{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AARRHGJCONWE3JZKYCCCR5QKIT","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":"aca183f5de69db958a06f914e57e2c3fddeff697810f3fbe3bf949c7a4f498cb","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T00:36:06Z","title_canon_sha256":"5ca3d579ce3627a3b245d0506aece34b9b6f51eb9b53364838b0e4d6a135202f"},"schema_version":"1.0","source":{"id":"2410.17485","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17485","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17485v2","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17485","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"AARRHGJCONWE","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"AARRHGJCONWE3JZK","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"AARRHGJC","created_at":"2026-07-05T10:10:45Z"}],"graph_snapshots":[{"event_id":"sha256:a50b7e2d3eac05886f94603ecdea7d54e2ac85b85c4aa0a329162af57f7312dd","target":"graph","created_at":"2026-07-05T10:10:45Z","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/2410.17485/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have augmented large language models (LLMs) with speech capabilities, leading to the development of speech language models (SpeechLMs). Earlier SpeechLMs focused on single-turn speech-based question answering (QA), where user input comprised a speech context and a text question. More recent studies have extended this to multi-turn conversations, though they often require complex, multi-stage supervised fine-tuning (SFT) with diverse data. Another critical challenge with SpeechLMs is catastrophic forgetting, where models optimized for speech tasks suffer significant degradation i","authors_text":"Boris Ginsburg, He Huang, Jagadeesh Balam, Ke Hu, Krishna C. Puvvada, Kunal Dhawan, Piotr Zelasko, Shinji Watanabe, Yifan Peng, Zhehuai Chen","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T00:36:06Z","title":"VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17485","kind":"arxiv","version":2},"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":"sha256:6407d8712cee00647323cd8a44088ada91b51db1a46246fc99c04f0830d54537","target":"record","created_at":"2026-07-05T10:10:45Z","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":"aca183f5de69db958a06f914e57e2c3fddeff697810f3fbe3bf949c7a4f498cb","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T00:36:06Z","title_canon_sha256":"5ca3d579ce3627a3b245d0506aece34b9b6f51eb9b53364838b0e4d6a135202f"},"schema_version":"1.0","source":{"id":"2410.17485","kind":"arxiv","version":2}},"canonical_sha256":"0023139922736c4da72ac08428f60a44f6e1229192a70baa9ad20892449cf33b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0023139922736c4da72ac08428f60a44f6e1229192a70baa9ad20892449cf33b","first_computed_at":"2026-07-05T10:10:45.301107Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:45.301107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cW4z/AdF3vdoz07qj/LLTQNUmJwmJebFCSWHbbPbw8Ts/71k8loFQaBp4NOHvZf7m/NzcRlhiHO2hbFCjGdqCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:45.301526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17485","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6407d8712cee00647323cd8a44088ada91b51db1a46246fc99c04f0830d54537","sha256:a50b7e2d3eac05886f94603ecdea7d54e2ac85b85c4aa0a329162af57f7312dd"],"state_sha256":"e1b02e2c89066e1460f8c48264c2b3e697ebf754dc19e226f96d5e947bb1e0ee"}