{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SQRILUWVPLADHB3CHS7FOZLC7F","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":"52e42a4e4208203e6cfbe4f4309aef8b020df162cd8aa4332fed19c7358597b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T15:53:37Z","title_canon_sha256":"286b201ac3a9b827d7e50df08feb5cda4f1e1a64a1728e0b53cae4813a072bfb"},"schema_version":"1.0","source":{"id":"2309.04399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04399","created_at":"2026-07-05T06:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04399v1","created_at":"2026-07-05T06:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04399","created_at":"2026-07-05T06:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"SQRILUWVPLAD","created_at":"2026-07-05T06:48:59Z"},{"alias_kind":"pith_short_16","alias_value":"SQRILUWVPLADHB3C","created_at":"2026-07-05T06:48:59Z"},{"alias_kind":"pith_short_8","alias_value":"SQRILUWV","created_at":"2026-07-05T06:48:59Z"}],"graph_snapshots":[{"event_id":"sha256:2c870d9c47a9ff628b04413f8522c67812f31b5cec2c2de44bb4c601916bdcda","target":"graph","created_at":"2026-07-05T06:48:59Z","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/2309.04399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in diffusion models have showcased their impressive capacity to generate visually striking images. Nevertheless, ensuring a close match between the generated image and the given prompt remains a persistent challenge. In this work, we identify that a crucial factor leading to the text-image mismatch issue is the inadequate cross-modality relation learning between the prompt and the output image. To better align the prompt and image content, we advance the cross-attention with an adaptive mask, which is conditioned on the attention maps and the prompt embeddings, to dynamical","authors_text":"Daquan Zhou, Jiashi Feng, Qibin Hou, Yaxing Wang, Yupeng Zhou, Zuo-Liang Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T15:53:37Z","title":"MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04399","kind":"arxiv","version":1},"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":"sha256:8eba87bcced9c091c1ea63fc96ef1166172f8df27e56a650e2ee45909a2872bc","target":"record","created_at":"2026-07-05T06:48:59Z","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":"52e42a4e4208203e6cfbe4f4309aef8b020df162cd8aa4332fed19c7358597b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T15:53:37Z","title_canon_sha256":"286b201ac3a9b827d7e50df08feb5cda4f1e1a64a1728e0b53cae4813a072bfb"},"schema_version":"1.0","source":{"id":"2309.04399","kind":"arxiv","version":1}},"canonical_sha256":"942285d2d57ac03387623cbe576562f97f50f824847445d7f8a20a38dfcf29f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"942285d2d57ac03387623cbe576562f97f50f824847445d7f8a20a38dfcf29f5","first_computed_at":"2026-07-05T06:48:59.099732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:59.099732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BjqtIb2jGJYk3fs/DO5mflbTh+WQpGYa3QB+5TfqUYPPqdfCJVRXKo9MEDlSJ1+Re35Z27eeev3zMsihhS5GAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:59.100139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8eba87bcced9c091c1ea63fc96ef1166172f8df27e56a650e2ee45909a2872bc","sha256:2c870d9c47a9ff628b04413f8522c67812f31b5cec2c2de44bb4c601916bdcda"],"state_sha256":"ecaf2b8f82fbc41ae2d2860c6248cd1ce93744c426d7af9961270fb2393050e2"}