{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:POEWCBW2UWGOTSETIWZIW4DY2V","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":"8288b35c3a560faa2d94b70437d3aad717b8c0c85affb5b9dbf6b40941220fb2","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-15T17:59:29Z","title_canon_sha256":"9135475023c4c802e8b3875c90f1a1c257ef7f7dd69c1b5509eb814318bbca26"},"schema_version":"1.0","source":{"id":"2505.10561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10561","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10561v1","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10561","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"POEWCBW2UWGO","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"POEWCBW2UWGOTSET","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"POEWCBW2","created_at":"2026-07-05T11:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:19a8b68dc4fd841e20c645e5987168f237fb732a44f103452b8f72a87ae62fb5","target":"graph","created_at":"2026-07-05T11:03:45Z","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/2505.10561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-audio (T2A) generation has achieved remarkable progress in generating a variety of audio outputs from language prompts. However, current state-of-the-art T2A models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio. To improve the performance of the model in these high-level applications, we propose to enhance the basic capabilities of the model with AI feedback learning. First, we introduce fine-grained AI audio scoring pipelines to: 1) verify whether each event in the text prompt is present in the audio (Ev","authors_text":"Chen Zhu, Jiawei Huang, Ke Lei, Luping Liu, Sashuai Zhou, Shengpeng Ji, Tao Jin, Xize Cheng, Zehan Wang, Zhenhui Ye, Zhou Zhao","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-15T17:59:29Z","title":"T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10561","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":"sha256:689e918ebca060b9e00120b851dd3a7b5b54a86d6287dcb34b6b15cde13fe086","target":"record","created_at":"2026-07-05T11:03:45Z","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":"8288b35c3a560faa2d94b70437d3aad717b8c0c85affb5b9dbf6b40941220fb2","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-15T17:59:29Z","title_canon_sha256":"9135475023c4c802e8b3875c90f1a1c257ef7f7dd69c1b5509eb814318bbca26"},"schema_version":"1.0","source":{"id":"2505.10561","kind":"arxiv","version":1}},"canonical_sha256":"7b896106daa58ce9c89345b28b7078d56f1a9ddfc074cfdbafad1d9683f1b10c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b896106daa58ce9c89345b28b7078d56f1a9ddfc074cfdbafad1d9683f1b10c","first_computed_at":"2026-07-05T11:03:45.734092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:45.734092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tg+DWXqNoGkJqBZqGlRYpDcwZ7lVruOt2IGu9QBLrJudisrtmg+vsloxUT1LWzaFkaGzPGvzsW5S5yGrjHqPAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:45.734714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:689e918ebca060b9e00120b851dd3a7b5b54a86d6287dcb34b6b15cde13fe086","sha256:19a8b68dc4fd841e20c645e5987168f237fb732a44f103452b8f72a87ae62fb5"],"state_sha256":"d67197263afc918337d722189702996fc59c026d65b7c87db6569f7513288a18"}