{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N3ENU2IHEMXUSD7LFBUR2W3V2J","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":"59e1eacf790c2a30d7f523c081898c06b6995bfc82f13ae216972e6d9028236d","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-30T07:01:21Z","title_canon_sha256":"18724d28dbf2ed9717292b49a51e1cff161ed42455afe140d256eba4ccf66c5d"},"schema_version":"1.0","source":{"id":"2409.20007","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.20007","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2409.20007v2","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20007","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"N3ENU2IHEMXU","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"pith_short_16","alias_value":"N3ENU2IHEMXUSD7L","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"pith_short_8","alias_value":"N3ENU2IH","created_at":"2026-07-05T11:44:41Z"}],"graph_snapshots":[{"event_id":"sha256:813b5184093796b6ae2d91b2d8f88ccddace4afa014ad65cd082fc193c006ca2","target":"graph","created_at":"2026-07-05T11:44:41Z","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/2409.20007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent end-to-end speech language models (SLMs) have expanded upon the capabilities of large language models (LLMs) by incorporating pre-trained speech models. However, these SLMs often undergo extensive speech instruction-tuning to bridge the gap between speech and text modalities. This requires significant annotation efforts and risks catastrophic forgetting of the original language capabilities. In this work, we present a simple yet effective automatic process for creating speech-text pair data that carefully injects speech paralinguistic understanding abilities into SLMs while preserving t","authors_text":"Boris Ginsburg, Chao-Han Huck Yang, Hung-yi Lee, Jagadeesh Balam, Ke-Han Lu, Szu-Wei Fu, Yu-Chiang Frank Wang, Zhehuai Chen","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-30T07:01:21Z","title":"DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20007","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":"sha256:602c5dd55cd47b0c17926ea139f91b951332ca964f0d8c4fa4a34d550eb65476","target":"record","created_at":"2026-07-05T11:44:41Z","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":"59e1eacf790c2a30d7f523c081898c06b6995bfc82f13ae216972e6d9028236d","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-30T07:01:21Z","title_canon_sha256":"18724d28dbf2ed9717292b49a51e1cff161ed42455afe140d256eba4ccf66c5d"},"schema_version":"1.0","source":{"id":"2409.20007","kind":"arxiv","version":2}},"canonical_sha256":"6ec8da6907232f490feb28691d5b75d254bec7d1a52b94f3e9ebaefa9a756b2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ec8da6907232f490feb28691d5b75d254bec7d1a52b94f3e9ebaefa9a756b2b","first_computed_at":"2026-07-05T11:44:41.594212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:41.594212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2oeuLu3JMFkCWiRwvHc54CyA10GpXeyrmR00h3T1I1B+N7BE/a1Gni+8phgqEX8XW74smL1dGuPdgQo7OheYBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:41.594706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.20007","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:602c5dd55cd47b0c17926ea139f91b951332ca964f0d8c4fa4a34d550eb65476","sha256:813b5184093796b6ae2d91b2d8f88ccddace4afa014ad65cd082fc193c006ca2"],"state_sha256":"cb3c619d524149b239b2d579de9706d5fd781220d2d6fb11831efe940e3fcf05"}