{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W4V7RKFJWJY5UXPOZK3M44KPXV","short_pith_number":"pith:W4V7RKFJ","schema_version":"1.0","canonical_sha256":"b72bf8a8a9b271da5deecab6ce714fbd659d0b13a2cb14b0ab1e07a8d8d7ae59","source":{"kind":"arxiv","id":"2505.15307","version":1},"attestation_state":"computed","paper":{"title":"Towards Pre-training an Effective Respiratory Audio Foundation Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Binh Thien Nguyen, Daiki Takeuchi, Daisuke Niizumi, Masahiro Yasuda, Noboru Harada, Yasunori Ohishi","submitted_at":"2025-05-21T09:36:11Z","abstract_excerpt":"Recent advancements in foundation models have sparked interest in respiratory audio foundation models. However, the effectiveness of applying conventional pre-training schemes to datasets that are small-sized and lack diversity has not been sufficiently verified. This study aims to explore better pre-training practices for respiratory sounds by comparing numerous pre-trained audio models. Our investigation reveals that models pre-trained on AudioSet, a general audio dataset, are more effective than the models specifically pre-trained on respiratory sounds. Moreover, combining AudioSet and resp"},"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":"2505.15307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-21T09:36:11Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"709e7ae5e137758c7c22de598658b179b5d9d9d1814c00763c5f8dd936d3aefb","abstract_canon_sha256":"da61790d7c5d45fa9fd5f0abbb84b9678333e3749cb9baf9ce24dc4b89deb399"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:43.529799Z","signature_b64":"gzUthBhb4U/owAcltRWASZU+ypEZPB7YwiELyBqMcN56tNDfXS51EB3j9cpCAj5a8kfHY1LusHuEckHKhH0dBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b72bf8a8a9b271da5deecab6ce714fbd659d0b13a2cb14b0ab1e07a8d8d7ae59","last_reissued_at":"2026-07-05T11:06:43.529301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:43.529301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Pre-training an Effective Respiratory Audio Foundation Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Binh Thien Nguyen, Daiki Takeuchi, Daisuke Niizumi, Masahiro Yasuda, Noboru Harada, Yasunori Ohishi","submitted_at":"2025-05-21T09:36:11Z","abstract_excerpt":"Recent advancements in foundation models have sparked interest in respiratory audio foundation models. However, the effectiveness of applying conventional pre-training schemes to datasets that are small-sized and lack diversity has not been sufficiently verified. This study aims to explore better pre-training practices for respiratory sounds by comparing numerous pre-trained audio models. Our investigation reveals that models pre-trained on AudioSet, a general audio dataset, are more effective than the models specifically pre-trained on respiratory sounds. Moreover, combining AudioSet and resp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15307","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/2505.15307/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":"2505.15307","created_at":"2026-07-05T11:06:43.529365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15307v1","created_at":"2026-07-05T11:06:43.529365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15307","created_at":"2026-07-05T11:06:43.529365+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4V7RKFJWJY5","created_at":"2026-07-05T11:06:43.529365+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4V7RKFJWJY5UXPO","created_at":"2026-07-05T11:06:43.529365+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4V7RKFJ","created_at":"2026-07-05T11:06:43.529365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21411","citing_title":"CoughPhase-CLR: Designing an acoustics-informed foundation model for coughing sound classification","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4V7RKFJWJY5UXPOZK3M44KPXV","json":"https://pith.science/pith/W4V7RKFJWJY5UXPOZK3M44KPXV.json","graph_json":"https://pith.science/api/pith-number/W4V7RKFJWJY5UXPOZK3M44KPXV/graph.json","events_json":"https://pith.science/api/pith-number/W4V7RKFJWJY5UXPOZK3M44KPXV/events.json","paper":"https://pith.science/paper/W4V7RKFJ"},"agent_actions":{"view_html":"https://pith.science/pith/W4V7RKFJWJY5UXPOZK3M44KPXV","download_json":"https://pith.science/pith/W4V7RKFJWJY5UXPOZK3M44KPXV.json","view_paper":"https://pith.science/paper/W4V7RKFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15307&json=true","fetch_graph":"https://pith.science/api/pith-number/W4V7RKFJWJY5UXPOZK3M44KPXV/graph.json","fetch_events":"https://pith.science/api/pith-number/W4V7RKFJWJY5UXPOZK3M44KPXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4V7RKFJWJY5UXPOZK3M44KPXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4V7RKFJWJY5UXPOZK3M44KPXV/action/storage_attestation","attest_author":"https://pith.science/pith/W4V7RKFJWJY5UXPOZK3M44KPXV/action/author_attestation","sign_citation":"https://pith.science/pith/W4V7RKFJWJY5UXPOZK3M44KPXV/action/citation_signature","submit_replication":"https://pith.science/pith/W4V7RKFJWJY5UXPOZK3M44KPXV/action/replication_record"}},"created_at":"2026-07-05T11:06:43.529365+00:00","updated_at":"2026-07-05T11:06:43.529365+00:00"}