RGB images for conditional control in the generative process, leading to insufficient spatial and semantic controllability of individual instances. To address these limitations, we propose a novel Spatial-Semantic Map"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10156","kind":"arxiv","version":2},"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/2308.10156/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":"2308.10156","created_at":"2026-07-05T07:55:23.780685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10156v2","created_at":"2026-07-05T07:55:23.780685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10156","created_at":"2026-07-05T07:55:23.780685+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFGY5NUXUDBJ","created_at":"2026-07-05T07:55:23.780685+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFGY5NUXUDBJA444","created_at":"2026-07-05T07:55:23.780685+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFGY5NUX","created_at":"2026-07-05T07:55:23.780685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05501","citing_title":"Preliminary Explorations with GPT-4o(mni) Native Image Generation","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFGY5NUXUDBJA444RCL7DTTBRS","json":"https://pith.science/pith/ZFGY5NUXUDBJA444RCL7DTTBRS.json","graph_json":"https://pith.science/api/pith-number/ZFGY5NUXUDBJA444RCL7DTTBRS/graph.json","events_json":"https://pith.science/api/pith-number/ZFGY5NUXUDBJA444RCL7DTTBRS/events.json","paper":"https://pith.science/paper/ZFGY5NUX"},"agent_actions":{"view_html":"https://pith.science/pith/ZFGY5NUXUDBJA444RCL7DTTBRS","download_json":"https://pith.science/pith/ZFGY5NUXUDBJA444RCL7DTTBRS.json","view_paper":"https://pith.science/paper/ZFGY5NUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10156&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFGY5NUXUDBJA444RCL7DTTBRS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFGY5NUXUDBJA444RCL7DTTBRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFGY5NUXUDBJA444RCL7DTTBRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFGY5NUXUDBJA444RCL7DTTBRS/action/storage_attestation","attest_author":"https://pith.science/pith/ZFGY5NUXUDBJA444RCL7DTTBRS/action/author_attestation","sign_citation":"https://pith.science/pith/ZFGY5NUXUDBJA444RCL7DTTBRS/action/citation_signature","submit_replication":"https://pith.science/pith/ZFGY5NUXUDBJA444RCL7DTTBRS/action/replication_record"}},"created_at":"2026-07-05T07:55:23.780685+00:00","updated_at":"2026-07-05T07:55:23.780685+00:00"}