{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z3ZJ6F7LLSOPJNV5AOXDBWCGMD","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":"5a128520654090306949affb4cfaa89f53a330b30284d402a77cfe581d76c48b","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T22:07:33Z","title_canon_sha256":"cc1aff0c40e24222431cd381d9255e77065bc573d72a0d2d1e449eee97e4c79c"},"schema_version":"1.0","source":{"id":"2310.09424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09424","created_at":"2026-07-05T07:00:47Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09424v1","created_at":"2026-07-05T07:00:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09424","created_at":"2026-07-05T07:00:47Z"},{"alias_kind":"pith_short_12","alias_value":"Z3ZJ6F7LLSOP","created_at":"2026-07-05T07:00:47Z"},{"alias_kind":"pith_short_16","alias_value":"Z3ZJ6F7LLSOPJNV5","created_at":"2026-07-05T07:00:47Z"},{"alias_kind":"pith_short_8","alias_value":"Z3ZJ6F7L","created_at":"2026-07-05T07:00:47Z"}],"graph_snapshots":[{"event_id":"sha256:aefa4978d1de5b7aead40cca327edd52de165f12fec629e81c6658e26b5b43c9","target":"graph","created_at":"2026-07-05T07:00:47Z","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/2310.09424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel Speech Augmented Language Model (SALM) with {\\em multitask} and {\\em in-context} learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech input and associated task instructions. The unified SALM not only achieves performance on par with task-specific Conformer baselines for Automatic Speech Recognition (ASR) and Speech Translation (AST), but also exhibits zero-shot in-context learning capabilities, demonstrated through keyword-boosting task for ASR and AST. Moreover, {\\em speech supervised in-c","authors_text":"Andrei Andrusenko, Boris Ginsburg, He Huang, Jagadeesh Balam, Jason Li, Krishna C. Puvvada, Oleksii Hrinchuk, Subhankar Ghosh, Zhehuai Chen","cross_cats":["cs.HC","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T22:07:33Z","title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09424","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":"sha256:891518355b2d228599ecc1cddd84e1bee7ae899c1548e8afccae29353d914520","target":"record","created_at":"2026-07-05T07:00:47Z","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":"5a128520654090306949affb4cfaa89f53a330b30284d402a77cfe581d76c48b","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T22:07:33Z","title_canon_sha256":"cc1aff0c40e24222431cd381d9255e77065bc573d72a0d2d1e449eee97e4c79c"},"schema_version":"1.0","source":{"id":"2310.09424","kind":"arxiv","version":1}},"canonical_sha256":"cef29f17eb5c9cf4b6bd03ae30d84660e29c930fd3aab039cbca515e862ba24d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cef29f17eb5c9cf4b6bd03ae30d84660e29c930fd3aab039cbca515e862ba24d","first_computed_at":"2026-07-05T07:00:47.697431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:47.697431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XSoaPUl+QpkHt0IVauuZVVt0VxAfBhU2YBXpR9fkWJgDvwM4OCnbgG++vSo321e8bEM2EsZiCvX4WTEeRdEOBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:47.697878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.09424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:891518355b2d228599ecc1cddd84e1bee7ae899c1548e8afccae29353d914520","sha256:aefa4978d1de5b7aead40cca327edd52de165f12fec629e81c6658e26b5b43c9"],"state_sha256":"a3c0fae93bd965e7b2471ed308478fab08f98e09e1679247478f0bf776c33370"}