{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WBKOWKJ6PDLLVAMHQIHU5F5DIJ","short_pith_number":"pith:WBKOWKJ6","canonical_record":{"source":{"id":"2312.09582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T07:37:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ee73b56959cee70909dd76a1851f94eb55df468bd3585f19f4997c2823b7aeb1","abstract_canon_sha256":"185cee4c17802f9cd4ff7b676e62a006d7cf72ff820fcd7c5e81af289c365429"},"schema_version":"1.0"},"canonical_sha256":"b054eb293e78d6ba8187820f4e97a3425d103183f499535a854432d6b8604105","source":{"kind":"arxiv","id":"2312.09582","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09582","created_at":"2026-07-05T07:24:27Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09582v1","created_at":"2026-07-05T07:24:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09582","created_at":"2026-07-05T07:24:27Z"},{"alias_kind":"pith_short_12","alias_value":"WBKOWKJ6PDLL","created_at":"2026-07-05T07:24:27Z"},{"alias_kind":"pith_short_16","alias_value":"WBKOWKJ6PDLLVAMH","created_at":"2026-07-05T07:24:27Z"},{"alias_kind":"pith_short_8","alias_value":"WBKOWKJ6","created_at":"2026-07-05T07:24:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WBKOWKJ6PDLLVAMHQIHU5F5DIJ","target":"record","payload":{"canonical_record":{"source":{"id":"2312.09582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T07:37:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ee73b56959cee70909dd76a1851f94eb55df468bd3585f19f4997c2823b7aeb1","abstract_canon_sha256":"185cee4c17802f9cd4ff7b676e62a006d7cf72ff820fcd7c5e81af289c365429"},"schema_version":"1.0"},"canonical_sha256":"b054eb293e78d6ba8187820f4e97a3425d103183f499535a854432d6b8604105","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:27.635754Z","signature_b64":"xiRx/7E+bOiTMeEJu4YZEmE1wyYAgVO/kt1MNvD38DsGLTmUU0/rEajFtMJIIJeSjA9aqfqfSsxS4d+mnvDfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b054eb293e78d6ba8187820f4e97a3425d103183f499535a854432d6b8604105","last_reissued_at":"2026-07-05T07:24:27.635151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:27.635151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.09582","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:24:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H1J2IZzVBNPmN3NIk+ujsGGi3PxCZeoUoBk6l/1kTHXhQ7EURqlzQh8qyvfufRG3FswvKV3lf1MjXMJ26VSNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:18:53.965700Z"},"content_sha256":"de89341de1a6174ffe7d93da5629860253c02364949a9482837513494fa093c3","schema_version":"1.0","event_id":"sha256:de89341de1a6174ffe7d93da5629860253c02364949a9482837513494fa093c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WBKOWKJ6PDLLVAMHQIHU5F5DIJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phoneme-aware Encoding for Prefix-tree-based Contextual ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emiru Tsunoo, Hayato Futami, Hiroaki Ogawa, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2023-12-15T07:37:09Z","abstract_excerpt":"In speech recognition applications, it is important to recognize context-specific rare words, such as proper nouns. Tree-constrained Pointer Generator (TCPGen) has shown promise for this purpose, which efficiently biases such words with a prefix tree. While the original TCPGen relies on grapheme-based encoding, we propose extending it with phoneme-aware encoding to better recognize words of unusual pronunciations. As TCPGen handles biasing words as subword units, we propose obtaining subword-level phoneme-aware encoding by using alignment between phonemes and subwords. Furthermore, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09582","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.09582/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:24:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BvLHY4M0ylAqai+cYgFuyvWZWuIu/BXbRhUlRSM0LW4FQMRAsejhtiz2shuWBaaaoNAPq6604sGxBzx6nVmIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:18:53.966228Z"},"content_sha256":"870380f59059a2791bf53360bd83873d5180cec754eaa49c511de74e3212272f","schema_version":"1.0","event_id":"sha256:870380f59059a2791bf53360bd83873d5180cec754eaa49c511de74e3212272f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/bundle.json","state_url":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T06:18:53Z","links":{"resolver":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ","bundle":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/bundle.json","state":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WBKOWKJ6PDLLVAMHQIHU5F5DIJ","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":"185cee4c17802f9cd4ff7b676e62a006d7cf72ff820fcd7c5e81af289c365429","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T07:37:09Z","title_canon_sha256":"ee73b56959cee70909dd76a1851f94eb55df468bd3585f19f4997c2823b7aeb1"},"schema_version":"1.0","source":{"id":"2312.09582","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09582","created_at":"2026-07-05T07:24:27Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09582v1","created_at":"2026-07-05T07:24:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09582","created_at":"2026-07-05T07:24:27Z"},{"alias_kind":"pith_short_12","alias_value":"WBKOWKJ6PDLL","created_at":"2026-07-05T07:24:27Z"},{"alias_kind":"pith_short_16","alias_value":"WBKOWKJ6PDLLVAMH","created_at":"2026-07-05T07:24:27Z"},{"alias_kind":"pith_short_8","alias_value":"WBKOWKJ6","created_at":"2026-07-05T07:24:27Z"}],"graph_snapshots":[{"event_id":"sha256:870380f59059a2791bf53360bd83873d5180cec754eaa49c511de74e3212272f","target":"graph","created_at":"2026-07-05T07:24:27Z","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/2312.09582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In speech recognition applications, it is important to recognize context-specific rare words, such as proper nouns. Tree-constrained Pointer Generator (TCPGen) has shown promise for this purpose, which efficiently biases such words with a prefix tree. While the original TCPGen relies on grapheme-based encoding, we propose extending it with phoneme-aware encoding to better recognize words of unusual pronunciations. As TCPGen handles biasing words as subword units, we propose obtaining subword-level phoneme-aware encoding by using alignment between phonemes and subwords. Furthermore, we propose ","authors_text":"Emiru Tsunoo, Hayato Futami, Hiroaki Ogawa, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T07:37:09Z","title":"Phoneme-aware Encoding for Prefix-tree-based Contextual ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09582","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:de89341de1a6174ffe7d93da5629860253c02364949a9482837513494fa093c3","target":"record","created_at":"2026-07-05T07:24:27Z","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":"185cee4c17802f9cd4ff7b676e62a006d7cf72ff820fcd7c5e81af289c365429","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T07:37:09Z","title_canon_sha256":"ee73b56959cee70909dd76a1851f94eb55df468bd3585f19f4997c2823b7aeb1"},"schema_version":"1.0","source":{"id":"2312.09582","kind":"arxiv","version":1}},"canonical_sha256":"b054eb293e78d6ba8187820f4e97a3425d103183f499535a854432d6b8604105","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b054eb293e78d6ba8187820f4e97a3425d103183f499535a854432d6b8604105","first_computed_at":"2026-07-05T07:24:27.635151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:27.635151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xiRx/7E+bOiTMeEJu4YZEmE1wyYAgVO/kt1MNvD38DsGLTmUU0/rEajFtMJIIJeSjA9aqfqfSsxS4d+mnvDfBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:27.635754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.09582","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de89341de1a6174ffe7d93da5629860253c02364949a9482837513494fa093c3","sha256:870380f59059a2791bf53360bd83873d5180cec754eaa49c511de74e3212272f"],"state_sha256":"c98085659542735aa6ad2dfcab868275ec4f86816f9878bd45a2d069b00b5ad6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kA3I3ligfcjHGBAUbIf6BHFy7m/CFSoi3z+PCPLFzPk2Qqiq+dqzuJ7vPyl/m3UYp23bxT1RoGS7WbflUmbzAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T06:18:53.972026Z","bundle_sha256":"53f2d1d3407f77e82e51e6f939763125a348fe7110e319e3da1783ecffeb11fc"}}