{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W7L6MWRRPNA5U3RNPWXVT6GCIX","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":"df8b1563434f1bac118304f509587d094e92686e7d88abc099e131d451ebaf40","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T20:20:29Z","title_canon_sha256":"64f15b4893e1dd7388afc2455cd6564397309a6e1053f2be891ba31d9b3e9a43"},"schema_version":"1.0","source":{"id":"2406.09569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09569","created_at":"2026-07-05T08:31:55Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09569v1","created_at":"2026-07-05T08:31:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09569","created_at":"2026-07-05T08:31:55Z"},{"alias_kind":"pith_short_12","alias_value":"W7L6MWRRPNA5","created_at":"2026-07-05T08:31:55Z"},{"alias_kind":"pith_short_16","alias_value":"W7L6MWRRPNA5U3RN","created_at":"2026-07-05T08:31:55Z"},{"alias_kind":"pith_short_8","alias_value":"W7L6MWRR","created_at":"2026-07-05T08:31:55Z"}],"graph_snapshots":[{"event_id":"sha256:184c2557215f280806ccc68582d7c722d9ab67f5f2446eae2d130e664b8232bc","target":"graph","created_at":"2026-07-05T08:31:55Z","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/2406.09569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Speech ReaLLM, a new ASR architecture that marries \"decoder-only\" ASR with the RNN-T to make multimodal LLM architectures capable of real-time streaming. This is the first \"decoder-only\" ASR architecture designed to handle continuous audio without explicit end-pointing. Speech ReaLLM is a special case of the more general ReaLLM (\"real-time LLM\") approach, also introduced here for the first time. The idea is inspired by RNN-T: Instead of generating a response only at the end of a user prompt, generate after every input token received in real time (it is often empty). On Librispeech","authors_text":"Chunyang Wu, Frank Seide, Junteng Jia, Morrie Doulaty, Yangyang Shi, Yashesh Gaur","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T20:20:29Z","title":"Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09569","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":"sha256:95e5911c65d792309ec6bdb152ec8e114f8f7669d67cf8fcbe6d93b67be021e1","target":"record","created_at":"2026-07-05T08:31:55Z","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":"df8b1563434f1bac118304f509587d094e92686e7d88abc099e131d451ebaf40","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T20:20:29Z","title_canon_sha256":"64f15b4893e1dd7388afc2455cd6564397309a6e1053f2be891ba31d9b3e9a43"},"schema_version":"1.0","source":{"id":"2406.09569","kind":"arxiv","version":1}},"canonical_sha256":"b7d7e65a317b41da6e2d7daf59f8c245fc267fa3cff554f82b20ab527e4e0e23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7d7e65a317b41da6e2d7daf59f8c245fc267fa3cff554f82b20ab527e4e0e23","first_computed_at":"2026-07-05T08:31:55.938456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:55.938456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HqfGxTrsAMjt8ARAstg2sx1331DEuIP2ASf07sk1MJtLbzH7OJ6C6kCGwizuKuP0b3HWIqxNHMG9B/prOJwDCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:55.938971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95e5911c65d792309ec6bdb152ec8e114f8f7669d67cf8fcbe6d93b67be021e1","sha256:184c2557215f280806ccc68582d7c722d9ab67f5f2446eae2d130e664b8232bc"],"state_sha256":"aeb0650421f0d3835dd02a95087f13c413ffadf4b4d47098a66cbd403740a280"}