{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S7HLSPC24XLO57HHPQUMLUEWHV","short_pith_number":"pith:S7HLSPC2","schema_version":"1.0","canonical_sha256":"97ceb93c5ae5d6eefce77c28c5d0963d4e6b2d316794faedb84d2fee37146f72","source":{"kind":"arxiv","id":"2409.06580","version":1},"attestation_state":"computed","paper":{"title":"Exploring Differences between Human Perception and Model Inference in Audio Event Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dick Botteldooren, Hui Bu, Mark D. Plumbley, Shengchen Li, Xin Xu, Yanru Wu, Yizhou Tan, Yuanbo Hou","submitted_at":"2024-09-10T15:19:50Z","abstract_excerpt":"Audio Event Recognition (AER) traditionally focuses on detecting and identifying audio events. Most existing AER models tend to detect all potential events without considering their varying significance across different contexts. This makes the AER results detected by existing models often have a large discrepancy with human auditory perception. Although this is a critical and significant issue, it has not been extensively studied by the Detection and Classification of Sound Scenes and Events (DCASE) community because solving it is time-consuming and labour-intensive. To address this issue, th"},"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":"2409.06580","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-10T15:19:50Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"27f40dc75a417c90df127da076402af2bc45b9e03bf799182a5f788569eeb0c2","abstract_canon_sha256":"1e24fdd662222f6f7a34ba1a749719dfd6f5d9c2bcad9e6bb7890956b676bd14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:26.622489Z","signature_b64":"3Yu+jXepjhNT+jAJk9dxVFuGaLxDZctI3NNnlMnLmWMbd1tw07q1xZ5GtE7XyyEeri52Fg7ojcVTMU/rcP1LAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97ceb93c5ae5d6eefce77c28c5d0963d4e6b2d316794faedb84d2fee37146f72","last_reissued_at":"2026-07-05T09:05:26.622095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:26.622095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Differences between Human Perception and Model Inference in Audio Event Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dick Botteldooren, Hui Bu, Mark D. Plumbley, Shengchen Li, Xin Xu, Yanru Wu, Yizhou Tan, Yuanbo Hou","submitted_at":"2024-09-10T15:19:50Z","abstract_excerpt":"Audio Event Recognition (AER) traditionally focuses on detecting and identifying audio events. Most existing AER models tend to detect all potential events without considering their varying significance across different contexts. This makes the AER results detected by existing models often have a large discrepancy with human auditory perception. Although this is a critical and significant issue, it has not been extensively studied by the Detection and Classification of Sound Scenes and Events (DCASE) community because solving it is time-consuming and labour-intensive. To address this issue, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06580","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/2409.06580/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":"2409.06580","created_at":"2026-07-05T09:05:26.622149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06580v1","created_at":"2026-07-05T09:05:26.622149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06580","created_at":"2026-07-05T09:05:26.622149+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7HLSPC24XLO","created_at":"2026-07-05T09:05:26.622149+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7HLSPC24XLO57HH","created_at":"2026-07-05T09:05:26.622149+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7HLSPC2","created_at":"2026-07-05T09:05:26.622149+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/S7HLSPC24XLO57HHPQUMLUEWHV","json":"https://pith.science/pith/S7HLSPC24XLO57HHPQUMLUEWHV.json","graph_json":"https://pith.science/api/pith-number/S7HLSPC24XLO57HHPQUMLUEWHV/graph.json","events_json":"https://pith.science/api/pith-number/S7HLSPC24XLO57HHPQUMLUEWHV/events.json","paper":"https://pith.science/paper/S7HLSPC2"},"agent_actions":{"view_html":"https://pith.science/pith/S7HLSPC24XLO57HHPQUMLUEWHV","download_json":"https://pith.science/pith/S7HLSPC24XLO57HHPQUMLUEWHV.json","view_paper":"https://pith.science/paper/S7HLSPC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06580&json=true","fetch_graph":"https://pith.science/api/pith-number/S7HLSPC24XLO57HHPQUMLUEWHV/graph.json","fetch_events":"https://pith.science/api/pith-number/S7HLSPC24XLO57HHPQUMLUEWHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7HLSPC24XLO57HHPQUMLUEWHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7HLSPC24XLO57HHPQUMLUEWHV/action/storage_attestation","attest_author":"https://pith.science/pith/S7HLSPC24XLO57HHPQUMLUEWHV/action/author_attestation","sign_citation":"https://pith.science/pith/S7HLSPC24XLO57HHPQUMLUEWHV/action/citation_signature","submit_replication":"https://pith.science/pith/S7HLSPC24XLO57HHPQUMLUEWHV/action/replication_record"}},"created_at":"2026-07-05T09:05:26.622149+00:00","updated_at":"2026-07-05T09:05:26.622149+00:00"}