{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FUCAHD754V6EJEWUKE3RRZYT3E","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":"469dbc58f8a4e329a1105447a4f778bdd7845a1e9569874f0dd7a623bdca441d","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-28T07:32:07Z","title_canon_sha256":"0aaeefe09b74f400d0e1e3411d30929b2d030a2e939160186882fb3d38f3c678"},"schema_version":"1.0","source":{"id":"2501.16761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16761","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16761v1","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16761","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"FUCAHD754V6E","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"pith_short_16","alias_value":"FUCAHD754V6EJEWU","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"pith_short_8","alias_value":"FUCAHD75","created_at":"2026-07-05T10:06:18Z"}],"graph_snapshots":[{"event_id":"sha256:e17e6365b7ec0965b383dbc66b3c5bd7721fd83d7e1e79d7552fea0676ec9bc8","target":"graph","created_at":"2026-07-05T10:06:18Z","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/2501.16761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-Audio (TTA) generation is an emerging area within AI-generated content (AIGC), where audio is created from natural language descriptions. Despite growing interest, developing robust TTA models remains challenging due to the scarcity of well-labeled datasets and the prevalence of noisy or inaccurate captions in large-scale, weakly labeled corpora. To address these challenges, we propose CosyAudio, a novel framework that utilizes confidence scores and synthetic captions to enhance the quality of audio generation. CosyAudio consists of two core components: AudioCapTeller and an audio gene","authors_text":"Lei He, Lei Xie, Sheng Zhao, Wenjie Tian, Xinfa Zhu, Xinsheng Wang, Xi Wang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-28T07:32:07Z","title":"CosyAudio: Improving Audio Generation with Confidence Scores and Synthetic Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16761","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":"sha256:9e8aec92b8d691afb13be8b09dbebf4b9cea33695522c9c341e3440b92764943","target":"record","created_at":"2026-07-05T10:06:18Z","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":"469dbc58f8a4e329a1105447a4f778bdd7845a1e9569874f0dd7a623bdca441d","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-28T07:32:07Z","title_canon_sha256":"0aaeefe09b74f400d0e1e3411d30929b2d030a2e939160186882fb3d38f3c678"},"schema_version":"1.0","source":{"id":"2501.16761","kind":"arxiv","version":1}},"canonical_sha256":"2d04038ffde57c4492d4513718e713d90f7127d2d4a111759ce24d09fd162007","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d04038ffde57c4492d4513718e713d90f7127d2d4a111759ce24d09fd162007","first_computed_at":"2026-07-05T10:06:18.150358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:18.150358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c3bBX475lQ/c9b3q0lysx0idON2uGuYSRboe4j8pRHVktjW89HSYyr7SDdZehbNfClfCv/pzAv+/pC1ARLWBAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:18.150801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e8aec92b8d691afb13be8b09dbebf4b9cea33695522c9c341e3440b92764943","sha256:e17e6365b7ec0965b383dbc66b3c5bd7721fd83d7e1e79d7552fea0676ec9bc8"],"state_sha256":"35c7c207013b2fbec214cc4682a21dd3e0cd7f1e339f6ecb458f2290e36a5dc9"}