{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P53EMQOYJ4SWOADEQ7BABL4JXN","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":"d17108efcd1357b4f3b6972aacdb54846ef5decc0a3fcb8f137c719491a8abdd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:04:48Z","title_canon_sha256":"50ea97663cb391393e9a3a952d9a857eee4466119fae3abb7a6e51d8fef00bf2"},"schema_version":"1.0","source":{"id":"2410.02678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02678","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02678v1","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02678","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"P53EMQOYJ4SW","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"P53EMQOYJ4SWOADE","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"P53EMQOY","created_at":"2026-07-05T09:15:24Z"}],"graph_snapshots":[{"event_id":"sha256:7f740e60d8fbaa24699126c5921c37fdd75c9ca5c4006858ec6282466b816e7b","target":"graph","created_at":"2026-07-05T09:15:24Z","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/2410.02678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Voice assistants, such as Siri and Google Assistant, typically model audio and text separately, resulting in lost speech information and increased complexity. Recent efforts to address this with end-to-end Speech Large Language Models (LLMs) trained with supervised finetuning (SFT)\n  have led to models ``forgetting\" capabilities from text-only LLMs. Our work proposes an alternative paradigm for training Speech LLMs without instruction data, using the response of a text-only LLM to transcripts as self-supervision. Importantly, this process can be performed without annotated responses. We show t","authors_text":"Diyi Yang, Ella Li, Michael Ryan, Weiyan Shi, William Held, Yanzhe Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:04:48Z","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02678","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":"sha256:822b483067a34fe0513382d772dceb01038437747eabe070e7b34e24ee478de2","target":"record","created_at":"2026-07-05T09:15:24Z","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":"d17108efcd1357b4f3b6972aacdb54846ef5decc0a3fcb8f137c719491a8abdd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:04:48Z","title_canon_sha256":"50ea97663cb391393e9a3a952d9a857eee4466119fae3abb7a6e51d8fef00bf2"},"schema_version":"1.0","source":{"id":"2410.02678","kind":"arxiv","version":1}},"canonical_sha256":"7f764641d84f2567006487c200af89bb7216c0dc1b078dbe49fa7b3c6e95fd6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f764641d84f2567006487c200af89bb7216c0dc1b078dbe49fa7b3c6e95fd6a","first_computed_at":"2026-07-05T09:15:24.066868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:24.066868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Iuk1Xlyb+fLNcp8EIm6uX/iz3jzWK2p8EPaXQLha1IrjPUsmHOYIRJIOzDiz/A/O6cx/VJ9TvfqN8e0CkGTBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:24.067303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:822b483067a34fe0513382d772dceb01038437747eabe070e7b34e24ee478de2","sha256:7f740e60d8fbaa24699126c5921c37fdd75c9ca5c4006858ec6282466b816e7b"],"state_sha256":"80567a8b975181b56b2e7e1a82206189e969f176344e0baab2b6822c74d0257e"}