{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:56JM66TSAHIQDZDOQ5462BMYQZ","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":"aa3081661e3405abe7e8371784aed3c31126b1ef7738d72769485b84145899f5","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T03:50:19Z","title_canon_sha256":"8b2f8d08dedd9ca60580dd00fda6c109146206809f1b4a22914b09bd8385c461"},"schema_version":"1.0","source":{"id":"2111.00400","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00400","created_at":"2026-07-05T03:27:42Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00400v1","created_at":"2026-07-05T03:27:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00400","created_at":"2026-07-05T03:27:42Z"},{"alias_kind":"pith_short_12","alias_value":"56JM66TSAHIQ","created_at":"2026-07-05T03:27:42Z"},{"alias_kind":"pith_short_16","alias_value":"56JM66TSAHIQDZDO","created_at":"2026-07-05T03:27:42Z"},{"alias_kind":"pith_short_8","alias_value":"56JM66TS","created_at":"2026-07-05T03:27:42Z"}],"graph_snapshots":[{"event_id":"sha256:92fdae8d782d738b72a55a4d8edff768af03a4448ac2d2daea93010a3d1fef50","target":"graph","created_at":"2026-07-05T03:27:42Z","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/2111.00400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken language understanding (SLU) systems translate voice input commands to semantics which are encoded as an intent and pairs of slot tags and values. Most current SLU systems deploy a cascade of two neural models where the first one maps the input audio to a transcript (ASR) and the second predicts the intent and slots from the transcript (NLU). In this paper, we introduce FANS, a new end-to-end SLU model that fuses an ASR audio encoder to a multi-task NLU decoder to infer the intent, slot tags, and slot values directly from a given input audio, obviating the need for transcription. FANS c","authors_text":"Ariya Rastrow, Athanasios Mouchtaris, Martin Radfar, Siegfried Kunzmann","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T03:50:19Z","title":"FANS: Fusing ASR and NLU for on-device SLU"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00400","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":"sha256:79080ae535d50c0c6501746406564586dcf1595c148dc8526f15cb4279953488","target":"record","created_at":"2026-07-05T03:27:42Z","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":"aa3081661e3405abe7e8371784aed3c31126b1ef7738d72769485b84145899f5","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-31T03:50:19Z","title_canon_sha256":"8b2f8d08dedd9ca60580dd00fda6c109146206809f1b4a22914b09bd8385c461"},"schema_version":"1.0","source":{"id":"2111.00400","kind":"arxiv","version":1}},"canonical_sha256":"ef92cf7a7201d101e46e8779ed0598867ab3f47ee7750c8164783bb0773d561b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef92cf7a7201d101e46e8779ed0598867ab3f47ee7750c8164783bb0773d561b","first_computed_at":"2026-07-05T03:27:42.288060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:42.288060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lYYH149f1RgEr/S34nCWIdjhpzoGdLf34JEiWZllZ4kL2kwkF6PJNQLXFVIRQ5qw4LQaq0RA9Y004oAVYRV6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:42.288561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.00400","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79080ae535d50c0c6501746406564586dcf1595c148dc8526f15cb4279953488","sha256:92fdae8d782d738b72a55a4d8edff768af03a4448ac2d2daea93010a3d1fef50"],"state_sha256":"0515fd260332b3087c540bbc99a41445bf121778d3b6ae03b9aadac163c6d240"}