{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F2C7SEG3VABAN3OIDZIRRMIKAF","short_pith_number":"pith:F2C7SEG3","schema_version":"1.0","canonical_sha256":"2e85f910dba80206edc81e5118b10a016baac75b628d36e3829b4651977eb46e","source":{"kind":"arxiv","id":"2504.18650","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised outlier detection to improve bird audio dataset labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Bruce Collins","submitted_at":"2025-04-25T19:04:40Z","abstract_excerpt":"The Xeno-Canto bird audio repository is an invaluable resource for those interested in vocalizations and other sounds made by birds around the world. This is particularly the case for machine learning researchers attempting to improve on the bird species recognition accuracy of classification models. However, the task of extracting labeled datasets from the recordings found in this crowd-sourced repository faces several challenges. One challenge of particular significance to machine learning practitioners is that one bird species label is applied to each audio recording, but frequently other s"},"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":"2504.18650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-25T19:04:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b2eab85152d1a7aacd4a7d2d18ab0cc6e6f23f4bc6296b2f04fcfbf734034b5a","abstract_canon_sha256":"798045b0095846cb2b7ca21b1b2358474806518b8ea211d5b61f4031f4f83cbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:18.432871Z","signature_b64":"nwooJLUUxFQWU/RYMaHsE6Fmeqp3vPMSRB9UA7SXtcfkDS9GRXgWpp4hUcKA1gRF1GjkThFjku/bJtbvwWCGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e85f910dba80206edc81e5118b10a016baac75b628d36e3829b4651977eb46e","last_reissued_at":"2026-07-05T10:54:18.432395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:18.432395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised outlier detection to improve bird audio dataset labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Bruce Collins","submitted_at":"2025-04-25T19:04:40Z","abstract_excerpt":"The Xeno-Canto bird audio repository is an invaluable resource for those interested in vocalizations and other sounds made by birds around the world. This is particularly the case for machine learning researchers attempting to improve on the bird species recognition accuracy of classification models. However, the task of extracting labeled datasets from the recordings found in this crowd-sourced repository faces several challenges. One challenge of particular significance to machine learning practitioners is that one bird species label is applied to each audio recording, but frequently other s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18650","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/2504.18650/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":"2504.18650","created_at":"2026-07-05T10:54:18.432455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18650v1","created_at":"2026-07-05T10:54:18.432455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18650","created_at":"2026-07-05T10:54:18.432455+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2C7SEG3VABA","created_at":"2026-07-05T10:54:18.432455+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2C7SEG3VABAN3OI","created_at":"2026-07-05T10:54:18.432455+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2C7SEG3","created_at":"2026-07-05T10:54:18.432455+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/F2C7SEG3VABAN3OIDZIRRMIKAF","json":"https://pith.science/pith/F2C7SEG3VABAN3OIDZIRRMIKAF.json","graph_json":"https://pith.science/api/pith-number/F2C7SEG3VABAN3OIDZIRRMIKAF/graph.json","events_json":"https://pith.science/api/pith-number/F2C7SEG3VABAN3OIDZIRRMIKAF/events.json","paper":"https://pith.science/paper/F2C7SEG3"},"agent_actions":{"view_html":"https://pith.science/pith/F2C7SEG3VABAN3OIDZIRRMIKAF","download_json":"https://pith.science/pith/F2C7SEG3VABAN3OIDZIRRMIKAF.json","view_paper":"https://pith.science/paper/F2C7SEG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18650&json=true","fetch_graph":"https://pith.science/api/pith-number/F2C7SEG3VABAN3OIDZIRRMIKAF/graph.json","fetch_events":"https://pith.science/api/pith-number/F2C7SEG3VABAN3OIDZIRRMIKAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2C7SEG3VABAN3OIDZIRRMIKAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2C7SEG3VABAN3OIDZIRRMIKAF/action/storage_attestation","attest_author":"https://pith.science/pith/F2C7SEG3VABAN3OIDZIRRMIKAF/action/author_attestation","sign_citation":"https://pith.science/pith/F2C7SEG3VABAN3OIDZIRRMIKAF/action/citation_signature","submit_replication":"https://pith.science/pith/F2C7SEG3VABAN3OIDZIRRMIKAF/action/replication_record"}},"created_at":"2026-07-05T10:54:18.432455+00:00","updated_at":"2026-07-05T10:54:18.432455+00:00"}