{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H7QDXOJSH47XHRWWGXNVLGBAQT","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":"1cf95cf8affa25040ad63c2ac5dc0f603bb41dd80758de413da54a09a89ce49e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-18T12:17:16Z","title_canon_sha256":"10dd1b04a36970f1b6380ed10ec2c8379f5cba195ff06a096d42d1c61b5b99e2"},"schema_version":"1.0","source":{"id":"2309.09705","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09705","created_at":"2026-07-05T06:51:43Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09705v1","created_at":"2026-07-05T06:51:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09705","created_at":"2026-07-05T06:51:43Z"},{"alias_kind":"pith_short_12","alias_value":"H7QDXOJSH47X","created_at":"2026-07-05T06:51:43Z"},{"alias_kind":"pith_short_16","alias_value":"H7QDXOJSH47XHRWW","created_at":"2026-07-05T06:51:43Z"},{"alias_kind":"pith_short_8","alias_value":"H7QDXOJS","created_at":"2026-07-05T06:51:43Z"}],"graph_snapshots":[{"event_id":"sha256:2d307a440c876c10e1f1ce58899728783c769cc144b62b87d26740aea9047868","target":"graph","created_at":"2026-07-05T06:51:43Z","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/2309.09705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data-driven approaches hold promise for audio captioning. However, the development of audio captioning methods can be biased due to the limited availability and quality of text-audio data. This paper proposes a SynthAC framework, which leverages recent advances in audio generative models and commonly available text corpus to create synthetic text-audio pairs, thereby enhancing text-audio representation. Specifically, the text-to-audio generation model, i.e., AudioLDM, is used to generate synthetic audio signals with captions from an image captioning dataset. Our SynthAC expands the availabilit","authors_text":"Feiyang Xiao, Haohe Liu, Jian Guan, Kejia Zhang, Qiaoxi Zhu, Wenwu Wang, Xubo Liu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-18T12:17:16Z","title":"Synth-AC: Enhancing Audio Captioning with Synthetic Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09705","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":"sha256:5803eda981d1835a4edeb9960a5290cb949af22e227f5c80403e0800829a52ea","target":"record","created_at":"2026-07-05T06:51:43Z","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":"1cf95cf8affa25040ad63c2ac5dc0f603bb41dd80758de413da54a09a89ce49e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-18T12:17:16Z","title_canon_sha256":"10dd1b04a36970f1b6380ed10ec2c8379f5cba195ff06a096d42d1c61b5b99e2"},"schema_version":"1.0","source":{"id":"2309.09705","kind":"arxiv","version":1}},"canonical_sha256":"3fe03bb9323f3f73c6d635db55982084f9ac7fd382f9aa006c47d5f5923487f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fe03bb9323f3f73c6d635db55982084f9ac7fd382f9aa006c47d5f5923487f0","first_computed_at":"2026-07-05T06:51:43.424952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:43.424952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eSj/9vuSPmjihRnbhJJ/9n9pGc10P30/paZ54IkSnc+GuCKXxG946nzNRCO5+fiuY4JdIEN1wOHjSLIECl6BAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:43.425377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.09705","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5803eda981d1835a4edeb9960a5290cb949af22e227f5c80403e0800829a52ea","sha256:2d307a440c876c10e1f1ce58899728783c769cc144b62b87d26740aea9047868"],"state_sha256":"44630d8d70f8b37ae13513e76ce32d6b2f162c9e8edab8f8eb678ee52e580a53"}