{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QFBNZNJLLQBIZECQUJHWXQGIL2","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":"126f7a0283e408b294da95622a78688a4dab17670c3491ff2124584871e984d1","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-12T11:43:54Z","title_canon_sha256":"0c525aa59ea118f26807ae54a50e25da0cf733d2754827ae6665ca96458dff20"},"schema_version":"1.0","source":{"id":"2410.09503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09503","created_at":"2026-07-05T09:19:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09503v1","created_at":"2026-07-05T09:19:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09503","created_at":"2026-07-05T09:19:40Z"},{"alias_kind":"pith_short_12","alias_value":"QFBNZNJLLQBI","created_at":"2026-07-05T09:19:40Z"},{"alias_kind":"pith_short_16","alias_value":"QFBNZNJLLQBIZECQ","created_at":"2026-07-05T09:19:40Z"},{"alias_kind":"pith_short_8","alias_value":"QFBNZNJL","created_at":"2026-07-05T09:19:40Z"}],"graph_snapshots":[{"event_id":"sha256:cdbda5a99ce42901cb03158d3615e4f7727c6e942468ac534f1764393704d7ef","target":"graph","created_at":"2026-07-05T09:19:40Z","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/2410.09503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kai Yu, Wenxi Chen, Xie Chen, Xiquan Li, Xuenan Xu, Yuzhe Liang, Zhisheng Zheng, Ziyang Ma","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-12T11:43:54Z","title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09503","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":"sha256:8b785da328c63f6c2860484def10380b2e84e330aa8a161fea08e0fecc9f48b3","target":"record","created_at":"2026-07-05T09:19:40Z","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":"126f7a0283e408b294da95622a78688a4dab17670c3491ff2124584871e984d1","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-12T11:43:54Z","title_canon_sha256":"0c525aa59ea118f26807ae54a50e25da0cf733d2754827ae6665ca96458dff20"},"schema_version":"1.0","source":{"id":"2410.09503","kind":"arxiv","version":1}},"canonical_sha256":"8142dcb52b5c028c9050a24f6bc0c85e9642db24638c4f1ad2e17d084ddb9276","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8142dcb52b5c028c9050a24f6bc0c85e9642db24638c4f1ad2e17d084ddb9276","first_computed_at":"2026-07-05T09:19:40.060230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:40.060230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MZ1b8JkFD16tDBFsGJpigYE/s3AK8sDNSSyTBHJSRmpAnguAEpBQ9EkKKcrJ1caF3hcIZAZhng92L13sIbWFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:40.060699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b785da328c63f6c2860484def10380b2e84e330aa8a161fea08e0fecc9f48b3","sha256:cdbda5a99ce42901cb03158d3615e4f7727c6e942468ac534f1764393704d7ef"],"state_sha256":"84b7354549edbd553953edf756f80751a195a06a26ba6e6d34b702a69b07f076"}