{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3VPCCPZCKRC4KX6QB3NM55NNLX","short_pith_number":"pith:3VPCCPZC","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"},"canonical_sha256":"dd5e213f225445c55fd00edacef5ad5dc5a829ede992fdcde40a8b6ad71fe587","source":{"kind":"arxiv","id":"2606.08486","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08486","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08486v1","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08486","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"3VPCCPZCKRC4","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"3VPCCPZCKRC4KX6Q","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"3VPCCPZC","created_at":"2026-06-09T01:05:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3VPCCPZCKRC4KX6QB3NM55NNLX","target":"record","payload":{"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"},"canonical_sha256":"dd5e213f225445c55fd00edacef5ad5dc5a829ede992fdcde40a8b6ad71fe587","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"},"source_kind":"arxiv","source_id":"2606.08486","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":"2026-06-09T01:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gmv9e2tcKaiOFbUG4uQi7y31e6V76p9JbCdO7sAu76adkbh68KAAcsSgS/4VQhacaBmc+Rni5JJz6DenOYAaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:26:07.127410Z"},"content_sha256":"ad39014532f06fe32087ccf63e2256ebcad7b98811f743d20dec38929ef36b02","schema_version":"1.0","event_id":"sha256:ad39014532f06fe32087ccf63e2256ebcad7b98811f743d20dec38929ef36b02"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3VPCCPZCKRC4KX6QB3NM55NNLX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TGw9JWdS5zI6Tvha5mZxYYjErRnvsjjpbN331+5exvv42BSjsXQ4tKi/8lOmS7xWmTYSa9ko2pmKJ2uut4IkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:26:07.128279Z"},"content_sha256":"357c3a3f68d7402a0d7a4c913c88ee78e18fe9f7106141454c1ef936e767e9a2","schema_version":"1.0","event_id":"sha256:357c3a3f68d7402a0d7a4c913c88ee78e18fe9f7106141454c1ef936e767e9a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/bundle.json","state_url":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/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":"2026-06-11T22:26:07Z","links":{"resolver":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX","bundle":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/bundle.json","state":"https://pith.science/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3VPCCPZCKRC4KX6QB3NM55NNLX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3VPCCPZCKRC4KX6QB3NM55NNLX","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":"6ac35db501e2b81f63509c5e7c6a5ab9da0348aa788501e994949aa74cc1551a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:15:34Z","title_canon_sha256":"ee3c5af1d3bf2cd5f16e534ee2a5c4eb627cb12e94b259d1f8eb9d8380b17ec3"},"schema_version":"1.0","source":{"id":"2606.08486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08486","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08486v1","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08486","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"3VPCCPZCKRC4","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"3VPCCPZCKRC4KX6Q","created_at":"2026-06-09T01:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"3VPCCPZC","created_at":"2026-06-09T01:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:357c3a3f68d7402a0d7a4c913c88ee78e18fe9f7106141454c1ef936e767e9a2","target":"graph","created_at":"2026-06-09T01:05:38Z","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/2606.08486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Shanil Puri, Shinji Watanabe, Subhabrata Mukherjee, Yun Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:15:34Z","title":"TRADE: Transducer-Augmented Decoder for Speech LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08486","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:ad39014532f06fe32087ccf63e2256ebcad7b98811f743d20dec38929ef36b02","target":"record","created_at":"2026-06-09T01:05:38Z","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":"6ac35db501e2b81f63509c5e7c6a5ab9da0348aa788501e994949aa74cc1551a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T07:15:34Z","title_canon_sha256":"ee3c5af1d3bf2cd5f16e534ee2a5c4eb627cb12e94b259d1f8eb9d8380b17ec3"},"schema_version":"1.0","source":{"id":"2606.08486","kind":"arxiv","version":1}},"canonical_sha256":"dd5e213f225445c55fd00edacef5ad5dc5a829ede992fdcde40a8b6ad71fe587","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd5e213f225445c55fd00edacef5ad5dc5a829ede992fdcde40a8b6ad71fe587","first_computed_at":"2026-06-09T01:05:38.045104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:38.045104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"thDmTTrUJI4AYg5gTvRPww+d1AtYGhLg9IiXwozr6o/gbyqP7ivsAB7V5mfmt6B3m8SdxBiFppltVgoLGwLuAQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:38.045525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad39014532f06fe32087ccf63e2256ebcad7b98811f743d20dec38929ef36b02","sha256:357c3a3f68d7402a0d7a4c913c88ee78e18fe9f7106141454c1ef936e767e9a2"],"state_sha256":"70d4212e612134fca33fefb76c3c028e11000189879dc5483fd002bac84fd028"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CDhHT/PTKxl2PIY4IgBU7bQONFdUdqvdUNXvvdC4geHV7SYDbSPo136Rq+WiMPSBm/vSGkuYvYPq7oR7gb5CAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T22:26:07.133551Z","bundle_sha256":"38c74fb70a9095be2c5d66bcc8c674d841daa0150833670fbc109b57182bbc42"}}