{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UTOWSQAUI2NDS3ZYOIHUYTRQ3U","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":"608a2f62a3f6c5e5e639c4ed2f154a53572221142099d5d7bc0270122dd90800","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T20:28:57Z","title_canon_sha256":"f5e545f9e4dfd48d7aa1e89597693af0c5beaeade821a192b817a65ad2d30b66"},"schema_version":"1.0","source":{"id":"2309.10917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10917","created_at":"2026-07-05T06:52:28Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10917v1","created_at":"2026-07-05T06:52:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10917","created_at":"2026-07-05T06:52:28Z"},{"alias_kind":"pith_short_12","alias_value":"UTOWSQAUI2ND","created_at":"2026-07-05T06:52:28Z"},{"alias_kind":"pith_short_16","alias_value":"UTOWSQAUI2NDS3ZY","created_at":"2026-07-05T06:52:28Z"},{"alias_kind":"pith_short_8","alias_value":"UTOWSQAU","created_at":"2026-07-05T06:52:28Z"}],"graph_snapshots":[{"event_id":"sha256:e8d70db71a15059e80ec0887419faebfb6c5c566ae0f0993ce621f1bf1cf28f0","target":"graph","created_at":"2026-07-05T06:52:28Z","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/2309.10917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities. In this paper, we introduce a novel method for contextualizing speech recognition models incorporating LLMs. Our approach casts speech recognition as a mixed-modal language modeling task based on a pretrained LLM. We provide audio features, along with optional text tokens for context, to train the system to complete transcriptions in a decoder-only fashion. As a result, the system is implicitly incentivized to learn ","authors_text":"Christian Fuegen, Chunyang Wu, Egor Lakomkin, Michael L. Seltzer, Ozlem Kalinli, Yassir Fathullah","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T20:28:57Z","title":"End-to-End Speech Recognition Contextualization with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10917","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:e454c5978692270c95d2647f26a37e2a74b6b94153b8c73d18047613aa1c02fd","target":"record","created_at":"2026-07-05T06:52:28Z","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":"608a2f62a3f6c5e5e639c4ed2f154a53572221142099d5d7bc0270122dd90800","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T20:28:57Z","title_canon_sha256":"f5e545f9e4dfd48d7aa1e89597693af0c5beaeade821a192b817a65ad2d30b66"},"schema_version":"1.0","source":{"id":"2309.10917","kind":"arxiv","version":1}},"canonical_sha256":"a4dd694014469a396f38720f4c4e30dd314b83c57ed8453acfbc07fa63f0543f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4dd694014469a396f38720f4c4e30dd314b83c57ed8453acfbc07fa63f0543f","first_computed_at":"2026-07-05T06:52:28.487737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:28.487737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d5hOFofeC33GrRIC8GVbNU8MS3E/Bem3cI17o8TIkPHZaQWlQ1qFGWRtGFU5XQ1kgpsjML7XOu0JPHZdnUm4BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:28.488227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e454c5978692270c95d2647f26a37e2a74b6b94153b8c73d18047613aa1c02fd","sha256:e8d70db71a15059e80ec0887419faebfb6c5c566ae0f0993ce621f1bf1cf28f0"],"state_sha256":"65e7044da6787aad4e14753f26f7f4284983dc10bfa7a8946d1f47f456490088"}