{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VBR74DB36WLALULVOFRLWM3ENL","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":"006cdcea16876b635ffc13fec8a0c3098b185dd412f8838aa10305c6b941ab9d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-10T09:46:29Z","title_canon_sha256":"1e0ba14ab4a58f3743003696db4484d5d456a12f3e99f369b3d91deef10100b9"},"schema_version":"1.0","source":{"id":"2506.08633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08633","created_at":"2026-07-05T11:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08633v1","created_at":"2026-07-05T11:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08633","created_at":"2026-07-05T11:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"VBR74DB36WLA","created_at":"2026-07-05T11:19:10Z"},{"alias_kind":"pith_short_16","alias_value":"VBR74DB36WLALULV","created_at":"2026-07-05T11:19:10Z"},{"alias_kind":"pith_short_8","alias_value":"VBR74DB3","created_at":"2026-07-05T11:19:10Z"}],"graph_snapshots":[{"event_id":"sha256:0af6eaa98249358a937858d97497789b8d14dcbf78a7850df9ae6ea4e025222f","target":"graph","created_at":"2026-07-05T11:19:10Z","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/2506.08633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-10T09:46:29Z","title":"Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08633","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:cdfdcad3ab38ff4f9a0d072d40ce098b8756263d516de4a9bc993a928b372637","target":"record","created_at":"2026-07-05T11:19:10Z","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":"006cdcea16876b635ffc13fec8a0c3098b185dd412f8838aa10305c6b941ab9d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-10T09:46:29Z","title_canon_sha256":"1e0ba14ab4a58f3743003696db4484d5d456a12f3e99f369b3d91deef10100b9"},"schema_version":"1.0","source":{"id":"2506.08633","kind":"arxiv","version":1}},"canonical_sha256":"a863fe0c3bf59605d1757162bb33646ae8517d56d847095e51d2f007fa60c623","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a863fe0c3bf59605d1757162bb33646ae8517d56d847095e51d2f007fa60c623","first_computed_at":"2026-07-05T11:19:10.804134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:10.804134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1x51NahxyFetN9oOwHeMCvZmRrZVZ4u4DYX8032iyi8tARPZWBmIGoRSjLUMP90Juu1O6qW28VLzYCB/Fqi8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:10.804669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdfdcad3ab38ff4f9a0d072d40ce098b8756263d516de4a9bc993a928b372637","sha256:0af6eaa98249358a937858d97497789b8d14dcbf78a7850df9ae6ea4e025222f"],"state_sha256":"3e3fcbf77322612e4935dcb8df26c91cb0a3a1603d020079511c144a8a4f9658"}