{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JEJMX74Z6FJ56MV55UPKYTTMQ4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"addb4117037dfcb2fe7f994fea1f01df1ce505e9899d311653f7da8982a14c27","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T05:48:42Z","title_canon_sha256":"a2c45126b980fc72ffe5580a2b766882f498be1ad7ee12272b39704d09825df6"},"schema_version":"1.0","source":{"id":"2310.08872","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08872","created_at":"2026-07-05T07:16:47Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08872v5","created_at":"2026-07-05T07:16:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08872","created_at":"2026-07-05T07:16:47Z"},{"alias_kind":"pith_short_12","alias_value":"JEJMX74Z6FJ5","created_at":"2026-07-05T07:16:47Z"},{"alias_kind":"pith_short_16","alias_value":"JEJMX74Z6FJ56MV5","created_at":"2026-07-05T07:16:47Z"},{"alias_kind":"pith_short_8","alias_value":"JEJMX74Z","created_at":"2026-07-05T07:16:47Z"}],"graph_snapshots":[{"event_id":"sha256:e52794046b431af3e93be861868e7a2454b07d0f470290c4073c8817052cf276","target":"graph","created_at":"2026-07-05T07:16:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.08872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Henglei Lv, Jiayu Xiao, Liang Li, Qingming Huang, Shuhui Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T05:48:42Z","title":"R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08872","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dd77942f2140afc9899c7bea4d50c556c90181b744f074b11fb064d92de94d77","target":"record","created_at":"2026-07-05T07:16:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"addb4117037dfcb2fe7f994fea1f01df1ce505e9899d311653f7da8982a14c27","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T05:48:42Z","title_canon_sha256":"a2c45126b980fc72ffe5580a2b766882f498be1ad7ee12272b39704d09825df6"},"schema_version":"1.0","source":{"id":"2310.08872","kind":"arxiv","version":5}},"canonical_sha256":"4912cbff99f153df32bded1eac4e6c872c34809969d1b0e8bd75b0855cb6c007","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4912cbff99f153df32bded1eac4e6c872c34809969d1b0e8bd75b0855cb6c007","first_computed_at":"2026-07-05T07:16:47.415378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:47.415378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zAQPM5TQfLahVY/mXRIi+RM3ByTGwWYCI+lfc5EEaKOAtj7A9TYG1kNEbVOYNFU+ptMsETaSQKbQvpbTVof3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:47.415843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08872","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd77942f2140afc9899c7bea4d50c556c90181b744f074b11fb064d92de94d77","sha256:e52794046b431af3e93be861868e7a2454b07d0f470290c4073c8817052cf276"],"state_sha256":"1866caf13482c57c5bb8ae5f067e64e63df927c6adfc9ef2e993658e93835d60"}