{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3VPCCPZCKRC4KX6QB3NM55NNLX","short_pith_number":"pith:3VPCCPZC","schema_version":"1.0","canonical_sha256":"dd5e213f225445c55fd00edacef5ad5dc5a829ede992fdcde40a8b6ad71fe587","source":{"kind":"arxiv","id":"2606.08486","version":1},"attestation_state":"computed","paper":{"title":"TRADE: Transducer-Augmented Decoder for Speech LLM","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shanil Puri, Shinji Watanabe, Subhabrata Mukherjee, Yun Tang","submitted_at":"2026-06-07T07:15:34Z","abstract_excerpt":"Speech Large Language Models (Speech LLMs) lack a principled mechanism for streaming inference: their label-synchronous generation has no acoustic-frame alignment, making real-time decoding and end-of-utterance detection difficult. We propose TRADE TRansducer-Augmented DEcoder, which augments a multimodal LLM with a transducer branch that shares the audio encoder and uses the LLM's hidden states directly as the prediction network -- coupling frame-synchronous acoustic alignment with the LLM's linguistic reasoning. Three design choices make the system accurate, streamable, and long-form capable"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.08486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"ee3c5af1d3bf2cd5f16e534ee2a5c4eb627cb12e94b259d1f8eb9d8380b17ec3","abstract_canon_sha256":"6ac35db501e2b81f63509c5e7c6a5ab9da0348aa788501e994949aa74cc1551a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:38.045525Z","signature_b64":"thDmTTrUJI4AYg5gTvRPww+d1AtYGhLg9IiXwozr6o/gbyqP7ivsAB7V5mfmt6B3m8SdxBiFppltVgoLGwLuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd5e213f225445c55fd00edacef5ad5dc5a829ede992fdcde40a8b6ad71fe587","last_reissued_at":"2026-06-09T01:05:38.045104Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:38.045104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRADE: Transducer-Augmented Decoder for Speech LLM","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shanil Puri, Shinji Watanabe, Subhabrata Mukherjee, Yun Tang","submitted_at":"2026-06-07T07:15:34Z","abstract_excerpt":"Speech Large Language Models (Speech LLMs) lack a principled mechanism for streaming inference: their label-synchronous generation has no acoustic-frame alignment, making real-time decoding and end-of-utterance detection difficult. We propose TRADE TRansducer-Augmented DEcoder, which augments a multimodal LLM with a transducer branch that shares the audio encoder and uses the LLM's hidden states directly as the prediction network -- coupling frame-synchronous acoustic alignment with the LLM's linguistic reasoning. Three design choices make the system accurate, streamable, and long-form capable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08486","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/2606.08486/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.08486","created_at":"2026-06-09T01:05:38.045163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08486v1","created_at":"2026-06-09T01:05:38.045163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08486","created_at":"2026-06-09T01:05:38.045163+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VPCCPZCKRC4","created_at":"2026-06-09T01:05:38.045163+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VPCCPZCKRC4KX6Q","created_at":"2026-06-09T01:05:38.045163+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VPCCPZC","created_at":"2026-06-09T01:05:38.045163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX","json":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX.json","graph_json":"https://pith.science/api/pith-number/3VPCCPZCKRC4KX6QB3NM55NNLX/graph.json","events_json":"https://pith.science/api/pith-number/3VPCCPZCKRC4KX6QB3NM55NNLX/events.json","paper":"https://pith.science/paper/3VPCCPZC"},"agent_actions":{"view_html":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX","download_json":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX.json","view_paper":"https://pith.science/paper/3VPCCPZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08486&json=true","fetch_graph":"https://pith.science/api/pith-number/3VPCCPZCKRC4KX6QB3NM55NNLX/graph.json","fetch_events":"https://pith.science/api/pith-number/3VPCCPZCKRC4KX6QB3NM55NNLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/action/storage_attestation","attest_author":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/action/author_attestation","sign_citation":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/action/citation_signature","submit_replication":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/action/replication_record"}},"created_at":"2026-06-09T01:05:38.045163+00:00","updated_at":"2026-06-09T01:05:38.045163+00:00"}