{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5XUYO6BU7N6VE2ML47COMDDUHX","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":"5c2040625a80a7abf43204184db6ae4e03e6958085a6bca870e9e893d67866d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T12:31:16Z","title_canon_sha256":"8bf8a0311354af2f9942a7374f32dd9cecfe6398eeedfc461261a020e5c2cb09"},"schema_version":"1.0","source":{"id":"2608.09529","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09529","created_at":"2026-08-11T02:24:25Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09529v1","created_at":"2026-08-11T02:24:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09529","created_at":"2026-08-11T02:24:25Z"},{"alias_kind":"pith_short_12","alias_value":"5XUYO6BU7N6V","created_at":"2026-08-11T02:24:25Z"},{"alias_kind":"pith_short_16","alias_value":"5XUYO6BU7N6VE2ML","created_at":"2026-08-11T02:24:25Z"},{"alias_kind":"pith_short_8","alias_value":"5XUYO6BU","created_at":"2026-08-11T02:24:25Z"}],"graph_snapshots":[{"event_id":"sha256:8e1192cba81fa8c9a52d9d15d7ad8a924b4932f7ad49eac5cf7b85a518c59046","target":"graph","created_at":"2026-08-11T02:24:25Z","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/2608.09529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As an important subfield of cross-modal generation, synthesizing static visual content in the form of images from audio, namely audio-to-image (A2I) generation, has attracted increasing research attention in recent years. Nevertheless, despite the remarkable visual quality of modern text-to-image (T2I) models, the performance of A2I remains fundamentally limited by traditional datasets, which often lack both high-fidelity images and precise cross-modal alignment. As a result, existing methods still struggle to achieve high-quality audio-to-image generation through finetuning strong T2I models,","authors_text":"Cheng Gong, Chi Zhang, Dongxu Ge, Shansong Liu, Xiao-Lei Zhang, Xuelong Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T12:31:16Z","title":"Towards Expressive and Faithful Audio-to-Image Generation: A Unified Multimodal Dataset and Synthesis Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09529","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":"sha256:0354b438e40e65a7f9546c7319900e425f8bb35c934a2929a6a57435e43835e3","target":"record","created_at":"2026-08-11T02:24:25Z","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":"5c2040625a80a7abf43204184db6ae4e03e6958085a6bca870e9e893d67866d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T12:31:16Z","title_canon_sha256":"8bf8a0311354af2f9942a7374f32dd9cecfe6398eeedfc461261a020e5c2cb09"},"schema_version":"1.0","source":{"id":"2608.09529","kind":"arxiv","version":1}},"canonical_sha256":"ede9877834fb7d52698be7c4e60c743df5b3db1bb45a546e819ccde86de0a756","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ede9877834fb7d52698be7c4e60c743df5b3db1bb45a546e819ccde86de0a756","first_computed_at":"2026-08-11T02:24:25.418688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:24:25.418688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VYF4Up+CVB0tEtBjSnNLnYiC7wkI8ss8nWB1Xb2lpToUTTA7PwX1oHk72WiNgSh58j9h/lkzqBquihbSw/kyCw==","signature_status":"signed_v1","signed_at":"2026-08-11T02:24:25.420190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09529","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0354b438e40e65a7f9546c7319900e425f8bb35c934a2929a6a57435e43835e3","sha256:8e1192cba81fa8c9a52d9d15d7ad8a924b4932f7ad49eac5cf7b85a518c59046"],"state_sha256":"7f962582c4732f774ef91a84e7687a0ddf968a265561639cd4f3350f99ae381a"}