{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H2PR7AIEGF75DB4SIDYWV56M5G","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":"7666b259ea301d18161319f7bbce7a5de7d10f0fe6c3896d9f91119f154b3ce9","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-10T14:16:28Z","title_canon_sha256":"c1cbb65166ed5712623c9b5f8dc16a0b7b6982f821ee530ce476538bc8267d71"},"schema_version":"1.0","source":{"id":"2406.06295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06295","created_at":"2026-07-05T08:29:40Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06295v1","created_at":"2026-07-05T08:29:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06295","created_at":"2026-07-05T08:29:40Z"},{"alias_kind":"pith_short_12","alias_value":"H2PR7AIEGF75","created_at":"2026-07-05T08:29:40Z"},{"alias_kind":"pith_short_16","alias_value":"H2PR7AIEGF75DB4S","created_at":"2026-07-05T08:29:40Z"},{"alias_kind":"pith_short_8","alias_value":"H2PR7AIE","created_at":"2026-07-05T08:29:40Z"}],"graph_snapshots":[{"event_id":"sha256:9e81ee9d904ceaef6b11eb95db9a8075bff194191af50d5702dc7ef94d762e63","target":"graph","created_at":"2026-07-05T08:29:40Z","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/2406.06295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haohe Liu, Ruoyi Du, Wenwu Wang, Xuenan Xu, Yiming Zhang, Yuan Dong, Zhanyu Ma, Zheng-Hua Tan","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-10T14:16:28Z","title":"Zero-Shot Audio Captioning Using Soft and Hard Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06295","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":"sha256:6d690a3b48eef6cf60c3848e47ad499206c053159cb0c43a744a4e092a8925d0","target":"record","created_at":"2026-07-05T08:29:40Z","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":"7666b259ea301d18161319f7bbce7a5de7d10f0fe6c3896d9f91119f154b3ce9","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-10T14:16:28Z","title_canon_sha256":"c1cbb65166ed5712623c9b5f8dc16a0b7b6982f821ee530ce476538bc8267d71"},"schema_version":"1.0","source":{"id":"2406.06295","kind":"arxiv","version":1}},"canonical_sha256":"3e9f1f8104317fd1879240f16af7cce991b0ad51aca118ebcc88190fdfa45bcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e9f1f8104317fd1879240f16af7cce991b0ad51aca118ebcc88190fdfa45bcf","first_computed_at":"2026-07-05T08:29:40.376456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:40.376456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5V8VUq77gC/09CvFuZ8td/Hkya7q6nhxOzBtak0+C2sLN2lHPFjZPnu2eqYFgVIgJBDJspAQExlyKgRSeJXIDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:40.376845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d690a3b48eef6cf60c3848e47ad499206c053159cb0c43a744a4e092a8925d0","sha256:9e81ee9d904ceaef6b11eb95db9a8075bff194191af50d5702dc7ef94d762e63"],"state_sha256":"07555e813c79eec462595712b69055daaf4ec87d5361eb17dcdb6fd471aad0d2"}