{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QFBNZNJLLQBIZECQUJHWXQGIL2","short_pith_number":"pith:QFBNZNJL","schema_version":"1.0","canonical_sha256":"8142dcb52b5c028c9050a24f6bc0c85e9642db24638c4f1ad2e17d084ddb9276","source":{"kind":"arxiv","id":"2410.09503","version":1},"attestation_state":"computed","paper":{"title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Kai Yu, Wenxi Chen, Xie Chen, Xiquan Li, Xuenan Xu, Yuzhe Liang, Zhisheng Zheng, Ziyang Ma","submitted_at":"2024-10-12T11:43:54Z","abstract_excerpt":"Automated Audio Captioning (AAC) aims to generate natural textual descriptions for input audio signals. Recent progress in audio pre-trained models and large language models (LLMs) has significantly enhanced audio understanding and textual reasoning capabilities, making improvements in AAC possible. In this paper, we propose SLAM-AAC to further enhance AAC with paraphrasing augmentation and CLAP-Refine through LLMs. Our approach uses the self-supervised EAT model to extract fine-grained audio representations, which are then aligned with textual embeddings via lightweight linear layers. The cap"},"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":"2410.09503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-12T11:43:54Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0c525aa59ea118f26807ae54a50e25da0cf733d2754827ae6665ca96458dff20","abstract_canon_sha256":"126f7a0283e408b294da95622a78688a4dab17670c3491ff2124584871e984d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:40.060699Z","signature_b64":"MZ1b8JkFD16tDBFsGJpigYE/s3AK8sDNSSyTBHJSRmpAnguAEpBQ9EkKKcrJ1caF3hcIZAZhng92L13sIbWFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8142dcb52b5c028c9050a24f6bc0c85e9642db24638c4f1ad2e17d084ddb9276","last_reissued_at":"2026-07-05T09:19:40.060230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:40.060230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Kai Yu, Wenxi Chen, Xie Chen, Xiquan Li, Xuenan Xu, Yuzhe Liang, Zhisheng Zheng, Ziyang Ma","submitted_at":"2024-10-12T11:43:54Z","abstract_excerpt":"Automated Audio Captioning (AAC) aims to generate natural textual descriptions for input audio signals. Recent progress in audio pre-trained models and large language models (LLMs) has significantly enhanced audio understanding and textual reasoning capabilities, making improvements in AAC possible. In this paper, we propose SLAM-AAC to further enhance AAC with paraphrasing augmentation and CLAP-Refine through LLMs. Our approach uses the self-supervised EAT model to extract fine-grained audio representations, which are then aligned with textual embeddings via lightweight linear layers. The cap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09503","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/2410.09503/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":"2410.09503","created_at":"2026-07-05T09:19:40.060284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09503v1","created_at":"2026-07-05T09:19:40.060284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09503","created_at":"2026-07-05T09:19:40.060284+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFBNZNJLLQBI","created_at":"2026-07-05T09:19:40.060284+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFBNZNJLLQBIZECQ","created_at":"2026-07-05T09:19:40.060284+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFBNZNJL","created_at":"2026-07-05T09:19:40.060284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01169","citing_title":"OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFBNZNJLLQBIZECQUJHWXQGIL2","json":"https://pith.science/pith/QFBNZNJLLQBIZECQUJHWXQGIL2.json","graph_json":"https://pith.science/api/pith-number/QFBNZNJLLQBIZECQUJHWXQGIL2/graph.json","events_json":"https://pith.science/api/pith-number/QFBNZNJLLQBIZECQUJHWXQGIL2/events.json","paper":"https://pith.science/paper/QFBNZNJL"},"agent_actions":{"view_html":"https://pith.science/pith/QFBNZNJLLQBIZECQUJHWXQGIL2","download_json":"https://pith.science/pith/QFBNZNJLLQBIZECQUJHWXQGIL2.json","view_paper":"https://pith.science/paper/QFBNZNJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09503&json=true","fetch_graph":"https://pith.science/api/pith-number/QFBNZNJLLQBIZECQUJHWXQGIL2/graph.json","fetch_events":"https://pith.science/api/pith-number/QFBNZNJLLQBIZECQUJHWXQGIL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFBNZNJLLQBIZECQUJHWXQGIL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFBNZNJLLQBIZECQUJHWXQGIL2/action/storage_attestation","attest_author":"https://pith.science/pith/QFBNZNJLLQBIZECQUJHWXQGIL2/action/author_attestation","sign_citation":"https://pith.science/pith/QFBNZNJLLQBIZECQUJHWXQGIL2/action/citation_signature","submit_replication":"https://pith.science/pith/QFBNZNJLLQBIZECQUJHWXQGIL2/action/replication_record"}},"created_at":"2026-07-05T09:19:40.060284+00:00","updated_at":"2026-07-05T09:19:40.060284+00:00"}