{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GXADJWNC4L7MZLLKTFAHF66LCQ","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":"171dac8615d9857523685b2381c71a3d096fd7a077f48caaef7a0bda831efcdc","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-05T11:07:13Z","title_canon_sha256":"3799f687b76a279c78b679d25ba20260299b2941bee6e808566ea17f43369dd7"},"schema_version":"1.0","source":{"id":"2407.04416","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04416","created_at":"2026-07-05T09:55:58Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04416v4","created_at":"2026-07-05T09:55:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04416","created_at":"2026-07-05T09:55:58Z"},{"alias_kind":"pith_short_12","alias_value":"GXADJWNC4L7M","created_at":"2026-07-05T09:55:58Z"},{"alias_kind":"pith_short_16","alias_value":"GXADJWNC4L7MZLLK","created_at":"2026-07-05T09:55:58Z"},{"alias_kind":"pith_short_8","alias_value":"GXADJWNC","created_at":"2026-07-05T09:55:58Z"}],"graph_snapshots":[{"event_id":"sha256:22c8d162a61123a724efc021c5e2ceb7014f6c9e5930674c93c903b6674a4650","target":"graph","created_at":"2026-07-05T09:55:58Z","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/2407.04416/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from the simplicity and scarcity of the training data. This work aims to create a large-scale audio dataset with rich captions for improving audio generation models. We first develop an automated pipeline to generate detailed captions by transforming predicted visual captions, audio captions, and tagging labels into comprehensive descriptions using a Large Langua","authors_text":"Dongya Jia, Mark D. Plumbley, Wenwu Wang, Xiaobin Zhuang, Xiyuan Kang, Xubo Liu, Yi Yuan, Yuanzhe Chen, Yuping Wang, Yuxuan Wang, Zhengxi Liu, Zhuo Chen","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-05T11:07:13Z","title":"Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04416","kind":"arxiv","version":4},"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:c4d26e8995997c9866a058691c62afd96600950da6f6bedef1d62f97bfaff504","target":"record","created_at":"2026-07-05T09:55:58Z","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":"171dac8615d9857523685b2381c71a3d096fd7a077f48caaef7a0bda831efcdc","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-05T11:07:13Z","title_canon_sha256":"3799f687b76a279c78b679d25ba20260299b2941bee6e808566ea17f43369dd7"},"schema_version":"1.0","source":{"id":"2407.04416","kind":"arxiv","version":4}},"canonical_sha256":"35c034d9a2e2feccad6a994072fbcb142d2ecebb221a251f7589edec76bcbe80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35c034d9a2e2feccad6a994072fbcb142d2ecebb221a251f7589edec76bcbe80","first_computed_at":"2026-07-05T09:55:58.522831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:58.522831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FdRv/Lb97fLD3CqAhhI3WBp8C6b3EynV9qbfTOUoWvm9ZOMg2giryRcOn1ulcySTSbGzALbAL0nsCLS8BbS0BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:58.523244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04416","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4d26e8995997c9866a058691c62afd96600950da6f6bedef1d62f97bfaff504","sha256:22c8d162a61123a724efc021c5e2ceb7014f6c9e5930674c93c903b6674a4650"],"state_sha256":"f53efe4f880876bc83e20d46322e8bdf5a60703b5250d1d0dbe01c537b4e8076"}