{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4JA5AFNMIT7IGA7FKGNIYMUXJX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e2d323b421e004c487dd967639f5dc790d23035c94e5b53a4a97a2b5b08a99c3","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-09-30T01:35:36Z","title_canon_sha256":"5fdec76c20e5840a0be7a261441686541fd0445064ca27b8f75c555e01d656fb"},"schema_version":"1.0","source":{"id":"2209.15167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15167","created_at":"2026-07-05T05:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15167v1","created_at":"2026-07-05T05:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15167","created_at":"2026-07-05T05:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"4JA5AFNMIT7I","created_at":"2026-07-05T05:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"4JA5AFNMIT7IGA7F","created_at":"2026-07-05T05:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"4JA5AFNM","created_at":"2026-07-05T05:02:16Z"}],"graph_snapshots":[{"event_id":"sha256:02bfcf0df1710b925e25a6517c3de22d0c79c4e0b1c22dbd05d0b87f5019fe7a","target":"graph","created_at":"2026-07-05T05:02:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.15167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the usability of pre-trained weakly supervised audio tagging (AT) models as feature extractors for general audio representations. We mainly analyze the feasibility of transferring those embeddings to other tasks within the speech and sound domains. Specifically, we benchmark weakly supervised pre-trained models (MobileNetV2 and EfficientNet-B0) against modern self-supervised learning methods (BYOL-A) as feature extractors. Fourteen downstream tasks are used for evaluation ranging from music instrument classification to language classification. Our results indicate that AT pre-trained ","authors_text":"Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-09-30T01:35:36Z","title":"An empirical study of weakly supervised audio tagging embeddings for general audio representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15167","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:47a01b97201d597c7c5b6cb113b3cdb9c688093984c7bd3483335f5efb278852","target":"record","created_at":"2026-07-05T05:02:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e2d323b421e004c487dd967639f5dc790d23035c94e5b53a4a97a2b5b08a99c3","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-09-30T01:35:36Z","title_canon_sha256":"5fdec76c20e5840a0be7a261441686541fd0445064ca27b8f75c555e01d656fb"},"schema_version":"1.0","source":{"id":"2209.15167","kind":"arxiv","version":1}},"canonical_sha256":"e241d015ac44fe8303e5519a8c32974dd7edc985350f55732a26f2b35c0125a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e241d015ac44fe8303e5519a8c32974dd7edc985350f55732a26f2b35c0125a6","first_computed_at":"2026-07-05T05:02:16.903304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:16.903304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6A7D0tp82SLpojhvTL9FS3r6Mv4HiwgWklFl0nLDOYi/PgKESBPHxOpHJH28NlvAjdMBvlsSad80YwCQtFOTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:16.903798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47a01b97201d597c7c5b6cb113b3cdb9c688093984c7bd3483335f5efb278852","sha256:02bfcf0df1710b925e25a6517c3de22d0c79c4e0b1c22dbd05d0b87f5019fe7a"],"state_sha256":"731ddf6a06717d29853d96899922b1a3187e92efdab41becbbb5c1206bf23240"}