{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PZEOTEAIJD6YQHUQJ4H5LQGGS3","short_pith_number":"pith:PZEOTEAI","canonical_record":{"source":{"id":"2305.13921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T10:49:22Z","cross_cats_sorted":[],"title_canon_sha256":"22d1855cf9bae05c7911ad9f9ca5f5fc803131602ea975c755e24a955658d52c","abstract_canon_sha256":"bd9d15d4ab5998bcc66817f98540ecc0b9e61c988d5c2c579a98c3fe148ab9d6"},"schema_version":"1.0"},"canonical_sha256":"7e48e9900848fd881e904f0fd5c0c696cc1820e7df1790fd8378def6d631c7b0","source":{"kind":"arxiv","id":"2305.13921","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13921","created_at":"2026-07-05T07:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13921v2","created_at":"2026-07-05T07:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13921","created_at":"2026-07-05T07:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"PZEOTEAIJD6Y","created_at":"2026-07-05T07:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"PZEOTEAIJD6YQHUQ","created_at":"2026-07-05T07:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"PZEOTEAI","created_at":"2026-07-05T07:23:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PZEOTEAIJD6YQHUQJ4H5LQGGS3","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T10:49:22Z","cross_cats_sorted":[],"title_canon_sha256":"22d1855cf9bae05c7911ad9f9ca5f5fc803131602ea975c755e24a955658d52c","abstract_canon_sha256":"bd9d15d4ab5998bcc66817f98540ecc0b9e61c988d5c2c579a98c3fe148ab9d6"},"schema_version":"1.0"},"canonical_sha256":"7e48e9900848fd881e904f0fd5c0c696cc1820e7df1790fd8378def6d631c7b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:57.937066Z","signature_b64":"rXc/B5FepnL75d4gTz3L+WS4nbZOildxLteSDt3+JCzsmhYOZpxHvlho7hLToXOg8kOmjO0HN4PQuxr8pHz2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e48e9900848fd881e904f0fd5c0c696cc1820e7df1790fd8378def6d631c7b0","last_reissued_at":"2026-07-05T07:23:57.936560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:57.936560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13921","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":"2026-07-05T07:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kqSSWjdu3FCOEZ3LHbnZVeASfcE8oL0zmWCw8QnQFPy363bnyhpl7grB5ZklhuQARW5YjQNeed6TrRtGigrRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:47:21.434596Z"},"content_sha256":"88f6ac3c8176f31858834cbb6948730abc216c565f9deaee883ebaea88dc94b3","schema_version":"1.0","event_id":"sha256:88f6ac3c8176f31858834cbb6948730abc216c565f9deaee883ebaea88dc94b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PZEOTEAIJD6YQHUQJ4H5LQGGS3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Haonan Lu, Jian Ma, Ruichen Wang, Xiaodong Lin, Zekang Chen","submitted_at":"2023-05-23T10:49:22Z","abstract_excerpt":"Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited compositional capabilities, leading to attribute leakage, entity leakage, and missing entities. In this paper, we propose a novel attention mask control strategy based on predicted object boxes to address these issues. In particular, we first train a BoxNet to predict a box for each entity that possesses the attribute specified in the prompt. Then, depending "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13921","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/2305.13921/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":"2026-07-05T07:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ePOc7s7hF1plLGVHGp/IBWpEUaEBuC9pGlNomiIZDkicDNwHPPO1H0mGzYN0aCjCJSnTLSOrSKYnzkQr7xRMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:47:21.435133Z"},"content_sha256":"112b5ddd0d4e42cb742e6b10532e4bae5e3f1fc69636b1956ea5bfe0326ea758","schema_version":"1.0","event_id":"sha256:112b5ddd0d4e42cb742e6b10532e4bae5e3f1fc69636b1956ea5bfe0326ea758"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZEOTEAIJD6YQHUQJ4H5LQGGS3/bundle.json","state_url":"https://pith.science/pith/PZEOTEAIJD6YQHUQJ4H5LQGGS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZEOTEAIJD6YQHUQJ4H5LQGGS3/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":"2026-08-15T03:47:21Z","links":{"resolver":"https://pith.science/pith/PZEOTEAIJD6YQHUQJ4H5LQGGS3","bundle":"https://pith.science/pith/PZEOTEAIJD6YQHUQJ4H5LQGGS3/bundle.json","state":"https://pith.science/pith/PZEOTEAIJD6YQHUQJ4H5LQGGS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZEOTEAIJD6YQHUQJ4H5LQGGS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PZEOTEAIJD6YQHUQJ4H5LQGGS3","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":"bd9d15d4ab5998bcc66817f98540ecc0b9e61c988d5c2c579a98c3fe148ab9d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T10:49:22Z","title_canon_sha256":"22d1855cf9bae05c7911ad9f9ca5f5fc803131602ea975c755e24a955658d52c"},"schema_version":"1.0","source":{"id":"2305.13921","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13921","created_at":"2026-07-05T07:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13921v2","created_at":"2026-07-05T07:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13921","created_at":"2026-07-05T07:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"PZEOTEAIJD6Y","created_at":"2026-07-05T07:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"PZEOTEAIJD6YQHUQ","created_at":"2026-07-05T07:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"PZEOTEAI","created_at":"2026-07-05T07:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:112b5ddd0d4e42cb742e6b10532e4bae5e3f1fc69636b1956ea5bfe0326ea758","target":"graph","created_at":"2026-07-05T07:23:57Z","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/2305.13921/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 show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited compositional capabilities, leading to attribute leakage, entity leakage, and missing entities. In this paper, we propose a novel attention mask control strategy based on predicted object boxes to address these issues. In particular, we first train a BoxNet to predict a box for each entity that possesses the attribute specified in the prompt. Then, depending ","authors_text":"Chen Chen, Haonan Lu, Jian Ma, Ruichen Wang, Xiaodong Lin, Zekang Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T10:49:22Z","title":"Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13921","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":"sha256:88f6ac3c8176f31858834cbb6948730abc216c565f9deaee883ebaea88dc94b3","target":"record","created_at":"2026-07-05T07:23:57Z","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":"bd9d15d4ab5998bcc66817f98540ecc0b9e61c988d5c2c579a98c3fe148ab9d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T10:49:22Z","title_canon_sha256":"22d1855cf9bae05c7911ad9f9ca5f5fc803131602ea975c755e24a955658d52c"},"schema_version":"1.0","source":{"id":"2305.13921","kind":"arxiv","version":2}},"canonical_sha256":"7e48e9900848fd881e904f0fd5c0c696cc1820e7df1790fd8378def6d631c7b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e48e9900848fd881e904f0fd5c0c696cc1820e7df1790fd8378def6d631c7b0","first_computed_at":"2026-07-05T07:23:57.936560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:57.936560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rXc/B5FepnL75d4gTz3L+WS4nbZOildxLteSDt3+JCzsmhYOZpxHvlho7hLToXOg8kOmjO0HN4PQuxr8pHz2AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:57.937066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13921","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88f6ac3c8176f31858834cbb6948730abc216c565f9deaee883ebaea88dc94b3","sha256:112b5ddd0d4e42cb742e6b10532e4bae5e3f1fc69636b1956ea5bfe0326ea758"],"state_sha256":"107f12b0a665ef2bc7fe1e77c55e1c622ab2f53f789a81456dc7f06f9f32dc2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mit5GLxJ1BeMfIWOiuBdqRw2+KZ7OyKvTIFyzN/lWgTJkiGONdYuBmRCBDc8MaY6eMIywnIvEI4reslDUHJaCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T03:47:21.440176Z","bundle_sha256":"1a55fb91e3d2230a4fc6e03eb9c25e015c8a98e54e94a8f744bdcf144030a155"}}