{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5ZIL7FFXNQOD4VRPUJUGDQ4HMB","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":"b40b71148d00657c39c76463554c408b59570f69d43e487911a48ca463b42445","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T02:46:16Z","title_canon_sha256":"06ed02fcfc9995cfd94048977c13ed662f99f440bb6c917c3fffe689839cf961"},"schema_version":"1.0","source":{"id":"2606.31055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31055","created_at":"2026-07-01T01:17:27Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31055v1","created_at":"2026-07-01T01:17:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31055","created_at":"2026-07-01T01:17:27Z"},{"alias_kind":"pith_short_12","alias_value":"5ZIL7FFXNQOD","created_at":"2026-07-01T01:17:27Z"},{"alias_kind":"pith_short_16","alias_value":"5ZIL7FFXNQOD4VRP","created_at":"2026-07-01T01:17:27Z"},{"alias_kind":"pith_short_8","alias_value":"5ZIL7FFX","created_at":"2026-07-01T01:17:27Z"}],"graph_snapshots":[{"event_id":"sha256:5aa6868c1d4952d7affc8b61724ea9d6e949bf767e4c5cdc15f5eb2e446fc5cc","target":"graph","created_at":"2026-07-01T01:17:27Z","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/2606.31055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-to-speech (S2S) AI agents are advancing rapidly, yet evaluation lacks interpretable speech-native measures for conversational prosody and rhythm. Because $F_0$, speaking rate, articulation rate, and pausing shift with model-predicted speaker traits and interaction state, pooled human statistics can be poorly calibrated for evaluating a particular output. Using 4000+ hours of dyadic English conversation from the Seamless Interaction dataset, we construct matched reference regimes for $F_0$ mean, $F_0$ expressivity, speech rate, articulation rate, pause ratio, and mean pause duration. We ","authors_text":"Ashish Hallur, Georgi Tinchev, Laureano Moro-Velazquez, Thomas Thebaud, Venkatesh Ravichandran","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T02:46:16Z","title":"Reference-Based Prosody and Rhythm Evaluation for Spoken Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31055","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:afe68b1e6c5ece63fe355409518278a2b4f686fffa772a44ba52771c59de3d34","target":"record","created_at":"2026-07-01T01:17:27Z","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":"b40b71148d00657c39c76463554c408b59570f69d43e487911a48ca463b42445","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T02:46:16Z","title_canon_sha256":"06ed02fcfc9995cfd94048977c13ed662f99f440bb6c917c3fffe689839cf961"},"schema_version":"1.0","source":{"id":"2606.31055","kind":"arxiv","version":1}},"canonical_sha256":"ee50bf94b76c1c3e562fa26861c387604eee49029baef501beaeec2ab144bf94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee50bf94b76c1c3e562fa26861c387604eee49029baef501beaeec2ab144bf94","first_computed_at":"2026-07-01T01:17:27.769347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:27.769347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"92LKPXO+aM50o3LsVE5oSnRiR+LTcy1UVviXWjGKSZn1UQDDxbWxIOCVEumyaYjuW9FQ3HUDZz0oacIusMD2AA==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:27.769842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afe68b1e6c5ece63fe355409518278a2b4f686fffa772a44ba52771c59de3d34","sha256:5aa6868c1d4952d7affc8b61724ea9d6e949bf767e4c5cdc15f5eb2e446fc5cc"],"state_sha256":"5240531eb52454137f26112aac172ada116a5295a7763ab3a5a42fb457fa2bbb"}