{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HLS5JW6SRGSE4P6NLJVPANQ55X","short_pith_number":"pith:HLS5JW6S","schema_version":"1.0","canonical_sha256":"3ae5d4dbd289a44e3fcd5a6af0361dedd8d9ae0c9dada1ac63f5545996b4337b","source":{"kind":"arxiv","id":"2503.02389","version":2},"attestation_state":"computed","paper":{"title":"Robust detection of overlapping bioacoustic sound events","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Benjamin Hoffman, Felix Effenberger, Jen-Yu Liu, Logan James, Louis Mahon, Maddie Cusimano, Masato Hagiwara, Olivier Pietquin, Sarah C Woolley, Sara Keen","submitted_at":"2025-03-04T08:26:03Z","abstract_excerpt":"We propose a method for accurately detecting bioacoustic sound events that is robust to overlapping events, a common issue in domains such as ethology, ecology and conservation. While standard methods employ a frame-based, multi-label approach, we introduce an onset-based detection method which we name Voxaboxen. It takes inspiration from object detection methods in computer vision, but simultaneously takes advantage of recent advances in self-supervised audio encoders. For each time window, Voxaboxen predicts whether it contains the start of a vocalization and how long the vocalization is. It"},"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":"2503.02389","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-04T08:26:03Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"8b0fa0f9fde3097bb608598fe35cd2ef24f7721f80aed06667ecc43f6a3e7ed1","abstract_canon_sha256":"db267dace9eb69a185c4f08eb5f46404ae15bec70e90b7bd3d76adcc43976e0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:41.337655Z","signature_b64":"3hAh2E8JdmjCZqWfnsSIuSSXENfzlhfeQl1KKuERDZAFQKWrLtPzcG3PSymUYjBloqc+haeE+nDemr4Ytq2rDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ae5d4dbd289a44e3fcd5a6af0361dedd8d9ae0c9dada1ac63f5545996b4337b","last_reissued_at":"2026-07-05T12:05:41.337078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:41.337078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust detection of overlapping bioacoustic sound events","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Benjamin Hoffman, Felix Effenberger, Jen-Yu Liu, Logan James, Louis Mahon, Maddie Cusimano, Masato Hagiwara, Olivier Pietquin, Sarah C Woolley, Sara Keen","submitted_at":"2025-03-04T08:26:03Z","abstract_excerpt":"We propose a method for accurately detecting bioacoustic sound events that is robust to overlapping events, a common issue in domains such as ethology, ecology and conservation. While standard methods employ a frame-based, multi-label approach, we introduce an onset-based detection method which we name Voxaboxen. It takes inspiration from object detection methods in computer vision, but simultaneously takes advantage of recent advances in self-supervised audio encoders. For each time window, Voxaboxen predicts whether it contains the start of a vocalization and how long the vocalization is. It"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02389","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/2503.02389/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":"2503.02389","created_at":"2026-07-05T12:05:41.337138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02389v2","created_at":"2026-07-05T12:05:41.337138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02389","created_at":"2026-07-05T12:05:41.337138+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLS5JW6SRGSE","created_at":"2026-07-05T12:05:41.337138+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLS5JW6SRGSE4P6N","created_at":"2026-07-05T12:05:41.337138+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLS5JW6S","created_at":"2026-07-05T12:05:41.337138+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.11845","citing_title":"AVEX: What Matters for Animal Vocalization Encoding","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10494","citing_title":"Multi-layer attentive probing improves transfer of audio representations for bioacoustics","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLS5JW6SRGSE4P6NLJVPANQ55X","json":"https://pith.science/pith/HLS5JW6SRGSE4P6NLJVPANQ55X.json","graph_json":"https://pith.science/api/pith-number/HLS5JW6SRGSE4P6NLJVPANQ55X/graph.json","events_json":"https://pith.science/api/pith-number/HLS5JW6SRGSE4P6NLJVPANQ55X/events.json","paper":"https://pith.science/paper/HLS5JW6S"},"agent_actions":{"view_html":"https://pith.science/pith/HLS5JW6SRGSE4P6NLJVPANQ55X","download_json":"https://pith.science/pith/HLS5JW6SRGSE4P6NLJVPANQ55X.json","view_paper":"https://pith.science/paper/HLS5JW6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02389&json=true","fetch_graph":"https://pith.science/api/pith-number/HLS5JW6SRGSE4P6NLJVPANQ55X/graph.json","fetch_events":"https://pith.science/api/pith-number/HLS5JW6SRGSE4P6NLJVPANQ55X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLS5JW6SRGSE4P6NLJVPANQ55X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLS5JW6SRGSE4P6NLJVPANQ55X/action/storage_attestation","attest_author":"https://pith.science/pith/HLS5JW6SRGSE4P6NLJVPANQ55X/action/author_attestation","sign_citation":"https://pith.science/pith/HLS5JW6SRGSE4P6NLJVPANQ55X/action/citation_signature","submit_replication":"https://pith.science/pith/HLS5JW6SRGSE4P6NLJVPANQ55X/action/replication_record"}},"created_at":"2026-07-05T12:05:41.337138+00:00","updated_at":"2026-07-05T12:05:41.337138+00:00"}