{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VBIXLMB5QL2BDBWL2KVKGGIH7J","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":"7cb24467d91876d6e055c1c61cf139402d671335f648eaa259faef4a20a64a64","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-22T07:03:57Z","title_canon_sha256":"c9dd44aa073653990c2f63e41999fa0390d0c3e8a6fc1bf7b41941ffb79de154"},"schema_version":"1.0","source":{"id":"2503.17675","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17675","created_at":"2026-07-05T10:37:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17675v1","created_at":"2026-07-05T10:37:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17675","created_at":"2026-07-05T10:37:51Z"},{"alias_kind":"pith_short_12","alias_value":"VBIXLMB5QL2B","created_at":"2026-07-05T10:37:51Z"},{"alias_kind":"pith_short_16","alias_value":"VBIXLMB5QL2BDBWL","created_at":"2026-07-05T10:37:51Z"},{"alias_kind":"pith_short_8","alias_value":"VBIXLMB5","created_at":"2026-07-05T10:37:51Z"}],"graph_snapshots":[{"event_id":"sha256:52c6b3fabd8702c969a022f50ee562a27b4d5bba0e21b356c29768d0cfcde069","target":"graph","created_at":"2026-07-05T10:37:51Z","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/2503.17675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex text prompts or multi-concept attribute binding challenges. Previous U-Net-based methods primarily optimized the latent space, but their direct application to Transformer-based architectures has shown limited effectiveness. Our method addresses these challenges by directly optimizing cross-attention maps during the generation process. Specifically, we introduc","authors_text":"Hai Huang, Hanting Wang, Jiacheng Sun, Jieming Zhu, Jingyuan Chen, Shulei Wang, Sihang Cai, Tao Jin, Wang Lin, Wenkang Han, Zhou Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-22T07:03:57Z","title":"Towards Transformer-Based Aligned Generation with Self-Coherence Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17675","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":"sha256:327611823332812ed5ecb5de69bd9168e2397a99ab079822ae9213950658f7ba","target":"record","created_at":"2026-07-05T10:37:51Z","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":"7cb24467d91876d6e055c1c61cf139402d671335f648eaa259faef4a20a64a64","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-22T07:03:57Z","title_canon_sha256":"c9dd44aa073653990c2f63e41999fa0390d0c3e8a6fc1bf7b41941ffb79de154"},"schema_version":"1.0","source":{"id":"2503.17675","kind":"arxiv","version":1}},"canonical_sha256":"a85175b03d82f41186cbd2aaa31907fa631016d9fc8f73f145f217e967bf3cac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a85175b03d82f41186cbd2aaa31907fa631016d9fc8f73f145f217e967bf3cac","first_computed_at":"2026-07-05T10:37:51.967234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:51.967234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vcy4kCbbZ3IZ+zJoCh6b4vts8ErljJqa+1NoLzOps0LttgYOiN5zsgrBqoijI+BozibtogqMdpCN8ah7aDZGDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:51.967735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17675","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:327611823332812ed5ecb5de69bd9168e2397a99ab079822ae9213950658f7ba","sha256:52c6b3fabd8702c969a022f50ee562a27b4d5bba0e21b356c29768d0cfcde069"],"state_sha256":"b0a1297f71ead95d0a8ec1a1fadfb783d6aaf5da0a4edbe1f4dff8dd0ac66ca2"}