{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SIGZTV5X7AW7TFU7JHJBWWYH7Y","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":"35655f94b0df08ba674f052b9ba3936eb451e1cff50de94242471cc533d7531d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T19:03:37Z","title_canon_sha256":"152be6b29687174cdd1391beded116cd676542b027c161f3d67c508466f8a00a"},"schema_version":"1.0","source":{"id":"2505.22792","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22792","created_at":"2026-07-05T11:51:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22792v2","created_at":"2026-07-05T11:51:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22792","created_at":"2026-07-05T11:51:27Z"},{"alias_kind":"pith_short_12","alias_value":"SIGZTV5X7AW7","created_at":"2026-07-05T11:51:27Z"},{"alias_kind":"pith_short_16","alias_value":"SIGZTV5X7AW7TFU7","created_at":"2026-07-05T11:51:27Z"},{"alias_kind":"pith_short_8","alias_value":"SIGZTV5X","created_at":"2026-07-05T11:51:27Z"}],"graph_snapshots":[{"event_id":"sha256:51d3f88c653d84b04bfeca58f0aebb2287d2a5dac4805d0bb3c422c410dfa935","target":"graph","created_at":"2026-07-05T11:51:27Z","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/2505.22792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating images from rhetorical languages remains a critical challenge for text-to-image models. Even state-of-the-art (SOTA) multimodal large language models (MLLM) fail to generate images based on the hidden meaning inherent in rhetorical language--despite such content being readily mappable to visual representations by humans. A key limitation is that current models emphasize object-level word embedding alignment, causing metaphorical expressions to steer image generation towards their literal visuals and overlook the intended semantic meaning. To address this, we propose Rhet2Pix, a fram","authors_text":"Sibo Wang, Xinyu Du, Yueting Li, Yuxi Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T19:03:37Z","title":"Rhetorical Text-to-Image Generation via Two-layer Diffusion Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22792","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:aaa839bad85958985309f72eab03e7026f34951660cd1a496142b28d73cb72c7","target":"record","created_at":"2026-07-05T11:51:27Z","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":"35655f94b0df08ba674f052b9ba3936eb451e1cff50de94242471cc533d7531d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T19:03:37Z","title_canon_sha256":"152be6b29687174cdd1391beded116cd676542b027c161f3d67c508466f8a00a"},"schema_version":"1.0","source":{"id":"2505.22792","kind":"arxiv","version":2}},"canonical_sha256":"920d99d7b7f82df9969f49d21b5b07fe0d408fbe9a2d97ef234d91568846a1ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"920d99d7b7f82df9969f49d21b5b07fe0d408fbe9a2d97ef234d91568846a1ac","first_computed_at":"2026-07-05T11:51:27.725809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:27.725809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N47PhQqxIIfflKHp4SXKgPKA0FzZ7IBW1vk5Xaoufy2ilwkf1WF05pjDwQLo0PwZphj/h6SS06Vw6eBQxXwHDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:27.729578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22792","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaa839bad85958985309f72eab03e7026f34951660cd1a496142b28d73cb72c7","sha256:51d3f88c653d84b04bfeca58f0aebb2287d2a5dac4805d0bb3c422c410dfa935"],"state_sha256":"3625d9c07a1764a1923c14cb808b762f9ebe2526ce95a25c14812037ec7b15ce"}