{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VBR74DB36WLALULVOFRLWM3ENL","short_pith_number":"pith:VBR74DB3","schema_version":"1.0","canonical_sha256":"a863fe0c3bf59605d1757162bb33646ae8517d56d847095e51d2f007fa60c623","source":{"kind":"arxiv","id":"2506.08633","version":1},"attestation_state":"computed","paper":{"title":"Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Bolaji Yusuf, Jan \\v{C}ernock\\'y, J\\'an \\v{S}vec, Old\\v{r}ich Plchot, Pradyoth Hegde, Santosh Kesiraju, \\v{S}imon Sedl\\'a\\v{c}ek","submitted_at":"2025-06-10T09:46:29Z","abstract_excerpt":"In this work, we approach spoken Dialogue State Tracking (DST) by bridging the representation spaces of speech encoders and LLMs via a small connector module, with a focus on fully open-sourced and open-data components (WavLM-large, OLMo). We focus on ablating different aspects of such systems including full/LoRA adapter fine-tuning, the effect of agent turns in the dialogue history, as well as fuzzy matching-based output post-processing, which greatly improves performance of our systems on named entities in the dialogue slot values. We conduct our experiments on the SpokenWOZ dataset, and add"},"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":"2506.08633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-10T09:46:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1e0ba14ab4a58f3743003696db4484d5d456a12f3e99f369b3d91deef10100b9","abstract_canon_sha256":"006cdcea16876b635ffc13fec8a0c3098b185dd412f8838aa10305c6b941ab9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:10.804669Z","signature_b64":"1x51NahxyFetN9oOwHeMCvZmRrZVZ4u4DYX8032iyi8tARPZWBmIGoRSjLUMP90Juu1O6qW28VLzYCB/Fqi8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a863fe0c3bf59605d1757162bb33646ae8517d56d847095e51d2f007fa60c623","last_reissued_at":"2026-07-05T11:19:10.804134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:10.804134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Bolaji Yusuf, Jan \\v{C}ernock\\'y, J\\'an \\v{S}vec, Old\\v{r}ich Plchot, Pradyoth Hegde, Santosh Kesiraju, \\v{S}imon Sedl\\'a\\v{c}ek","submitted_at":"2025-06-10T09:46:29Z","abstract_excerpt":"In this work, we approach spoken Dialogue State Tracking (DST) by bridging the representation spaces of speech encoders and LLMs via a small connector module, with a focus on fully open-sourced and open-data components (WavLM-large, OLMo). We focus on ablating different aspects of such systems including full/LoRA adapter fine-tuning, the effect of agent turns in the dialogue history, as well as fuzzy matching-based output post-processing, which greatly improves performance of our systems on named entities in the dialogue slot values. We conduct our experiments on the SpokenWOZ dataset, and add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08633","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/2506.08633/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":"2506.08633","created_at":"2026-07-05T11:19:10.804189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08633v1","created_at":"2026-07-05T11:19:10.804189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08633","created_at":"2026-07-05T11:19:10.804189+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBR74DB36WLA","created_at":"2026-07-05T11:19:10.804189+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBR74DB36WLALULV","created_at":"2026-07-05T11:19:10.804189+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBR74DB3","created_at":"2026-07-05T11:19:10.804189+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.20898","citing_title":"Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBR74DB36WLALULVOFRLWM3ENL","json":"https://pith.science/pith/VBR74DB36WLALULVOFRLWM3ENL.json","graph_json":"https://pith.science/api/pith-number/VBR74DB36WLALULVOFRLWM3ENL/graph.json","events_json":"https://pith.science/api/pith-number/VBR74DB36WLALULVOFRLWM3ENL/events.json","paper":"https://pith.science/paper/VBR74DB3"},"agent_actions":{"view_html":"https://pith.science/pith/VBR74DB36WLALULVOFRLWM3ENL","download_json":"https://pith.science/pith/VBR74DB36WLALULVOFRLWM3ENL.json","view_paper":"https://pith.science/paper/VBR74DB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08633&json=true","fetch_graph":"https://pith.science/api/pith-number/VBR74DB36WLALULVOFRLWM3ENL/graph.json","fetch_events":"https://pith.science/api/pith-number/VBR74DB36WLALULVOFRLWM3ENL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBR74DB36WLALULVOFRLWM3ENL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBR74DB36WLALULVOFRLWM3ENL/action/storage_attestation","attest_author":"https://pith.science/pith/VBR74DB36WLALULVOFRLWM3ENL/action/author_attestation","sign_citation":"https://pith.science/pith/VBR74DB36WLALULVOFRLWM3ENL/action/citation_signature","submit_replication":"https://pith.science/pith/VBR74DB36WLALULVOFRLWM3ENL/action/replication_record"}},"created_at":"2026-07-05T11:19:10.804189+00:00","updated_at":"2026-07-05T11:19:10.804189+00:00"}