{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XNMZAYNYGEC2TLBUY2R45SLOPN","short_pith_number":"pith:XNMZAYNY","canonical_record":{"source":{"id":"2506.04711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-05T07:35:55Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"c220bf112a3723a33bbcff96bf1766a9d5668623bd2401d06b890e2f8577c570","abstract_canon_sha256":"aa17f1f1760c15f604dc2ebe7d0f3bc382eff53b35925bf9fd691282f42c2497"},"schema_version":"1.0"},"canonical_sha256":"bb599061b83105a9ac34c6a3cec96e7b7173b40b1d698de6f5c0928b9184e9c8","source":{"kind":"arxiv","id":"2506.04711","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04711","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04711v1","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04711","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"XNMZAYNYGEC2","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"pith_short_16","alias_value":"XNMZAYNYGEC2TLBU","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"pith_short_8","alias_value":"XNMZAYNY","created_at":"2026-07-05T11:16:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XNMZAYNYGEC2TLBUY2R45SLOPN","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-05T07:35:55Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"c220bf112a3723a33bbcff96bf1766a9d5668623bd2401d06b890e2f8577c570","abstract_canon_sha256":"aa17f1f1760c15f604dc2ebe7d0f3bc382eff53b35925bf9fd691282f42c2497"},"schema_version":"1.0"},"canonical_sha256":"bb599061b83105a9ac34c6a3cec96e7b7173b40b1d698de6f5c0928b9184e9c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:19.244168Z","signature_b64":"pYa7/nty8FujflJw9x8CQKl06Wj10XysQpkkTvWJ/9rQsIrKHdIvPHxamv4BMJW/SzJ01MQ1nwfsGJiQj7/TBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb599061b83105a9ac34c6a3cec96e7b7173b40b1d698de6f5c0928b9184e9c8","last_reissued_at":"2026-07-05T11:16:19.243673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:19.243673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04711","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":"2026-07-05T11:16:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s3kdgRo9aP3+Y3lCB37k8mk2r8h9Ik4dIxDr31KRNEZgPhyOJaX0za5bjXkeUCwTG2o5mXYAxGF/2S0u629NBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:25:09.411795Z"},"content_sha256":"994f2c721700af92411a185337ac5f537028d5c8a6ecd0f6cd47472588b3ce70","schema_version":"1.0","event_id":"sha256:994f2c721700af92411a185337ac5f537028d5c8a6ecd0f6cd47472588b3ce70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XNMZAYNYGEC2TLBUY2R45SLOPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-based phoneme-to-grapheme for phoneme-based speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hao Huang, Min Bi, Saierdaer Yusuyin, Te Ma, Zhijian Ou","submitted_at":"2025-06-05T07:35:55Z","abstract_excerpt":"In automatic speech recognition (ASR), phoneme-based multilingual pre-training and crosslingual fine-tuning is attractive for its high data efficiency and competitive results compared to subword-based models. However, Weighted Finite State Transducer (WFST) based decoding is limited by its complex pipeline and inability to leverage large language models (LLMs). Therefore, we propose LLM-based phoneme-to-grapheme (LLM-P2G) decoding for phoneme-based ASR, consisting of speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G). A challenge is that there seems to have information loss in cascading S2P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04711","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/2506.04711/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":"2026-07-05T11:16:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z9YXlZRg+30HPP/dHIbfa0vVjvc+px0gHyC8KVpfS9xcyOpVvevv1bbWz9XRH2weWySTDTjEkM51Xo+3QExeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:25:09.412444Z"},"content_sha256":"dbede0b3555d3ef746d20cea9d5c65f68ba530972fd6abeb162373840177dfdf","schema_version":"1.0","event_id":"sha256:dbede0b3555d3ef746d20cea9d5c65f68ba530972fd6abeb162373840177dfdf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XNMZAYNYGEC2TLBUY2R45SLOPN/bundle.json","state_url":"https://pith.science/pith/XNMZAYNYGEC2TLBUY2R45SLOPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XNMZAYNYGEC2TLBUY2R45SLOPN/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":"2026-08-08T06:25:09Z","links":{"resolver":"https://pith.science/pith/XNMZAYNYGEC2TLBUY2R45SLOPN","bundle":"https://pith.science/pith/XNMZAYNYGEC2TLBUY2R45SLOPN/bundle.json","state":"https://pith.science/pith/XNMZAYNYGEC2TLBUY2R45SLOPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XNMZAYNYGEC2TLBUY2R45SLOPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XNMZAYNYGEC2TLBUY2R45SLOPN","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":"aa17f1f1760c15f604dc2ebe7d0f3bc382eff53b35925bf9fd691282f42c2497","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-05T07:35:55Z","title_canon_sha256":"c220bf112a3723a33bbcff96bf1766a9d5668623bd2401d06b890e2f8577c570"},"schema_version":"1.0","source":{"id":"2506.04711","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04711","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04711v1","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04711","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"XNMZAYNYGEC2","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"pith_short_16","alias_value":"XNMZAYNYGEC2TLBU","created_at":"2026-07-05T11:16:19Z"},{"alias_kind":"pith_short_8","alias_value":"XNMZAYNY","created_at":"2026-07-05T11:16:19Z"}],"graph_snapshots":[{"event_id":"sha256:dbede0b3555d3ef746d20cea9d5c65f68ba530972fd6abeb162373840177dfdf","target":"graph","created_at":"2026-07-05T11:16:19Z","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/2506.04711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In automatic speech recognition (ASR), phoneme-based multilingual pre-training and crosslingual fine-tuning is attractive for its high data efficiency and competitive results compared to subword-based models. However, Weighted Finite State Transducer (WFST) based decoding is limited by its complex pipeline and inability to leverage large language models (LLMs). Therefore, we propose LLM-based phoneme-to-grapheme (LLM-P2G) decoding for phoneme-based ASR, consisting of speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G). A challenge is that there seems to have information loss in cascading S2P","authors_text":"Hao Huang, Min Bi, Saierdaer Yusuyin, Te Ma, Zhijian Ou","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-05T07:35:55Z","title":"LLM-based phoneme-to-grapheme for phoneme-based speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04711","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":"sha256:994f2c721700af92411a185337ac5f537028d5c8a6ecd0f6cd47472588b3ce70","target":"record","created_at":"2026-07-05T11:16:19Z","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":"aa17f1f1760c15f604dc2ebe7d0f3bc382eff53b35925bf9fd691282f42c2497","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-05T07:35:55Z","title_canon_sha256":"c220bf112a3723a33bbcff96bf1766a9d5668623bd2401d06b890e2f8577c570"},"schema_version":"1.0","source":{"id":"2506.04711","kind":"arxiv","version":1}},"canonical_sha256":"bb599061b83105a9ac34c6a3cec96e7b7173b40b1d698de6f5c0928b9184e9c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb599061b83105a9ac34c6a3cec96e7b7173b40b1d698de6f5c0928b9184e9c8","first_computed_at":"2026-07-05T11:16:19.243673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:19.243673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pYa7/nty8FujflJw9x8CQKl06Wj10XysQpkkTvWJ/9rQsIrKHdIvPHxamv4BMJW/SzJ01MQ1nwfsGJiQj7/TBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:19.244168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04711","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:994f2c721700af92411a185337ac5f537028d5c8a6ecd0f6cd47472588b3ce70","sha256:dbede0b3555d3ef746d20cea9d5c65f68ba530972fd6abeb162373840177dfdf"],"state_sha256":"76f4162ad28642e728a081f51b7958a1019e9add22c42ceab2143b71242e430c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ts9mnxad4/5/xik0Si4Djx8J+1tgUfzUGUgM9Cof6uCGJQKqvD6t7mSWB32jXu2jzeIz9Z8pJCqJpqdBjQ/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:25:09.417584Z","bundle_sha256":"ca2637576b57e7315eb65049d7b44f0373b6abb1cb9aea3de6fc335208c3a04b"}}