{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VSKR2XGK3VYDWSHZAX7H4425XG","short_pith_number":"pith:VSKR2XGK","canonical_record":{"source":{"id":"2606.21882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-20T04:47:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"983515e98079492cec282a3045e9a6f44072815bcad18c23291801362153f5b4","abstract_canon_sha256":"994d9090f8be06ea1b9f7c9b5e0df0fd6849975287fe4b171a66775e731dea57"},"schema_version":"1.0"},"canonical_sha256":"ac951d5ccadd703b48f905fe7e735db983a1337714eb710054be0c8ef6718def","source":{"kind":"arxiv","id":"2606.21882","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21882","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21882v1","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21882","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_12","alias_value":"VSKR2XGK3VYD","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_16","alias_value":"VSKR2XGK3VYDWSHZ","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_8","alias_value":"VSKR2XGK","created_at":"2026-06-23T02:13:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VSKR2XGK3VYDWSHZAX7H4425XG","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-20T04:47:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"983515e98079492cec282a3045e9a6f44072815bcad18c23291801362153f5b4","abstract_canon_sha256":"994d9090f8be06ea1b9f7c9b5e0df0fd6849975287fe4b171a66775e731dea57"},"schema_version":"1.0"},"canonical_sha256":"ac951d5ccadd703b48f905fe7e735db983a1337714eb710054be0c8ef6718def","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:01.809629Z","signature_b64":"7jcDpvg0ScZFIyH26jQf6rpS4E3y90Pr0Msle3C7EOI9UZbm6PauOXjCMYPsy4EQw/G8PyqMsZ1NjneIC93TAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac951d5ccadd703b48f905fe7e735db983a1337714eb710054be0c8ef6718def","last_reissued_at":"2026-06-23T02:13:01.809256Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:01.809256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21882","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":"2026-06-23T02:13:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3q1Tuebj0v95ctWaiDfbnHdQ+2+b4ulyjSBfvQaRoUTKJcf/xWq4AoHiqsGPtcLbVpntcV3KEA7I14AiVV+IAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T07:18:36.833582Z"},"content_sha256":"b4b5e5a64cd8ea354a20831211961d47de93fa6418a3a2a7f4995c6d46343810","schema_version":"1.0","event_id":"sha256:b4b5e5a64cd8ea354a20831211961d47de93fa6418a3a2a7f4995c6d46343810"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VSKR2XGK3VYDWSHZAX7H4425XG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Jason Roche, Junjie Lai, Muyang Du","submitted_at":"2026-06-20T04:47:45Z","abstract_excerpt":"Streaming text-to-speech synthesis in cascaded LLM-TTS systems still faces latency challenges as most TTS models require full context before initiating generation. We present S5-TTS, a streaming variant of T5-TTS that enables low-latency, word-by-word incremental speech synthesis through encoder-decoder language modeling and monotonic alignment learning. S5-TTS begins generating speech immediately after receiving the first few words, substantially reducing end-to-end response latency. To maintain quality under limited lookahead, we introduce a lookahead-causal masking mechanism with Conv-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21882","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/2606.21882/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":"2026-06-23T02:13:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/WwWkpCNoq7lLiIeDjfwRvc9et5f7ncR51iCmKy3J8stOjtmoRdYIhE63I7L6DLsBfNcYnpBNiFURUhvWWrzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T07:18:36.833950Z"},"content_sha256":"53e45f512426d8c7482a300a2db155c44b8cd663eb3c8718a787d1453c67daeb","schema_version":"1.0","event_id":"sha256:53e45f512426d8c7482a300a2db155c44b8cd663eb3c8718a787d1453c67daeb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG/bundle.json","state_url":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VSKR2XGK3VYDWSHZAX7H4425XG/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":"2026-06-28T07:18:36Z","links":{"resolver":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG","bundle":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG/bundle.json","state":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VSKR2XGK3VYDWSHZAX7H4425XG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VSKR2XGK3VYDWSHZAX7H4425XG","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":"994d9090f8be06ea1b9f7c9b5e0df0fd6849975287fe4b171a66775e731dea57","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-20T04:47:45Z","title_canon_sha256":"983515e98079492cec282a3045e9a6f44072815bcad18c23291801362153f5b4"},"schema_version":"1.0","source":{"id":"2606.21882","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21882","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21882v1","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21882","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_12","alias_value":"VSKR2XGK3VYD","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_16","alias_value":"VSKR2XGK3VYDWSHZ","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_8","alias_value":"VSKR2XGK","created_at":"2026-06-23T02:13:01Z"}],"graph_snapshots":[{"event_id":"sha256:53e45f512426d8c7482a300a2db155c44b8cd663eb3c8718a787d1453c67daeb","target":"graph","created_at":"2026-06-23T02:13:01Z","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/2606.21882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Streaming text-to-speech synthesis in cascaded LLM-TTS systems still faces latency challenges as most TTS models require full context before initiating generation. We present S5-TTS, a streaming variant of T5-TTS that enables low-latency, word-by-word incremental speech synthesis through encoder-decoder language modeling and monotonic alignment learning. S5-TTS begins generating speech immediately after receiving the first few words, substantially reducing end-to-end response latency. To maintain quality under limited lookahead, we introduce a lookahead-causal masking mechanism with Conv-based","authors_text":"Jason Roche, Junjie Lai, Muyang Du","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-20T04:47:45Z","title":"Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21882","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:b4b5e5a64cd8ea354a20831211961d47de93fa6418a3a2a7f4995c6d46343810","target":"record","created_at":"2026-06-23T02:13:01Z","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":"994d9090f8be06ea1b9f7c9b5e0df0fd6849975287fe4b171a66775e731dea57","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-20T04:47:45Z","title_canon_sha256":"983515e98079492cec282a3045e9a6f44072815bcad18c23291801362153f5b4"},"schema_version":"1.0","source":{"id":"2606.21882","kind":"arxiv","version":1}},"canonical_sha256":"ac951d5ccadd703b48f905fe7e735db983a1337714eb710054be0c8ef6718def","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac951d5ccadd703b48f905fe7e735db983a1337714eb710054be0c8ef6718def","first_computed_at":"2026-06-23T02:13:01.809256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:01.809256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7jcDpvg0ScZFIyH26jQf6rpS4E3y90Pr0Msle3C7EOI9UZbm6PauOXjCMYPsy4EQw/G8PyqMsZ1NjneIC93TAw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:01.809629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21882","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4b5e5a64cd8ea354a20831211961d47de93fa6418a3a2a7f4995c6d46343810","sha256:53e45f512426d8c7482a300a2db155c44b8cd663eb3c8718a787d1453c67daeb"],"state_sha256":"37eb5342bb7f92a0345545968e855e4e4b28ece6fd165e2701c9e4d09d69cfed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8I4m/4+UluT1nAdQQbUhDO56YbCPpmYvwWlAikjrEQTGm+aZjtRg5sbzMnfC7kj/hkXGywStDiat1gmhPioBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T07:18:36.835921Z","bundle_sha256":"0ea4e3f48cc3307dab351942945a8b9d8f58732688ffbfc5cc42d0917c9fb5b1"}}