{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SUQJ7ZMPS2OJVGSXHQIK7XI2LO","short_pith_number":"pith:SUQJ7ZMP","schema_version":"1.0","canonical_sha256":"95209fe58f969c9a9a573c10afdd1a5b838b5490ad85c78834250c351433fe02","source":{"kind":"arxiv","id":"2606.21453","version":1},"attestation_state":"computed","paper":{"title":"CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.HC","authors_text":"Donghyuk Jung, Hyeonyu Kim, Myeongkyun Cho, Taeyoun Kwon, Youngwon Choi","submitted_at":"2026-06-19T14:11:10Z","abstract_excerpt":"Task-oriented voice agents need to map spoken user requests to structured outputs such as semantic frames, executable actions, and function calls. A common approach is to cascade ASR with a text-based LLM, but transcription errors can propagate to downstream structured output generation, especially under noisy conditions. Spoken language models (SLMs) offer a direct speech-based alternative, yet adapting them to new tasks typically requires paired speech-target annotations. Motivated by this gap, we present CORTIS, a text-only adaptation framework for task-oriented voice agents. CORTIS fine-tu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.21453","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-06-19T14:11:10Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"e4d853031f340de72ee1c96002200dcf723ac3f08f3f92b365295c7c60849b8b","abstract_canon_sha256":"159c032dd40457559ced0d5e31889a2c4957005ce048d808859cfa72df539a9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:10.877779Z","signature_b64":"2NjX7imgHgcj2o0OcbiBcgwPACdmC8Uy9zDmDlz4+zNHVzjudpcd4vs2U4nvyLLBvAlzKAaeErXHW82d/IOvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95209fe58f969c9a9a573c10afdd1a5b838b5490ad85c78834250c351433fe02","last_reissued_at":"2026-06-23T01:13:10.877291Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:10.877291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.HC","authors_text":"Donghyuk Jung, Hyeonyu Kim, Myeongkyun Cho, Taeyoun Kwon, Youngwon Choi","submitted_at":"2026-06-19T14:11:10Z","abstract_excerpt":"Task-oriented voice agents need to map spoken user requests to structured outputs such as semantic frames, executable actions, and function calls. A common approach is to cascade ASR with a text-based LLM, but transcription errors can propagate to downstream structured output generation, especially under noisy conditions. Spoken language models (SLMs) offer a direct speech-based alternative, yet adapting them to new tasks typically requires paired speech-target annotations. Motivated by this gap, we present CORTIS, a text-only adaptation framework for task-oriented voice agents. CORTIS fine-tu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21453","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.21453/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.21453","created_at":"2026-06-23T01:13:10.877395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21453v1","created_at":"2026-06-23T01:13:10.877395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21453","created_at":"2026-06-23T01:13:10.877395+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUQJ7ZMPS2OJ","created_at":"2026-06-23T01:13:10.877395+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUQJ7ZMPS2OJVGSX","created_at":"2026-06-23T01:13:10.877395+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUQJ7ZMP","created_at":"2026-06-23T01:13:10.877395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUQJ7ZMPS2OJVGSXHQIK7XI2LO","json":"https://pith.science/pith/SUQJ7ZMPS2OJVGSXHQIK7XI2LO.json","graph_json":"https://pith.science/api/pith-number/SUQJ7ZMPS2OJVGSXHQIK7XI2LO/graph.json","events_json":"https://pith.science/api/pith-number/SUQJ7ZMPS2OJVGSXHQIK7XI2LO/events.json","paper":"https://pith.science/paper/SUQJ7ZMP"},"agent_actions":{"view_html":"https://pith.science/pith/SUQJ7ZMPS2OJVGSXHQIK7XI2LO","download_json":"https://pith.science/pith/SUQJ7ZMPS2OJVGSXHQIK7XI2LO.json","view_paper":"https://pith.science/paper/SUQJ7ZMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21453&json=true","fetch_graph":"https://pith.science/api/pith-number/SUQJ7ZMPS2OJVGSXHQIK7XI2LO/graph.json","fetch_events":"https://pith.science/api/pith-number/SUQJ7ZMPS2OJVGSXHQIK7XI2LO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUQJ7ZMPS2OJVGSXHQIK7XI2LO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUQJ7ZMPS2OJVGSXHQIK7XI2LO/action/storage_attestation","attest_author":"https://pith.science/pith/SUQJ7ZMPS2OJVGSXHQIK7XI2LO/action/author_attestation","sign_citation":"https://pith.science/pith/SUQJ7ZMPS2OJVGSXHQIK7XI2LO/action/citation_signature","submit_replication":"https://pith.science/pith/SUQJ7ZMPS2OJVGSXHQIK7XI2LO/action/replication_record"}},"created_at":"2026-06-23T01:13:10.877395+00:00","updated_at":"2026-06-23T01:13:10.877395+00:00"}