{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H2PR7AIEGF75DB4SIDYWV56M5G","short_pith_number":"pith:H2PR7AIE","schema_version":"1.0","canonical_sha256":"3e9f1f8104317fd1879240f16af7cce991b0ad51aca118ebcc88190fdfa45bcf","source":{"kind":"arxiv","id":"2406.06295","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Audio Captioning Using Soft and Hard Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Ruoyi Du, Wenwu Wang, Xuenan Xu, Yiming Zhang, Yuan Dong, Zhanyu Ma, Zheng-Hua Tan","submitted_at":"2024-06-10T14:16:28Z","abstract_excerpt":"In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test sets from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, which, however, has received little attention. We"},"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":"2406.06295","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-10T14:16:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c1cbb65166ed5712623c9b5f8dc16a0b7b6982f821ee530ce476538bc8267d71","abstract_canon_sha256":"7666b259ea301d18161319f7bbce7a5de7d10f0fe6c3896d9f91119f154b3ce9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:40.376845Z","signature_b64":"5V8VUq77gC/09CvFuZ8td/Hkya7q6nhxOzBtak0+C2sLN2lHPFjZPnu2eqYFgVIgJBDJspAQExlyKgRSeJXIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e9f1f8104317fd1879240f16af7cce991b0ad51aca118ebcc88190fdfa45bcf","last_reissued_at":"2026-07-05T08:29:40.376456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:40.376456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Audio Captioning Using Soft and Hard Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haohe Liu, Ruoyi Du, Wenwu Wang, Xuenan Xu, Yiming Zhang, Yuan Dong, Zhanyu Ma, Zheng-Hua Tan","submitted_at":"2024-06-10T14:16:28Z","abstract_excerpt":"In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test sets from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, which, however, has received little attention. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06295","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/2406.06295/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":"2406.06295","created_at":"2026-07-05T08:29:40.376509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06295v1","created_at":"2026-07-05T08:29:40.376509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06295","created_at":"2026-07-05T08:29:40.376509+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2PR7AIEGF75","created_at":"2026-07-05T08:29:40.376509+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2PR7AIEGF75DB4S","created_at":"2026-07-05T08:29:40.376509+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2PR7AIE","created_at":"2026-07-05T08:29:40.376509+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/H2PR7AIEGF75DB4SIDYWV56M5G","json":"https://pith.science/pith/H2PR7AIEGF75DB4SIDYWV56M5G.json","graph_json":"https://pith.science/api/pith-number/H2PR7AIEGF75DB4SIDYWV56M5G/graph.json","events_json":"https://pith.science/api/pith-number/H2PR7AIEGF75DB4SIDYWV56M5G/events.json","paper":"https://pith.science/paper/H2PR7AIE"},"agent_actions":{"view_html":"https://pith.science/pith/H2PR7AIEGF75DB4SIDYWV56M5G","download_json":"https://pith.science/pith/H2PR7AIEGF75DB4SIDYWV56M5G.json","view_paper":"https://pith.science/paper/H2PR7AIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06295&json=true","fetch_graph":"https://pith.science/api/pith-number/H2PR7AIEGF75DB4SIDYWV56M5G/graph.json","fetch_events":"https://pith.science/api/pith-number/H2PR7AIEGF75DB4SIDYWV56M5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2PR7AIEGF75DB4SIDYWV56M5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2PR7AIEGF75DB4SIDYWV56M5G/action/storage_attestation","attest_author":"https://pith.science/pith/H2PR7AIEGF75DB4SIDYWV56M5G/action/author_attestation","sign_citation":"https://pith.science/pith/H2PR7AIEGF75DB4SIDYWV56M5G/action/citation_signature","submit_replication":"https://pith.science/pith/H2PR7AIEGF75DB4SIDYWV56M5G/action/replication_record"}},"created_at":"2026-07-05T08:29:40.376509+00:00","updated_at":"2026-07-05T08:29:40.376509+00:00"}