{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CDIPYR6RQN2WS7NINTWKF2HBGU","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":"aecd8530554c6d5cf0a06896ce086db2188a431562d4cfd171c4ffd94da67fe5","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-02T01:54:35Z","title_canon_sha256":"ccfc40dcdee38734e70dd5e61ca1eccd153c5a4af5c97b2edb49e4e62eadafa3"},"schema_version":"1.0","source":{"id":"2410.03752","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03752","created_at":"2026-07-05T09:16:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03752v1","created_at":"2026-07-05T09:16:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03752","created_at":"2026-07-05T09:16:24Z"},{"alias_kind":"pith_short_12","alias_value":"CDIPYR6RQN2W","created_at":"2026-07-05T09:16:24Z"},{"alias_kind":"pith_short_16","alias_value":"CDIPYR6RQN2WS7NI","created_at":"2026-07-05T09:16:24Z"},{"alias_kind":"pith_short_8","alias_value":"CDIPYR6R","created_at":"2026-07-05T09:16:24Z"}],"graph_snapshots":[{"event_id":"sha256:5dfaef681612dc7d4eec05bda4b436354782773cf189b86ee95dce031bd37fe6","target":"graph","created_at":"2026-07-05T09:16:24Z","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/2410.03752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works have shown that prompting large language models with audio encodings can unlock speech recognition capabilities. However, existing techniques do not scale efficiently, especially while handling long form streaming audio inputs -- not only do they extrapolate poorly beyond the audio length seen during training, but they are also computationally inefficient due to the quadratic cost of attention.\n  In this work, we introduce SpeechLLM-XL, a linear scaling decoder-only model for streaming speech recognition. We process audios in configurable chunks using limited attention window for ","authors_text":"Chunyang Wu, Egor Lakomkin, Frank Seide, Gil Keren, Jay Mahadeokar, Junteng Jia, Ozlem Kalinli, Wei Zhou, Xiaohui Zhang","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-02T01:54:35Z","title":"Efficient Streaming LLM for Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03752","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":"sha256:492db0032982cebfcdba7d21892a2974dd770576daba56c24a389e15a8bae21f","target":"record","created_at":"2026-07-05T09:16:24Z","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":"aecd8530554c6d5cf0a06896ce086db2188a431562d4cfd171c4ffd94da67fe5","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-02T01:54:35Z","title_canon_sha256":"ccfc40dcdee38734e70dd5e61ca1eccd153c5a4af5c97b2edb49e4e62eadafa3"},"schema_version":"1.0","source":{"id":"2410.03752","kind":"arxiv","version":1}},"canonical_sha256":"10d0fc47d18375697da86ceca2e8e13500ac78e2cf5d8478dc350fe8ae7d43eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10d0fc47d18375697da86ceca2e8e13500ac78e2cf5d8478dc350fe8ae7d43eb","first_computed_at":"2026-07-05T09:16:24.436626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:24.436626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vl8Pif3CD5ICoQrBDFwdgY1ICE+T5XhcEECHMVWxR23Kg7NZ8yr5CJY9zIMqjaAwMpQqMOdmkwPVwlIAIKD1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:24.437092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03752","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:492db0032982cebfcdba7d21892a2974dd770576daba56c24a389e15a8bae21f","sha256:5dfaef681612dc7d4eec05bda4b436354782773cf189b86ee95dce031bd37fe6"],"state_sha256":"552f938d44f7ad381e996c5ee022d8a95a45229a803bcb46883d1b3fe1eeb158"}