{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JEJMX74Z6FJ56MV55UPKYTTMQ4","short_pith_number":"pith:JEJMX74Z","schema_version":"1.0","canonical_sha256":"4912cbff99f153df32bded1eac4e6c872c34809969d1b0e8bd75b0855cb6c007","source":{"kind":"arxiv","id":"2310.08872","version":5},"attestation_state":"computed","paper":{"title":"R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Henglei Lv, Jiayu Xiao, Liang Li, Qingming Huang, Shuhui Wang","submitted_at":"2023-10-13T05:48:42Z","abstract_excerpt":"Recent text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images given text-prompts as input. However, these models fail to convey appropriate spatial composition specified by a layout instruction. In this work, we probe into zero-shot grounded T2I generation with diffusion models, that is, generating images corresponding to the input layout information without training auxiliary modules or finetuning diffusion models. We propose a Region and Boundary (R&B) aware cross-attention guidance approach that gradually modulates the attention maps of diff"},"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":"2310.08872","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T05:48:42Z","cross_cats_sorted":[],"title_canon_sha256":"a2c45126b980fc72ffe5580a2b766882f498be1ad7ee12272b39704d09825df6","abstract_canon_sha256":"addb4117037dfcb2fe7f994fea1f01df1ce505e9899d311653f7da8982a14c27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:47.415843Z","signature_b64":"zAQPM5TQfLahVY/mXRIi+RM3ByTGwWYCI+lfc5EEaKOAtj7A9TYG1kNEbVOYNFU+ptMsETaSQKbQvpbTVof3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4912cbff99f153df32bded1eac4e6c872c34809969d1b0e8bd75b0855cb6c007","last_reissued_at":"2026-07-05T07:16:47.415378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:47.415378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Henglei Lv, Jiayu Xiao, Liang Li, Qingming Huang, Shuhui Wang","submitted_at":"2023-10-13T05:48:42Z","abstract_excerpt":"Recent text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images given text-prompts as input. However, these models fail to convey appropriate spatial composition specified by a layout instruction. In this work, we probe into zero-shot grounded T2I generation with diffusion models, that is, generating images corresponding to the input layout information without training auxiliary modules or finetuning diffusion models. We propose a Region and Boundary (R&B) aware cross-attention guidance approach that gradually modulates the attention maps of diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08872","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/2310.08872/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":"2310.08872","created_at":"2026-07-05T07:16:47.415435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08872v5","created_at":"2026-07-05T07:16:47.415435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08872","created_at":"2026-07-05T07:16:47.415435+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEJMX74Z6FJ5","created_at":"2026-07-05T07:16:47.415435+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEJMX74Z6FJ56MV5","created_at":"2026-07-05T07:16:47.415435+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEJMX74Z","created_at":"2026-07-05T07:16:47.415435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23178","citing_title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JEJMX74Z6FJ56MV55UPKYTTMQ4","json":"https://pith.science/pith/JEJMX74Z6FJ56MV55UPKYTTMQ4.json","graph_json":"https://pith.science/api/pith-number/JEJMX74Z6FJ56MV55UPKYTTMQ4/graph.json","events_json":"https://pith.science/api/pith-number/JEJMX74Z6FJ56MV55UPKYTTMQ4/events.json","paper":"https://pith.science/paper/JEJMX74Z"},"agent_actions":{"view_html":"https://pith.science/pith/JEJMX74Z6FJ56MV55UPKYTTMQ4","download_json":"https://pith.science/pith/JEJMX74Z6FJ56MV55UPKYTTMQ4.json","view_paper":"https://pith.science/paper/JEJMX74Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08872&json=true","fetch_graph":"https://pith.science/api/pith-number/JEJMX74Z6FJ56MV55UPKYTTMQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/JEJMX74Z6FJ56MV55UPKYTTMQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEJMX74Z6FJ56MV55UPKYTTMQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEJMX74Z6FJ56MV55UPKYTTMQ4/action/storage_attestation","attest_author":"https://pith.science/pith/JEJMX74Z6FJ56MV55UPKYTTMQ4/action/author_attestation","sign_citation":"https://pith.science/pith/JEJMX74Z6FJ56MV55UPKYTTMQ4/action/citation_signature","submit_replication":"https://pith.science/pith/JEJMX74Z6FJ56MV55UPKYTTMQ4/action/replication_record"}},"created_at":"2026-07-05T07:16:47.415435+00:00","updated_at":"2026-07-05T07:16:47.415435+00:00"}