{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XEOMZNN3ZMOYFKWNFQESDW55VP","short_pith_number":"pith:XEOMZNN3","schema_version":"1.0","canonical_sha256":"b91cccb5bbcb1d82aacd2c0921dbbdabfadca38f60d306eff6bbda5d3005585b","source":{"kind":"arxiv","id":"2110.09600","version":1},"attestation_state":"computed","paper":{"title":"Who calls the shots? Rethinking Few-Shot Learning for Audio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Juan Pablo Bello, Justin Salamon, Mark Cartwright, Nicholas J. Bryan, Yu Wang","submitted_at":"2021-10-18T19:47:15Z","abstract_excerpt":"Few-shot learning aims to train models that can recognize novel classes given just a handful of labeled examples, known as the support set. While the field has seen notable advances in recent years, they have often focused on multi-class image classification. Audio, in contrast, is often multi-label due to overlapping sounds, resulting in unique properties such as polyphony and signal-to-noise ratios (SNR). This leads to unanswered questions concerning the impact such audio properties may have on few-shot learning system design, performance, and human-computer interaction, as it is typically u"},"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":"2110.09600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-18T19:47:15Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"921faef0a8555d681c84211d717fd55170005c4d1026bb5f6854e25bab4b6c38","abstract_canon_sha256":"0e302a871c4c27638728d04feeef9d9b56b610f1a28f0b1dfad807c515bdeae5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:30.840255Z","signature_b64":"NyU8nvV93gU6tV36iFAy3H7ULsbnuOSoQA8+t1HwefxZ+s3IuFxyWCYL7uoP9t9aeqIJrXW0smUDB9/q6jFbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b91cccb5bbcb1d82aacd2c0921dbbdabfadca38f60d306eff6bbda5d3005585b","last_reissued_at":"2026-07-05T03:23:30.839784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:30.839784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Who calls the shots? Rethinking Few-Shot Learning for Audio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Juan Pablo Bello, Justin Salamon, Mark Cartwright, Nicholas J. Bryan, Yu Wang","submitted_at":"2021-10-18T19:47:15Z","abstract_excerpt":"Few-shot learning aims to train models that can recognize novel classes given just a handful of labeled examples, known as the support set. While the field has seen notable advances in recent years, they have often focused on multi-class image classification. Audio, in contrast, is often multi-label due to overlapping sounds, resulting in unique properties such as polyphony and signal-to-noise ratios (SNR). This leads to unanswered questions concerning the impact such audio properties may have on few-shot learning system design, performance, and human-computer interaction, as it is typically u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09600","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/2110.09600/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":"2110.09600","created_at":"2026-07-05T03:23:30.839838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.09600v1","created_at":"2026-07-05T03:23:30.839838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09600","created_at":"2026-07-05T03:23:30.839838+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEOMZNN3ZMOY","created_at":"2026-07-05T03:23:30.839838+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEOMZNN3ZMOYFKWN","created_at":"2026-07-05T03:23:30.839838+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEOMZNN3","created_at":"2026-07-05T03:23:30.839838+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/XEOMZNN3ZMOYFKWNFQESDW55VP","json":"https://pith.science/pith/XEOMZNN3ZMOYFKWNFQESDW55VP.json","graph_json":"https://pith.science/api/pith-number/XEOMZNN3ZMOYFKWNFQESDW55VP/graph.json","events_json":"https://pith.science/api/pith-number/XEOMZNN3ZMOYFKWNFQESDW55VP/events.json","paper":"https://pith.science/paper/XEOMZNN3"},"agent_actions":{"view_html":"https://pith.science/pith/XEOMZNN3ZMOYFKWNFQESDW55VP","download_json":"https://pith.science/pith/XEOMZNN3ZMOYFKWNFQESDW55VP.json","view_paper":"https://pith.science/paper/XEOMZNN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.09600&json=true","fetch_graph":"https://pith.science/api/pith-number/XEOMZNN3ZMOYFKWNFQESDW55VP/graph.json","fetch_events":"https://pith.science/api/pith-number/XEOMZNN3ZMOYFKWNFQESDW55VP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEOMZNN3ZMOYFKWNFQESDW55VP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEOMZNN3ZMOYFKWNFQESDW55VP/action/storage_attestation","attest_author":"https://pith.science/pith/XEOMZNN3ZMOYFKWNFQESDW55VP/action/author_attestation","sign_citation":"https://pith.science/pith/XEOMZNN3ZMOYFKWNFQESDW55VP/action/citation_signature","submit_replication":"https://pith.science/pith/XEOMZNN3ZMOYFKWNFQESDW55VP/action/replication_record"}},"created_at":"2026-07-05T03:23:30.839838+00:00","updated_at":"2026-07-05T03:23:30.839838+00:00"}