{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DD3ZJQODU74LP4WZVSJPIA27JG","short_pith_number":"pith:DD3ZJQOD","schema_version":"1.0","canonical_sha256":"18f794c1c3a7f8b7f2d9ac92f4035f49b55fdb5d9aaade9ec872da2a2e5663b4","source":{"kind":"arxiv","id":"2310.03889","version":1},"attestation_state":"computed","paper":{"title":"Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chuang Yu, Dick Botteldooren, Siyang Song, Wenwu Wang, Yuanbo Hou","submitted_at":"2023-10-05T20:48:59Z","abstract_excerpt":"Most deep learning-based acoustic scene classification (ASC) approaches identify scenes based on acoustic features converted from audio clips containing mixed information entangled by polyphonic audio events (AEs). However, these approaches have difficulties in explaining what cues they use to identify scenes. This paper conducts the first study on disclosing the relationship between real-life acoustic scenes and semantic embeddings from the most relevant AEs. Specifically, we propose an event-relational graph representation learning (ERGL) framework for ASC to classify scenes, and simultaneou"},"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":"2310.03889","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-05T20:48:59Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"90ef01cff317ddbf742f02b7f3d4d1a3f15523c78dfcab14a46338fafb3dd8bb","abstract_canon_sha256":"1cc44802ae5483e77420ac4c3b1b53f04778ce730662369f256228edba4c742a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:42.276818Z","signature_b64":"usHIIJysu74IUDcsX/dMoFUn3D7txO9ENCxMs6RgxFKe6y7iIFf54Gqj7LO1s2y1cxgygsdz65hcccbfYlkoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18f794c1c3a7f8b7f2d9ac92f4035f49b55fdb5d9aaade9ec872da2a2e5663b4","last_reissued_at":"2026-07-05T06:57:42.276366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:42.276366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chuang Yu, Dick Botteldooren, Siyang Song, Wenwu Wang, Yuanbo Hou","submitted_at":"2023-10-05T20:48:59Z","abstract_excerpt":"Most deep learning-based acoustic scene classification (ASC) approaches identify scenes based on acoustic features converted from audio clips containing mixed information entangled by polyphonic audio events (AEs). However, these approaches have difficulties in explaining what cues they use to identify scenes. This paper conducts the first study on disclosing the relationship between real-life acoustic scenes and semantic embeddings from the most relevant AEs. Specifically, we propose an event-relational graph representation learning (ERGL) framework for ASC to classify scenes, and simultaneou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03889","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/2310.03889/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":"2310.03889","created_at":"2026-07-05T06:57:42.276439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03889v1","created_at":"2026-07-05T06:57:42.276439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03889","created_at":"2026-07-05T06:57:42.276439+00:00"},{"alias_kind":"pith_short_12","alias_value":"DD3ZJQODU74L","created_at":"2026-07-05T06:57:42.276439+00:00"},{"alias_kind":"pith_short_16","alias_value":"DD3ZJQODU74LP4WZ","created_at":"2026-07-05T06:57:42.276439+00:00"},{"alias_kind":"pith_short_8","alias_value":"DD3ZJQOD","created_at":"2026-07-05T06:57:42.276439+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/DD3ZJQODU74LP4WZVSJPIA27JG","json":"https://pith.science/pith/DD3ZJQODU74LP4WZVSJPIA27JG.json","graph_json":"https://pith.science/api/pith-number/DD3ZJQODU74LP4WZVSJPIA27JG/graph.json","events_json":"https://pith.science/api/pith-number/DD3ZJQODU74LP4WZVSJPIA27JG/events.json","paper":"https://pith.science/paper/DD3ZJQOD"},"agent_actions":{"view_html":"https://pith.science/pith/DD3ZJQODU74LP4WZVSJPIA27JG","download_json":"https://pith.science/pith/DD3ZJQODU74LP4WZVSJPIA27JG.json","view_paper":"https://pith.science/paper/DD3ZJQOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03889&json=true","fetch_graph":"https://pith.science/api/pith-number/DD3ZJQODU74LP4WZVSJPIA27JG/graph.json","fetch_events":"https://pith.science/api/pith-number/DD3ZJQODU74LP4WZVSJPIA27JG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DD3ZJQODU74LP4WZVSJPIA27JG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DD3ZJQODU74LP4WZVSJPIA27JG/action/storage_attestation","attest_author":"https://pith.science/pith/DD3ZJQODU74LP4WZVSJPIA27JG/action/author_attestation","sign_citation":"https://pith.science/pith/DD3ZJQODU74LP4WZVSJPIA27JG/action/citation_signature","submit_replication":"https://pith.science/pith/DD3ZJQODU74LP4WZVSJPIA27JG/action/replication_record"}},"created_at":"2026-07-05T06:57:42.276439+00:00","updated_at":"2026-07-05T06:57:42.276439+00:00"}