{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Z6SFWLQJRZECJGTPU6BV63IW32","short_pith_number":"pith:Z6SFWLQJ","canonical_record":{"source":{"id":"2304.03373","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T21:00:00Z","cross_cats_sorted":[],"title_canon_sha256":"957692b737bbebec64d2e8ec853acf382747aeac3550164da74c47119d4467fe","abstract_canon_sha256":"b516154ffa9c6512946a5a9853524f195e02f689c29e8798fcc8ac409bde201d"},"schema_version":"1.0"},"canonical_sha256":"cfa45b2e098e48249a6fa7835f6d16debe697d36457166c90f9d3bbe3d4461b9","source":{"kind":"arxiv","id":"2304.03373","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03373","created_at":"2026-07-05T07:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03373v2","created_at":"2026-07-05T07:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03373","created_at":"2026-07-05T07:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z6SFWLQJRZEC","created_at":"2026-07-05T07:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"Z6SFWLQJRZECJGTP","created_at":"2026-07-05T07:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"Z6SFWLQJ","created_at":"2026-07-05T07:18:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Z6SFWLQJRZECJGTPU6BV63IW32","target":"record","payload":{"canonical_record":{"source":{"id":"2304.03373","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T21:00:00Z","cross_cats_sorted":[],"title_canon_sha256":"957692b737bbebec64d2e8ec853acf382747aeac3550164da74c47119d4467fe","abstract_canon_sha256":"b516154ffa9c6512946a5a9853524f195e02f689c29e8798fcc8ac409bde201d"},"schema_version":"1.0"},"canonical_sha256":"cfa45b2e098e48249a6fa7835f6d16debe697d36457166c90f9d3bbe3d4461b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:09.749655Z","signature_b64":"/b60laupZd2BJ7aj4Zu2WWCtFbJNc2g4UHNOX4te2VzQe1TPxajjEKweEzQDpFWNsR8B2XiBRf+uyg9e8Ol6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfa45b2e098e48249a6fa7835f6d16debe697d36457166c90f9d3bbe3d4461b9","last_reissued_at":"2026-07-05T07:18:09.749155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:09.749155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.03373","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:18:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZEKGkdjKjhdHM1j/ybvz6mtk1UJUQWQcG4JpcgR8CeBljXSKdZw6nxx25/isSQNaci9hH6roQYKA0zHbVyVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:09:02.408426Z"},"content_sha256":"badbbcc96cb46cdfd8bcea801659dfec0cb391c874263b79471a8ec80d68d54f","schema_version":"1.0","event_id":"sha256:badbbcc96cb46cdfd8bcea801659dfec0cb391c874263b79471a8ec80d68d54f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Z6SFWLQJRZECJGTPU6BV63IW32","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training-Free Layout Control with Cross-Attention Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Iro Laina, Minghao Chen","submitted_at":"2023-04-06T21:00:00Z","abstract_excerpt":"Recent diffusion-based generators can produce high-quality images from textual prompts. However, they often disregard textual instructions that specify the spatial layout of the composition. We propose a simple approach that achieves robust layout control without the need for training or fine-tuning of the image generator. Our technique manipulates the cross-attention layers that the model uses to interface textual and visual information and steers the generation in the desired direction given, e.g., a user-specified layout. To determine how to best guide attention, we study the role of attent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03373","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/2304.03373/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:18:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EZXkQ/9kCnwipAhj3ojuxj7qWRbslCCXIbQy03kfoTSms5er7j255Vzie/ZlVZk3CX5h4mPKgX2zWmSZV5+sAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:09:02.409228Z"},"content_sha256":"3b63be500cde981fc854e3212b8695f48bbeaa325a18b9da451da74e63d9722a","schema_version":"1.0","event_id":"sha256:3b63be500cde981fc854e3212b8695f48bbeaa325a18b9da451da74e63d9722a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z6SFWLQJRZECJGTPU6BV63IW32/bundle.json","state_url":"https://pith.science/pith/Z6SFWLQJRZECJGTPU6BV63IW32/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z6SFWLQJRZECJGTPU6BV63IW32/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T05:09:02Z","links":{"resolver":"https://pith.science/pith/Z6SFWLQJRZECJGTPU6BV63IW32","bundle":"https://pith.science/pith/Z6SFWLQJRZECJGTPU6BV63IW32/bundle.json","state":"https://pith.science/pith/Z6SFWLQJRZECJGTPU6BV63IW32/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z6SFWLQJRZECJGTPU6BV63IW32/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z6SFWLQJRZECJGTPU6BV63IW32","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":"b516154ffa9c6512946a5a9853524f195e02f689c29e8798fcc8ac409bde201d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T21:00:00Z","title_canon_sha256":"957692b737bbebec64d2e8ec853acf382747aeac3550164da74c47119d4467fe"},"schema_version":"1.0","source":{"id":"2304.03373","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03373","created_at":"2026-07-05T07:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03373v2","created_at":"2026-07-05T07:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03373","created_at":"2026-07-05T07:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z6SFWLQJRZEC","created_at":"2026-07-05T07:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"Z6SFWLQJRZECJGTP","created_at":"2026-07-05T07:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"Z6SFWLQJ","created_at":"2026-07-05T07:18:09Z"}],"graph_snapshots":[{"event_id":"sha256:3b63be500cde981fc854e3212b8695f48bbeaa325a18b9da451da74e63d9722a","target":"graph","created_at":"2026-07-05T07:18:09Z","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/2304.03373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent diffusion-based generators can produce high-quality images from textual prompts. However, they often disregard textual instructions that specify the spatial layout of the composition. We propose a simple approach that achieves robust layout control without the need for training or fine-tuning of the image generator. Our technique manipulates the cross-attention layers that the model uses to interface textual and visual information and steers the generation in the desired direction given, e.g., a user-specified layout. To determine how to best guide attention, we study the role of attent","authors_text":"Andrea Vedaldi, Iro Laina, Minghao Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T21:00:00Z","title":"Training-Free Layout Control with Cross-Attention Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03373","kind":"arxiv","version":2},"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:badbbcc96cb46cdfd8bcea801659dfec0cb391c874263b79471a8ec80d68d54f","target":"record","created_at":"2026-07-05T07:18:09Z","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":"b516154ffa9c6512946a5a9853524f195e02f689c29e8798fcc8ac409bde201d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T21:00:00Z","title_canon_sha256":"957692b737bbebec64d2e8ec853acf382747aeac3550164da74c47119d4467fe"},"schema_version":"1.0","source":{"id":"2304.03373","kind":"arxiv","version":2}},"canonical_sha256":"cfa45b2e098e48249a6fa7835f6d16debe697d36457166c90f9d3bbe3d4461b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfa45b2e098e48249a6fa7835f6d16debe697d36457166c90f9d3bbe3d4461b9","first_computed_at":"2026-07-05T07:18:09.749155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:09.749155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/b60laupZd2BJ7aj4Zu2WWCtFbJNc2g4UHNOX4te2VzQe1TPxajjEKweEzQDpFWNsR8B2XiBRf+uyg9e8Ol6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:09.749655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03373","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:badbbcc96cb46cdfd8bcea801659dfec0cb391c874263b79471a8ec80d68d54f","sha256:3b63be500cde981fc854e3212b8695f48bbeaa325a18b9da451da74e63d9722a"],"state_sha256":"f1d245346043d69b38fd4e60b3bc5d280e5456bcbf1d43735c0c02b57b6415bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"84fcCoiBj1iOSKwenbRf/jxB8KeBeCWu+VwDNrI6RqKVC+E23tAV6GmiUzQ/xa22XdqW+QUwY/suI9srmfI3Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:09:02.414311Z","bundle_sha256":"cbaa689e716abc3148c404ee731503a1a5990729e69c57e44c53c913d93cd1f1"}}