{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TEVYQWQJ53JF3H7AJHP2OJNTFF","short_pith_number":"pith:TEVYQWQJ","canonical_record":{"source":{"id":"2306.05427","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"bb7662df6060656420654af1167eca65ee4ee3aa46360e9c96fad9097e0d0400","abstract_canon_sha256":"fe75571e412483a143e16f63b2487759c46d75ac18d0d003680a3d6526354f4d"},"schema_version":"1.0"},"canonical_sha256":"992b885a09eed25d9fe049dfa725b329593a441d61e4065a1f98bbb967971a4d","source":{"kind":"arxiv","id":"2306.05427","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05427","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05427v2","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05427","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"TEVYQWQJ53JF","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"TEVYQWQJ53JF3H7A","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"TEVYQWQJ","created_at":"2026-07-05T07:20:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TEVYQWQJ53JF3H7AJHP2OJNTFF","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05427","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"bb7662df6060656420654af1167eca65ee4ee3aa46360e9c96fad9097e0d0400","abstract_canon_sha256":"fe75571e412483a143e16f63b2487759c46d75ac18d0d003680a3d6526354f4d"},"schema_version":"1.0"},"canonical_sha256":"992b885a09eed25d9fe049dfa725b329593a441d61e4065a1f98bbb967971a4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:08.933083Z","signature_b64":"wSVtt+aCw1KxlbB3XRu3U5aOpiYcCEdMQ3oESZNlMZyxL/mcOJW7YKO+SQPDSmRgMAnaJ8ai5tWwENBYyfPcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"992b885a09eed25d9fe049dfa725b329593a441d61e4065a1f98bbb967971a4d","last_reissued_at":"2026-07-05T07:20:08.932558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:08.932558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05427","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":"2026-07-05T07:20:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I0IrXOr7Ac3ExiNEHJhN2kcE2Z6Zx9cpBIqyWGSP1ed5yftr31CdrqNqA8+fItQmQ/XaMie1Jn2iWPcw9cVBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:59:52.822612Z"},"content_sha256":"174c71fdad3d66c442367e88128091b4da368d7d0ffaf2e284c816fbe881a0bb","schema_version":"1.0","event_id":"sha256:174c71fdad3d66c442367e88128091b4da368d7d0ffaf2e284c816fbe881a0bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TEVYQWQJ53JF3H7AJHP2OJNTFF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounded Text-to-Image Synthesis with Attention Refocusing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia-Bin Huang, Quynh Phung, Songwei Ge","submitted_at":"2023-06-08T17:59:59Z","abstract_excerpt":"Driven by the scalable diffusion models trained on large-scale datasets, text-to-image synthesis methods have shown compelling results. However, these models still fail to precisely follow the text prompt involving multiple objects, attributes, or spatial compositions. In this paper, we reveal the potential causes in the diffusion model's cross-attention and self-attention layers. We propose two novel losses to refocus attention maps according to a given spatial layout during sampling. Creating the layouts manually requires additional effort and can be tedious. Therefore, we explore using larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05427","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/2306.05427/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":"2026-07-05T07:20:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QP90g4X+6ZEAO+sODsSVyrlfT3UzcQBIgNWpd+STDT6cqBat/0Da9StnB+Wlo7sdnQe/cgaK7CzGi3cwkrVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:59:52.823551Z"},"content_sha256":"342fbf7d431b6229d03e79b2a4bc9bdca6eba6bbd6c8653c8d91551e59b7ec97","schema_version":"1.0","event_id":"sha256:342fbf7d431b6229d03e79b2a4bc9bdca6eba6bbd6c8653c8d91551e59b7ec97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TEVYQWQJ53JF3H7AJHP2OJNTFF/bundle.json","state_url":"https://pith.science/pith/TEVYQWQJ53JF3H7AJHP2OJNTFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TEVYQWQJ53JF3H7AJHP2OJNTFF/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":"2026-08-10T00:59:52Z","links":{"resolver":"https://pith.science/pith/TEVYQWQJ53JF3H7AJHP2OJNTFF","bundle":"https://pith.science/pith/TEVYQWQJ53JF3H7AJHP2OJNTFF/bundle.json","state":"https://pith.science/pith/TEVYQWQJ53JF3H7AJHP2OJNTFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TEVYQWQJ53JF3H7AJHP2OJNTFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TEVYQWQJ53JF3H7AJHP2OJNTFF","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":"fe75571e412483a143e16f63b2487759c46d75ac18d0d003680a3d6526354f4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:59Z","title_canon_sha256":"bb7662df6060656420654af1167eca65ee4ee3aa46360e9c96fad9097e0d0400"},"schema_version":"1.0","source":{"id":"2306.05427","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05427","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05427v2","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05427","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"TEVYQWQJ53JF","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"TEVYQWQJ53JF3H7A","created_at":"2026-07-05T07:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"TEVYQWQJ","created_at":"2026-07-05T07:20:08Z"}],"graph_snapshots":[{"event_id":"sha256:342fbf7d431b6229d03e79b2a4bc9bdca6eba6bbd6c8653c8d91551e59b7ec97","target":"graph","created_at":"2026-07-05T07:20:08Z","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/2306.05427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Driven by the scalable diffusion models trained on large-scale datasets, text-to-image synthesis methods have shown compelling results. However, these models still fail to precisely follow the text prompt involving multiple objects, attributes, or spatial compositions. In this paper, we reveal the potential causes in the diffusion model's cross-attention and self-attention layers. We propose two novel losses to refocus attention maps according to a given spatial layout during sampling. Creating the layouts manually requires additional effort and can be tedious. Therefore, we explore using larg","authors_text":"Jia-Bin Huang, Quynh Phung, Songwei Ge","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:59Z","title":"Grounded Text-to-Image Synthesis with Attention Refocusing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05427","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":"sha256:174c71fdad3d66c442367e88128091b4da368d7d0ffaf2e284c816fbe881a0bb","target":"record","created_at":"2026-07-05T07:20:08Z","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":"fe75571e412483a143e16f63b2487759c46d75ac18d0d003680a3d6526354f4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:59Z","title_canon_sha256":"bb7662df6060656420654af1167eca65ee4ee3aa46360e9c96fad9097e0d0400"},"schema_version":"1.0","source":{"id":"2306.05427","kind":"arxiv","version":2}},"canonical_sha256":"992b885a09eed25d9fe049dfa725b329593a441d61e4065a1f98bbb967971a4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"992b885a09eed25d9fe049dfa725b329593a441d61e4065a1f98bbb967971a4d","first_computed_at":"2026-07-05T07:20:08.932558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:08.932558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wSVtt+aCw1KxlbB3XRu3U5aOpiYcCEdMQ3oESZNlMZyxL/mcOJW7YKO+SQPDSmRgMAnaJ8ai5tWwENBYyfPcCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:08.933083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05427","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:174c71fdad3d66c442367e88128091b4da368d7d0ffaf2e284c816fbe881a0bb","sha256:342fbf7d431b6229d03e79b2a4bc9bdca6eba6bbd6c8653c8d91551e59b7ec97"],"state_sha256":"c25388c0b258f82ac93c5404688b7312fc49c3b2f132e2ceabe809674d533634"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ADNsLvX+Hkt1Da2BRzpBgsngl8zI0HCzNeaiI1YvfnznSSGyxGipdVgm/vvhFoSbY9Ws5MvVhjU3csvvc1sVDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:59:52.831030Z","bundle_sha256":"0a5a31f43af19b04f626120bc1caaeb06e0a22bf7138e2ca00610c85a7b84243"}}