{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H7QDXOJSH47XHRWWGXNVLGBAQT","short_pith_number":"pith:H7QDXOJS","schema_version":"1.0","canonical_sha256":"3fe03bb9323f3f73c6d635db55982084f9ac7fd382f9aa006c47d5f5923487f0","source":{"kind":"arxiv","id":"2309.09705","version":1},"attestation_state":"computed","paper":{"title":"Synth-AC: Enhancing Audio Captioning with Synthetic Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Feiyang Xiao, Haohe Liu, Jian Guan, Kejia Zhang, Qiaoxi Zhu, Wenwu Wang, Xubo Liu","submitted_at":"2023-09-18T12:17:16Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.09705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-18T12:17:16Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"10dd1b04a36970f1b6380ed10ec2c8379f5cba195ff06a096d42d1c61b5b99e2","abstract_canon_sha256":"1cf95cf8affa25040ad63c2ac5dc0f603bb41dd80758de413da54a09a89ce49e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:43.425377Z","signature_b64":"eSj/9vuSPmjihRnbhJJ/9n9pGc10P30/paZ54IkSnc+GuCKXxG946nzNRCO5+fiuY4JdIEN1wOHjSLIECl6BAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fe03bb9323f3f73c6d635db55982084f9ac7fd382f9aa006c47d5f5923487f0","last_reissued_at":"2026-07-05T06:51:43.424952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:43.424952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synth-AC: Enhancing Audio Captioning with Synthetic Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Feiyang Xiao, Haohe Liu, Jian Guan, Kejia Zhang, Qiaoxi Zhu, Wenwu Wang, Xubo Liu","submitted_at":"2023-09-18T12:17:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09705","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.09705/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.09705","created_at":"2026-07-05T06:51:43.425008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09705v1","created_at":"2026-07-05T06:51:43.425008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09705","created_at":"2026-07-05T06:51:43.425008+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7QDXOJSH47X","created_at":"2026-07-05T06:51:43.425008+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7QDXOJSH47XHRWW","created_at":"2026-07-05T06:51:43.425008+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7QDXOJS","created_at":"2026-07-05T06:51:43.425008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7QDXOJSH47XHRWWGXNVLGBAQT","json":"https://pith.science/pith/H7QDXOJSH47XHRWWGXNVLGBAQT.json","graph_json":"https://pith.science/api/pith-number/H7QDXOJSH47XHRWWGXNVLGBAQT/graph.json","events_json":"https://pith.science/api/pith-number/H7QDXOJSH47XHRWWGXNVLGBAQT/events.json","paper":"https://pith.science/paper/H7QDXOJS"},"agent_actions":{"view_html":"https://pith.science/pith/H7QDXOJSH47XHRWWGXNVLGBAQT","download_json":"https://pith.science/pith/H7QDXOJSH47XHRWWGXNVLGBAQT.json","view_paper":"https://pith.science/paper/H7QDXOJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09705&json=true","fetch_graph":"https://pith.science/api/pith-number/H7QDXOJSH47XHRWWGXNVLGBAQT/graph.json","fetch_events":"https://pith.science/api/pith-number/H7QDXOJSH47XHRWWGXNVLGBAQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7QDXOJSH47XHRWWGXNVLGBAQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7QDXOJSH47XHRWWGXNVLGBAQT/action/storage_attestation","attest_author":"https://pith.science/pith/H7QDXOJSH47XHRWWGXNVLGBAQT/action/author_attestation","sign_citation":"https://pith.science/pith/H7QDXOJSH47XHRWWGXNVLGBAQT/action/citation_signature","submit_replication":"https://pith.science/pith/H7QDXOJSH47XHRWWGXNVLGBAQT/action/replication_record"}},"created_at":"2026-07-05T06:51:43.425008+00:00","updated_at":"2026-07-05T06:51:43.425008+00:00"}