{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AWPKHAVB7RDYVMMQKTTJG3ZASU","short_pith_number":"pith:AWPKHAVB","canonical_record":{"source":{"id":"2412.16464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T03:35:49Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"82c16619e59168a8bda86eac6ad0d5af63ed7b1678ca3f685ca77e753641b4f7","abstract_canon_sha256":"f78cf889bde11231290045c6b219ff4434c632354b3736051fae586efa2d34d8"},"schema_version":"1.0"},"canonical_sha256":"059ea382a1fc478ab19054e6936f20950cdbe587444b788beeb7002b0ef436fe","source":{"kind":"arxiv","id":"2412.16464","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16464","created_at":"2026-07-05T09:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16464v1","created_at":"2026-07-05T09:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16464","created_at":"2026-07-05T09:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"AWPKHAVB7RDY","created_at":"2026-07-05T09:52:46Z"},{"alias_kind":"pith_short_16","alias_value":"AWPKHAVB7RDYVMMQ","created_at":"2026-07-05T09:52:46Z"},{"alias_kind":"pith_short_8","alias_value":"AWPKHAVB","created_at":"2026-07-05T09:52:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AWPKHAVB7RDYVMMQKTTJG3ZASU","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T03:35:49Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"82c16619e59168a8bda86eac6ad0d5af63ed7b1678ca3f685ca77e753641b4f7","abstract_canon_sha256":"f78cf889bde11231290045c6b219ff4434c632354b3736051fae586efa2d34d8"},"schema_version":"1.0"},"canonical_sha256":"059ea382a1fc478ab19054e6936f20950cdbe587444b788beeb7002b0ef436fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:46.521740Z","signature_b64":"pLm8ofxSozPv76YR2nZGB88oebh4LONyahORWbIWc08cJ7nLGfaTXnkWcQHj2royolGat1ScXRdwaSZAVcuzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"059ea382a1fc478ab19054e6936f20950cdbe587444b788beeb7002b0ef436fe","last_reissued_at":"2026-07-05T09:52:46.521297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:46.521297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16464","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":"2026-07-05T09:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G86NMqSTXCEkZrLMdm5NpUKQDN+ZYebo0SKniVsIEiO1avifqWknPbwkBSarj6OFM6gPjJOkweWTL+LWnDZHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T04:48:06.078429Z"},"content_sha256":"5f101fe4963aed1422740246e77439240d73b9fbae630708e94609c43cc75153","schema_version":"1.0","event_id":"sha256:5f101fe4963aed1422740246e77439240d73b9fbae630708e94609c43cc75153"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AWPKHAVB7RDYVMMQKTTJG3ZASU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Jinxi Guo, Keqi Deng, Mike Seltzer, Niko Moritz, Ozlem Kalinli, Philip C. Woodland, Yingyi Ma","submitted_at":"2024-12-21T03:35:49Z","abstract_excerpt":"While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs into a Factorized Transducer (FT) model, naturally enabling streaming capabilities. Furthermore, given that the large vocabulary of LLMs can cause data sparsity issue and increased training costs for spoken language systems, this paper introduces an efficient vocabulary adaptation technique to align LLMs with speech system vocabularies. The results show that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16464","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/2412.16464/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":"2026-07-05T09:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tjcxsomg8oL4WPssnPl/qeWEDQlZzzAV80srTqpnGk/sVy1XaIppWtAXGr/7UpinVAsFTO/0cMfdeo96ZGfpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T04:48:06.078808Z"},"content_sha256":"f0353b5e863fe6d16766d501ead83b36419241eecdce9d56acd23e215ae9b87e","schema_version":"1.0","event_id":"sha256:f0353b5e863fe6d16766d501ead83b36419241eecdce9d56acd23e215ae9b87e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AWPKHAVB7RDYVMMQKTTJG3ZASU/bundle.json","state_url":"https://pith.science/pith/AWPKHAVB7RDYVMMQKTTJG3ZASU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AWPKHAVB7RDYVMMQKTTJG3ZASU/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":"2026-07-13T04:48:06Z","links":{"resolver":"https://pith.science/pith/AWPKHAVB7RDYVMMQKTTJG3ZASU","bundle":"https://pith.science/pith/AWPKHAVB7RDYVMMQKTTJG3ZASU/bundle.json","state":"https://pith.science/pith/AWPKHAVB7RDYVMMQKTTJG3ZASU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AWPKHAVB7RDYVMMQKTTJG3ZASU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AWPKHAVB7RDYVMMQKTTJG3ZASU","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":"f78cf889bde11231290045c6b219ff4434c632354b3736051fae586efa2d34d8","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T03:35:49Z","title_canon_sha256":"82c16619e59168a8bda86eac6ad0d5af63ed7b1678ca3f685ca77e753641b4f7"},"schema_version":"1.0","source":{"id":"2412.16464","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16464","created_at":"2026-07-05T09:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16464v1","created_at":"2026-07-05T09:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16464","created_at":"2026-07-05T09:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"AWPKHAVB7RDY","created_at":"2026-07-05T09:52:46Z"},{"alias_kind":"pith_short_16","alias_value":"AWPKHAVB7RDYVMMQ","created_at":"2026-07-05T09:52:46Z"},{"alias_kind":"pith_short_8","alias_value":"AWPKHAVB","created_at":"2026-07-05T09:52:46Z"}],"graph_snapshots":[{"event_id":"sha256:f0353b5e863fe6d16766d501ead83b36419241eecdce9d56acd23e215ae9b87e","target":"graph","created_at":"2026-07-05T09:52:46Z","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/2412.16464/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs into a Factorized Transducer (FT) model, naturally enabling streaming capabilities. Furthermore, given that the large vocabulary of LLMs can cause data sparsity issue and increased training costs for spoken language systems, this paper introduces an efficient vocabulary adaptation technique to align LLMs with speech system vocabularies. The results show that","authors_text":"Jinxi Guo, Keqi Deng, Mike Seltzer, Niko Moritz, Ozlem Kalinli, Philip C. Woodland, Yingyi Ma","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T03:35:49Z","title":"Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16464","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":"sha256:5f101fe4963aed1422740246e77439240d73b9fbae630708e94609c43cc75153","target":"record","created_at":"2026-07-05T09:52:46Z","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":"f78cf889bde11231290045c6b219ff4434c632354b3736051fae586efa2d34d8","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T03:35:49Z","title_canon_sha256":"82c16619e59168a8bda86eac6ad0d5af63ed7b1678ca3f685ca77e753641b4f7"},"schema_version":"1.0","source":{"id":"2412.16464","kind":"arxiv","version":1}},"canonical_sha256":"059ea382a1fc478ab19054e6936f20950cdbe587444b788beeb7002b0ef436fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"059ea382a1fc478ab19054e6936f20950cdbe587444b788beeb7002b0ef436fe","first_computed_at":"2026-07-05T09:52:46.521297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:46.521297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pLm8ofxSozPv76YR2nZGB88oebh4LONyahORWbIWc08cJ7nLGfaTXnkWcQHj2royolGat1ScXRdwaSZAVcuzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:46.521740Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16464","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f101fe4963aed1422740246e77439240d73b9fbae630708e94609c43cc75153","sha256:f0353b5e863fe6d16766d501ead83b36419241eecdce9d56acd23e215ae9b87e"],"state_sha256":"79761e36d3cfb21a0071ff6b62792f0c6319dda3da386695c5ba5f0c75412e6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jHVDQGTHuALc8jxwac2wNuwAdUIR/p+kD0YhsvSiSEaCDxvx+csKV+AAsUeaU9WlBPtKXCkdTuSPiVETCyWRDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T04:48:06.082679Z","bundle_sha256":"bcfb8b1b7451a6714f12255021fa873f50bdf4012e05d2db68f01ee185789fc8"}}