{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MBI7MWXX3JBMPXNXN2V5FOOJEI","short_pith_number":"pith:MBI7MWXX","schema_version":"1.0","canonical_sha256":"6051f65af7da42c7ddb76eabd2b9c9220b9007429f58d3ad870f7217eaee7678","source":{"kind":"arxiv","id":"2403.10380","version":6},"attestation_state":"computed","paper":{"title":"BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bernhard Sick, Christoph Scholz, Denis Huseljic, Jonas Lange, Lukas Rauch, Marek Herde, Moritz Wirth, Raphael Schwinger, Ren\\'e Heinrich, Stefan Kahl, Sven Tomforde","submitted_at":"2024-03-15T15:10:40Z","abstract_excerpt":"Deep learning (DL) has greatly advanced audio classification, yet the field is limited by the scarcity of large-scale benchmark datasets that have propelled progress in other domains. While AudioSet is a pivotal step to bridge this gap as a universal-domain dataset, its restricted accessibility and limited range of evaluation use cases challenge its role as the sole resource. Therefore, we introduce BirdSet, a large-scale benchmark dataset for audio classification focusing on avian bioacoustics. BirdSet surpasses AudioSet with over 6,800 recording hours ($\\uparrow\\!17\\%$) from nearly 10,000 cl"},"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":"2403.10380","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-15T15:10:40Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"97e3b37560ffea971b58fe73528b61fd165b87dd686f28a73faceb3e86cad5da","abstract_canon_sha256":"d7d13255e3a91c5a57854f27ee91836aff4f1d46f22c7d49db09a00f5f58266f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:36.232614Z","signature_b64":"EFKqI6BbFkxQeoz+TlGP1bXltWme4bpv01kHS+0g0odUURqc2MEZjNeb5ovxeIMUTfUwo+2s4KDDWjTlnDQ8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6051f65af7da42c7ddb76eabd2b9c9220b9007429f58d3ad870f7217eaee7678","last_reissued_at":"2026-07-05T11:04:36.232120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:36.232120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bernhard Sick, Christoph Scholz, Denis Huseljic, Jonas Lange, Lukas Rauch, Marek Herde, Moritz Wirth, Raphael Schwinger, Ren\\'e Heinrich, Stefan Kahl, Sven Tomforde","submitted_at":"2024-03-15T15:10:40Z","abstract_excerpt":"Deep learning (DL) has greatly advanced audio classification, yet the field is limited by the scarcity of large-scale benchmark datasets that have propelled progress in other domains. While AudioSet is a pivotal step to bridge this gap as a universal-domain dataset, its restricted accessibility and limited range of evaluation use cases challenge its role as the sole resource. Therefore, we introduce BirdSet, a large-scale benchmark dataset for audio classification focusing on avian bioacoustics. BirdSet surpasses AudioSet with over 6,800 recording hours ($\\uparrow\\!17\\%$) from nearly 10,000 cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10380","kind":"arxiv","version":6},"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/2403.10380/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":"2403.10380","created_at":"2026-07-05T11:04:36.232187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10380v6","created_at":"2026-07-05T11:04:36.232187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10380","created_at":"2026-07-05T11:04:36.232187+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBI7MWXX3JBM","created_at":"2026-07-05T11:04:36.232187+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBI7MWXX3JBMPXNX","created_at":"2026-07-05T11:04:36.232187+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBI7MWXX","created_at":"2026-07-05T11:04:36.232187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10407","citing_title":"Time-frequency localization of bird calls in dense soundscapes","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03821","citing_title":"Finding Needles in the Haystack: Transductive Active Labeling in Ecology","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03821","citing_title":"Finding Needles in the Haystack: Transductive Active Labeling in Ecology","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03914","citing_title":"Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBI7MWXX3JBMPXNXN2V5FOOJEI","json":"https://pith.science/pith/MBI7MWXX3JBMPXNXN2V5FOOJEI.json","graph_json":"https://pith.science/api/pith-number/MBI7MWXX3JBMPXNXN2V5FOOJEI/graph.json","events_json":"https://pith.science/api/pith-number/MBI7MWXX3JBMPXNXN2V5FOOJEI/events.json","paper":"https://pith.science/paper/MBI7MWXX"},"agent_actions":{"view_html":"https://pith.science/pith/MBI7MWXX3JBMPXNXN2V5FOOJEI","download_json":"https://pith.science/pith/MBI7MWXX3JBMPXNXN2V5FOOJEI.json","view_paper":"https://pith.science/paper/MBI7MWXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10380&json=true","fetch_graph":"https://pith.science/api/pith-number/MBI7MWXX3JBMPXNXN2V5FOOJEI/graph.json","fetch_events":"https://pith.science/api/pith-number/MBI7MWXX3JBMPXNXN2V5FOOJEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBI7MWXX3JBMPXNXN2V5FOOJEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBI7MWXX3JBMPXNXN2V5FOOJEI/action/storage_attestation","attest_author":"https://pith.science/pith/MBI7MWXX3JBMPXNXN2V5FOOJEI/action/author_attestation","sign_citation":"https://pith.science/pith/MBI7MWXX3JBMPXNXN2V5FOOJEI/action/citation_signature","submit_replication":"https://pith.science/pith/MBI7MWXX3JBMPXNXN2V5FOOJEI/action/replication_record"}},"created_at":"2026-07-05T11:04:36.232187+00:00","updated_at":"2026-07-05T11:04:36.232187+00:00"}