{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GQBNEOSDJNSY57CF7UQO4IORVK","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":"bce30fa1febb7e1f9da398f22abc21ffdb6108a5caca7068ae257f37a3dc4767","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-09-23T02:39:59Z","title_canon_sha256":"6750bd8fee46bdeda51e548098ef2352d7a04b3fe5a08eb251196d464800bf8c"},"schema_version":"1.0","source":{"id":"2209.11377","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.11377","created_at":"2026-07-05T05:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2209.11377v1","created_at":"2026-07-05T05:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11377","created_at":"2026-07-05T05:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"GQBNEOSDJNSY","created_at":"2026-07-05T05:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"GQBNEOSDJNSY57CF","created_at":"2026-07-05T05:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"GQBNEOSD","created_at":"2026-07-05T05:00:19Z"}],"graph_snapshots":[{"event_id":"sha256:eb62f45cae8dcc33ec3fc178f0d7f566809ca8ad4c18063d9e277fd13120ffb6","target":"graph","created_at":"2026-07-05T05:00:19Z","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/2209.11377/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Within the audio research community and the industry, keyword spotting (KWS) and audio tagging (AT) are seen as two distinct tasks and research fields. However, from a technical point of view, both of these tasks are identical: they predict a label (keyword in KWS, sound event in AT) for some fixed-sized input audio segment. This work proposes UniKW-AT: An initial approach for jointly training both KWS and AT. UniKW-AT enhances the noise-robustness for KWS, while also being able to predict specific sound events and enabling conditional wake-ups on sound events. Our approach extends the AT pipe","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":"2022-09-23T02:39:59Z","title":"UniKW-AT: Unified Keyword Spotting and Audio Tagging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11377","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":"sha256:7d37f84132f331d9819d9293a2f43fd53439080dd3e6e0b4858061ffae0649b1","target":"record","created_at":"2026-07-05T05:00:19Z","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":"bce30fa1febb7e1f9da398f22abc21ffdb6108a5caca7068ae257f37a3dc4767","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-09-23T02:39:59Z","title_canon_sha256":"6750bd8fee46bdeda51e548098ef2352d7a04b3fe5a08eb251196d464800bf8c"},"schema_version":"1.0","source":{"id":"2209.11377","kind":"arxiv","version":1}},"canonical_sha256":"3402d23a434b658efc45fd20ee21d1aa914c6e0b13a5e77716c5e8868c15626f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3402d23a434b658efc45fd20ee21d1aa914c6e0b13a5e77716c5e8868c15626f","first_computed_at":"2026-07-05T05:00:19.858118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:00:19.858118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ot0jxc0JbVElA0qDdcc18Cdgw7F6HW1iw0nkYYwG4CMnkqNh28hhKEfFQBkfaH2PUQI2biUHWRp5fsm7MIPSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:00:19.858502Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.11377","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d37f84132f331d9819d9293a2f43fd53439080dd3e6e0b4858061ffae0649b1","sha256:eb62f45cae8dcc33ec3fc178f0d7f566809ca8ad4c18063d9e277fd13120ffb6"],"state_sha256":"03f09fa3357bb06bc93ec030d319bf7c0d66eb47a1e2c040c1e997237776c318"}