{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LDOADVJCCED62FCBR6CCSEOH44","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":"3a36ce9b2334a04d37901f46925f322a2e730be7b140694f1686525c55d920d6","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-03-03T09:38:53Z","title_canon_sha256":"83005c86c12e299465f41bf7cff751d6f7092a4a8086c373d1b3f0d7b38b7616"},"schema_version":"1.0","source":{"id":"2303.01812","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01812","created_at":"2026-07-05T05:47:49Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01812v1","created_at":"2026-07-05T05:47:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01812","created_at":"2026-07-05T05:47:49Z"},{"alias_kind":"pith_short_12","alias_value":"LDOADVJCCED6","created_at":"2026-07-05T05:47:49Z"},{"alias_kind":"pith_short_16","alias_value":"LDOADVJCCED62FCB","created_at":"2026-07-05T05:47:49Z"},{"alias_kind":"pith_short_8","alias_value":"LDOADVJC","created_at":"2026-07-05T05:47:49Z"}],"graph_snapshots":[{"event_id":"sha256:0b5f20eb41e065ce516f92134e035ad997c0d1f376f188ce8e1c2de63bcde8ce","target":"graph","created_at":"2026-07-05T05:47:49Z","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/2303.01812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Keyword spotting (KWS) is a core human-machine-interaction front-end task for most modern intelligent assistants. Recently, a unified (UniKW-AT) framework has been proposed that adds additional capabilities in the form of audio tagging (AT) to a KWS model. However, previous work did not consider the real-world deployment of a UniKW-AT model, where factors such as model size and inference speed are more important than performance alone. This work introduces three mobile-device deployable models named Unified Transformers (UiT). Our best model achieves an mAP of 34.09 on Audioset, and an accurac","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":"2023-03-03T09:38:53Z","title":"Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01812","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":"sha256:17b39e9de758ce7473284fa0b02fc874e925f21cd01ca6aaf1fe5cef092e5aee","target":"record","created_at":"2026-07-05T05:47:49Z","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":"3a36ce9b2334a04d37901f46925f322a2e730be7b140694f1686525c55d920d6","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-03-03T09:38:53Z","title_canon_sha256":"83005c86c12e299465f41bf7cff751d6f7092a4a8086c373d1b3f0d7b38b7616"},"schema_version":"1.0","source":{"id":"2303.01812","kind":"arxiv","version":1}},"canonical_sha256":"58dc01d5221107ed14418f842911c7e704b2448cdb10d7a7ab8e4cbf2304fb4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58dc01d5221107ed14418f842911c7e704b2448cdb10d7a7ab8e4cbf2304fb4b","first_computed_at":"2026-07-05T05:47:49.500198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:49.500198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k29uWXPw5AekABsPJ44P+Hn/lcWxvxtBr4b2cAWtyaYgHaMY0c5vUGLjPbYo6kSujZ835SCIslC0gmHie4CLCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:49.500628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.01812","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17b39e9de758ce7473284fa0b02fc874e925f21cd01ca6aaf1fe5cef092e5aee","sha256:0b5f20eb41e065ce516f92134e035ad997c0d1f376f188ce8e1c2de63bcde8ce"],"state_sha256":"fea9429fb34b5b64c967229d99e0b438ba4886673d578b8ae47cbf9d3b8d2a96"}