{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3A4O4Z3UCHU2OTZOJXL2XZLEFE","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":"1f4c2042cf92b5893d68e4a0613ed795819bf1777ac3e6442aab016e739f3dbe","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-12T10:21:00Z","title_canon_sha256":"41e7eb3b088162d0175d030933a8663ee72005971940416971a9c444cf9f831d"},"schema_version":"1.0","source":{"id":"2410.09472","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09472","created_at":"2026-07-05T09:57:23Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09472v2","created_at":"2026-07-05T09:57:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09472","created_at":"2026-07-05T09:57:23Z"},{"alias_kind":"pith_short_12","alias_value":"3A4O4Z3UCHU2","created_at":"2026-07-05T09:57:23Z"},{"alias_kind":"pith_short_16","alias_value":"3A4O4Z3UCHU2OTZO","created_at":"2026-07-05T09:57:23Z"},{"alias_kind":"pith_short_8","alias_value":"3A4O4Z3U","created_at":"2026-07-05T09:57:23Z"}],"graph_snapshots":[{"event_id":"sha256:1554fe4f0617466ac11a54f6296f34d7569239789d1d8bafa7382fc683893174","target":"graph","created_at":"2026-07-05T09:57:23Z","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/2410.09472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While automated audio captioning (AAC) has made notable progress, traditional fully supervised AAC models still face two critical challenges: the need for expensive audio-text pair data for training and performance degradation when transferring across domains. To overcome these limitations, we present DRCap, a data-efficient and flexible zero-shot audio captioning system that requires text-only data for training and can quickly adapt to new domains without additional fine-tuning. DRCap integrates a contrastive language-audio pre-training (CLAP) model and a large-language model (LLM) as its bac","authors_text":"Qiuqiang Kong, Wenxi Chen, Xie Chen, Xiquan Li, Xuenan Xu, Yuzhe Liang, Zhisheng Zheng, Ziyang Ma","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-12T10:21:00Z","title":"DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09472","kind":"arxiv","version":2},"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":"sha256:79bf0aa27c3753a3440b066514122d4a324014a071d126f7efa10510c94341c1","target":"record","created_at":"2026-07-05T09:57:23Z","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":"1f4c2042cf92b5893d68e4a0613ed795819bf1777ac3e6442aab016e739f3dbe","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-12T10:21:00Z","title_canon_sha256":"41e7eb3b088162d0175d030933a8663ee72005971940416971a9c444cf9f831d"},"schema_version":"1.0","source":{"id":"2410.09472","kind":"arxiv","version":2}},"canonical_sha256":"d838ee677411e9a74f2e4dd7abe564291346361e8b606f89ae97520c8b0efa84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d838ee677411e9a74f2e4dd7abe564291346361e8b606f89ae97520c8b0efa84","first_computed_at":"2026-07-05T09:57:23.348845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:23.348845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VmxDt3kQpRKZGB96To70nzhdgDvQycKoJwNkkHTj9D3HjggRSlzjbVC5CyM2DP0Zsbpt2XmqAOdefVblNlMXCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:23.349394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09472","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79bf0aa27c3753a3440b066514122d4a324014a071d126f7efa10510c94341c1","sha256:1554fe4f0617466ac11a54f6296f34d7569239789d1d8bafa7382fc683893174"],"state_sha256":"a2555a845366a81982cb8b5c0db83855ab8b7134fe9e9f0442c02f1981eb13b2"}