{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KEPONSLATOJFIW6UXJPLLXVHTV","short_pith_number":"pith:KEPONSLA","schema_version":"1.0","canonical_sha256":"511ee6c9609b92545bd4ba5eb5dea79d524e8acbe73fe0e8616cbface884cee2","source":{"kind":"arxiv","id":"2503.11373","version":2},"attestation_state":"computed","paper":{"title":"Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Schmid, Francesco Foscarin, Gerhard Widmer, Jonathan Greif, Tobias Morocutti","submitted_at":"2025-03-14T13:18:02Z","abstract_excerpt":"We target the problem of developing new low-complexity networks for the sound event detection task. Our goal is to meticulously analyze the performance-complexity trade-off, aiming to be competitive with the large state-of-the-art models, at a fraction of the computational requirements. We find that low-complexity convolutional models previously proposed for audio tagging can be effectively adapted for event detection (which requires frame-wise prediction) by adjusting convolutional strides, removing the global pooling, and, importantly, adding a sequence model before the (now frame-wise) clas"},"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":"2503.11373","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-14T13:18:02Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"1a11b48dc36641bf8e196c7afc88eebeeeeec77cbdf37a0bfc617433362ded47","abstract_canon_sha256":"5ddcafdfe0d95d922b543d8943f1a0fc2b7529b7b7e3dd28fcb397dd59880e3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:10.775688Z","signature_b64":"H6RwKIu3NyuMk3HAwnZGLLwNRm6U7AYgt5vR/lqofWgQGxv0uWmz6XEOwB7AbYpkwNPtC+GH1x2oa252MUpUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"511ee6c9609b92545bd4ba5eb5dea79d524e8acbe73fe0e8616cbface884cee2","last_reissued_at":"2026-07-05T11:20:10.775148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:10.775148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Schmid, Francesco Foscarin, Gerhard Widmer, Jonathan Greif, Tobias Morocutti","submitted_at":"2025-03-14T13:18:02Z","abstract_excerpt":"We target the problem of developing new low-complexity networks for the sound event detection task. Our goal is to meticulously analyze the performance-complexity trade-off, aiming to be competitive with the large state-of-the-art models, at a fraction of the computational requirements. We find that low-complexity convolutional models previously proposed for audio tagging can be effectively adapted for event detection (which requires frame-wise prediction) by adjusting convolutional strides, removing the global pooling, and, importantly, adding a sequence model before the (now frame-wise) clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11373","kind":"arxiv","version":2},"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/2503.11373/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":"2503.11373","created_at":"2026-07-05T11:20:10.775205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11373v2","created_at":"2026-07-05T11:20:10.775205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11373","created_at":"2026-07-05T11:20:10.775205+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEPONSLATOJF","created_at":"2026-07-05T11:20:10.775205+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEPONSLATOJFIW6U","created_at":"2026-07-05T11:20:10.775205+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEPONSLA","created_at":"2026-07-05T11:20:10.775205+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/KEPONSLATOJFIW6UXJPLLXVHTV","json":"https://pith.science/pith/KEPONSLATOJFIW6UXJPLLXVHTV.json","graph_json":"https://pith.science/api/pith-number/KEPONSLATOJFIW6UXJPLLXVHTV/graph.json","events_json":"https://pith.science/api/pith-number/KEPONSLATOJFIW6UXJPLLXVHTV/events.json","paper":"https://pith.science/paper/KEPONSLA"},"agent_actions":{"view_html":"https://pith.science/pith/KEPONSLATOJFIW6UXJPLLXVHTV","download_json":"https://pith.science/pith/KEPONSLATOJFIW6UXJPLLXVHTV.json","view_paper":"https://pith.science/paper/KEPONSLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11373&json=true","fetch_graph":"https://pith.science/api/pith-number/KEPONSLATOJFIW6UXJPLLXVHTV/graph.json","fetch_events":"https://pith.science/api/pith-number/KEPONSLATOJFIW6UXJPLLXVHTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEPONSLATOJFIW6UXJPLLXVHTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEPONSLATOJFIW6UXJPLLXVHTV/action/storage_attestation","attest_author":"https://pith.science/pith/KEPONSLATOJFIW6UXJPLLXVHTV/action/author_attestation","sign_citation":"https://pith.science/pith/KEPONSLATOJFIW6UXJPLLXVHTV/action/citation_signature","submit_replication":"https://pith.science/pith/KEPONSLATOJFIW6UXJPLLXVHTV/action/replication_record"}},"created_at":"2026-07-05T11:20:10.775205+00:00","updated_at":"2026-07-05T11:20:10.775205+00:00"}