{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TKB66VXGT4H7FE3BGDUK36OJLZ","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":"80b2b9701f2fc41fa068d2050ca4961a8084b631ad2501137d33e224251f6037","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T00:06:32Z","title_canon_sha256":"2f5ef69cda06d9ab56e770b22df3e7cf0b44677e53c36d1e4d5ee99e57d6ff18"},"schema_version":"1.0","source":{"id":"2310.09988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09988","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09988v1","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09988","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"pith_short_12","alias_value":"TKB66VXGT4H7","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"pith_short_16","alias_value":"TKB66VXGT4H7FE3B","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"pith_short_8","alias_value":"TKB66VXG","created_at":"2026-07-05T07:01:13Z"}],"graph_snapshots":[{"event_id":"sha256:c705d578980b363c8b19b858a3d7599ed1c0ebda18433a3717330ff1124b08e8","target":"graph","created_at":"2026-07-05T07:01:13Z","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/2310.09988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in deep learning and automatic speech recognition have improved the accuracy of end-to-end speech recognition systems, but recognition of personal content such as contact names remains a challenge. In this work, we describe our personalization solution for an end-to-end speech recognition system based on connectionist temporal classification. Building on previous work, we present a novel method for generating additional subword tokenizations for personal entities from their pronunciations. We show that using this technique in combination with two established techniques, context","authors_text":"Ernest Pusateri, Leo Liu, Man-Hung Siu, Mingbin Xu, Mirko Hannemann, Ruchir Travadi, Shiyi Han, Tim Ng, Youyuan Zhang, Zhen Huang, Zhihong Lei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T00:06:32Z","title":"Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09988","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":"sha256:2c4e18e750b1950a03b71731ccc9bbf12832fc91a1c922e12cff9c2ac7908b94","target":"record","created_at":"2026-07-05T07:01:13Z","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":"80b2b9701f2fc41fa068d2050ca4961a8084b631ad2501137d33e224251f6037","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T00:06:32Z","title_canon_sha256":"2f5ef69cda06d9ab56e770b22df3e7cf0b44677e53c36d1e4d5ee99e57d6ff18"},"schema_version":"1.0","source":{"id":"2310.09988","kind":"arxiv","version":1}},"canonical_sha256":"9a83ef56e69f0ff2936130e8adf9c95e6fc355d81a847382280506d0cba3e8f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a83ef56e69f0ff2936130e8adf9c95e6fc355d81a847382280506d0cba3e8f5","first_computed_at":"2026-07-05T07:01:13.432170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:13.432170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VgvJbRZTqKUsBJPhwRgH/lHYat3f/PGSc4LzVuc2539J36otJw5NmL5JjRJ7RLf+87xFk+duDPlbo3gB21kaAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:13.432580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.09988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c4e18e750b1950a03b71731ccc9bbf12832fc91a1c922e12cff9c2ac7908b94","sha256:c705d578980b363c8b19b858a3d7599ed1c0ebda18433a3717330ff1124b08e8"],"state_sha256":"c7b2ee8cbe55fdc2f49fbaf5aa51ebaa68c1341829882b02cc17e1e305843036"}