{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5ZIL7FFXNQOD4VRPUJUGDQ4HMB","short_pith_number":"pith:5ZIL7FFX","schema_version":"1.0","canonical_sha256":"ee50bf94b76c1c3e562fa26861c387604eee49029baef501beaeec2ab144bf94","source":{"kind":"arxiv","id":"2606.31055","version":1},"attestation_state":"computed","paper":{"title":"Reference-Based Prosody and Rhythm Evaluation for Spoken Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ashish Hallur, Georgi Tinchev, Laureano Moro-Velazquez, Thomas Thebaud, Venkatesh Ravichandran","submitted_at":"2026-06-30T02:46:16Z","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 "},"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":"2606.31055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T02:46:16Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"06ed02fcfc9995cfd94048977c13ed662f99f440bb6c917c3fffe689839cf961","abstract_canon_sha256":"b40b71148d00657c39c76463554c408b59570f69d43e487911a48ca463b42445"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:27.769842Z","signature_b64":"92LKPXO+aM50o3LsVE5oSnRiR+LTcy1UVviXWjGKSZn1UQDDxbWxIOCVEumyaYjuW9FQ3HUDZz0oacIusMD2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee50bf94b76c1c3e562fa26861c387604eee49029baef501beaeec2ab144bf94","last_reissued_at":"2026-07-01T01:17:27.769347Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:27.769347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reference-Based Prosody and Rhythm Evaluation for Spoken Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ashish Hallur, Georgi Tinchev, Laureano Moro-Velazquez, Thomas Thebaud, Venkatesh Ravichandran","submitted_at":"2026-06-30T02:46:16Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31055","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/2606.31055/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":"2606.31055","created_at":"2026-07-01T01:17:27.769411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31055v1","created_at":"2026-07-01T01:17:27.769411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31055","created_at":"2026-07-01T01:17:27.769411+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZIL7FFXNQOD","created_at":"2026-07-01T01:17:27.769411+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZIL7FFXNQOD4VRP","created_at":"2026-07-01T01:17:27.769411+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZIL7FFX","created_at":"2026-07-01T01:17:27.769411+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/5ZIL7FFXNQOD4VRPUJUGDQ4HMB","json":"https://pith.science/pith/5ZIL7FFXNQOD4VRPUJUGDQ4HMB.json","graph_json":"https://pith.science/api/pith-number/5ZIL7FFXNQOD4VRPUJUGDQ4HMB/graph.json","events_json":"https://pith.science/api/pith-number/5ZIL7FFXNQOD4VRPUJUGDQ4HMB/events.json","paper":"https://pith.science/paper/5ZIL7FFX"},"agent_actions":{"view_html":"https://pith.science/pith/5ZIL7FFXNQOD4VRPUJUGDQ4HMB","download_json":"https://pith.science/pith/5ZIL7FFXNQOD4VRPUJUGDQ4HMB.json","view_paper":"https://pith.science/paper/5ZIL7FFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31055&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZIL7FFXNQOD4VRPUJUGDQ4HMB/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZIL7FFXNQOD4VRPUJUGDQ4HMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZIL7FFXNQOD4VRPUJUGDQ4HMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZIL7FFXNQOD4VRPUJUGDQ4HMB/action/storage_attestation","attest_author":"https://pith.science/pith/5ZIL7FFXNQOD4VRPUJUGDQ4HMB/action/author_attestation","sign_citation":"https://pith.science/pith/5ZIL7FFXNQOD4VRPUJUGDQ4HMB/action/citation_signature","submit_replication":"https://pith.science/pith/5ZIL7FFXNQOD4VRPUJUGDQ4HMB/action/replication_record"}},"created_at":"2026-07-01T01:17:27.769411+00:00","updated_at":"2026-07-01T01:17:27.769411+00:00"}