{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LZMJIQZOGDAEDPPHXLO6TUAF5S","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":"74f64e90828d865503ace2746f9723a2ae771978e334de2b0682dd2165150592","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-12T15:43:10Z","title_canon_sha256":"a27e5ec5bcf6d547e8f73ca33e185b734da93e8ceb417bd13f7d5f6d3389a268"},"schema_version":"1.0","source":{"id":"2409.08148","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08148","created_at":"2026-07-05T09:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08148v1","created_at":"2026-07-05T09:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08148","created_at":"2026-07-05T09:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"LZMJIQZOGDAE","created_at":"2026-07-05T09:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"LZMJIQZOGDAEDPPH","created_at":"2026-07-05T09:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"LZMJIQZO","created_at":"2026-07-05T09:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:f91722e32665474edd3632d6cb524e2acb6b3de1080cc6d74c35011ac27bb5d8","target":"graph","created_at":"2026-07-05T09:06:20Z","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/2409.08148/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have become proficient at solving a wide variety of tasks, including those involving multi-modal inputs. In particular, instantiating an LLM (such as LLaMA) with a speech encoder and training it on paired data imparts speech recognition (ASR) abilities to the decoder-only model, hence called Speech-LLaMA. Nevertheless, due to the sequential nature of auto-regressive inference and the relatively large decoder, Speech-LLaMA models require relatively high inference time. In this work, we propose to speed up Speech-LLaMA inference by predicting multiple tokens in the s","authors_text":"Desh Raj, Gil Keren, Jay Mahadeokar, Junteng Jia, Ozlem Kalinli","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-12T15:43:10Z","title":"Faster Speech-LLaMA Inference with Multi-token Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08148","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:b28781e149c3ecc5632e5a2d35e651a335d00afb1d5268509c3ee298c6c005a2","target":"record","created_at":"2026-07-05T09:06:20Z","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":"74f64e90828d865503ace2746f9723a2ae771978e334de2b0682dd2165150592","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-12T15:43:10Z","title_canon_sha256":"a27e5ec5bcf6d547e8f73ca33e185b734da93e8ceb417bd13f7d5f6d3389a268"},"schema_version":"1.0","source":{"id":"2409.08148","kind":"arxiv","version":1}},"canonical_sha256":"5e5894432e30c041bde7badde9d005ecbf0fe13c6c827a32726947376bbd414f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e5894432e30c041bde7badde9d005ecbf0fe13c6c827a32726947376bbd414f","first_computed_at":"2026-07-05T09:06:20.938956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:20.938956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sFUkmTctOwjNQwUfv/46V/fgM/WKptjcJbErqtV1jXRtnqeBUqu5qlpxvscxKCARCcmTzPAqA7xSZ65+jeMbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:20.939436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08148","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b28781e149c3ecc5632e5a2d35e651a335d00afb1d5268509c3ee298c6c005a2","sha256:f91722e32665474edd3632d6cb524e2acb6b3de1080cc6d74c35011ac27bb5d8"],"state_sha256":"e989af8dd16b338761f2e048d9ee5d4071842aaa44544f168d1dcb6fc76c25e2"}