{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VOCV3ED4OAP4LRKPCHLJA2VPYG","short_pith_number":"pith:VOCV3ED4","schema_version":"1.0","canonical_sha256":"ab855d907c701fc5c54f11d6906aafc19169e16e8a8911dc9dd9ce45abd134bb","source":{"kind":"arxiv","id":"2607.07985","version":1},"attestation_state":"computed","paper":{"title":"A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"A. Sayyad, H. Krishnan, J. Emmons, S. Jones, T. Lin","submitted_at":"2026-07-08T23:24:55Z","abstract_excerpt":"We report the empirical reliability of Gemini models as audio judges that score full-duplex agent conversations directly from the raw stereo waveform, tested across three models in the Gemini family: 2.5 Flash, 3.5 Flash, and 3.1 Pro. Our primary evidence base uses Gemini 2.5 Flash as the ground-truth model, validated against three calibrated human raters on 209 stereo sessions, scored on 8 production dimensions: 152 full-duplex conversations across 13 accent-and-condition strata, together with 57 adversarial defect-injected clips. The evidence for Gemini 2.5 Flash is consistent across three t"},"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":"2607.07985","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T23:24:55Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"744ee8d445e0702d208e36c0dfc8495535aec8a4fd38718d205b88a0484e5238","abstract_canon_sha256":"acb35799c8dc209a279b4266b2deb26d1b5a058afbd8bfe1da52b6a71f4f73d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T00:19:06.606992Z","signature_b64":"ZdzmdTlq9NwU+AUCug00n0IqvYAd7xutDB/0F604F65pcSISTaGIXXWHPWlybcTGqPTORVGvDZ//tyuxi209Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab855d907c701fc5c54f11d6906aafc19169e16e8a8911dc9dd9ce45abd134bb","last_reissued_at":"2026-07-10T00:19:06.606591Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T00:19:06.606591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"A. Sayyad, H. Krishnan, J. Emmons, S. Jones, T. Lin","submitted_at":"2026-07-08T23:24:55Z","abstract_excerpt":"We report the empirical reliability of Gemini models as audio judges that score full-duplex agent conversations directly from the raw stereo waveform, tested across three models in the Gemini family: 2.5 Flash, 3.5 Flash, and 3.1 Pro. Our primary evidence base uses Gemini 2.5 Flash as the ground-truth model, validated against three calibrated human raters on 209 stereo sessions, scored on 8 production dimensions: 152 full-duplex conversations across 13 accent-and-condition strata, together with 57 adversarial defect-injected clips. The evidence for Gemini 2.5 Flash is consistent across three t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07985","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/2607.07985/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":"2607.07985","created_at":"2026-07-10T00:19:06.606655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.07985v1","created_at":"2026-07-10T00:19:06.606655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07985","created_at":"2026-07-10T00:19:06.606655+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOCV3ED4OAP4","created_at":"2026-07-10T00:19:06.606655+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOCV3ED4OAP4LRKP","created_at":"2026-07-10T00:19:06.606655+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOCV3ED4","created_at":"2026-07-10T00:19:06.606655+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/VOCV3ED4OAP4LRKPCHLJA2VPYG","json":"https://pith.science/pith/VOCV3ED4OAP4LRKPCHLJA2VPYG.json","graph_json":"https://pith.science/api/pith-number/VOCV3ED4OAP4LRKPCHLJA2VPYG/graph.json","events_json":"https://pith.science/api/pith-number/VOCV3ED4OAP4LRKPCHLJA2VPYG/events.json","paper":"https://pith.science/paper/VOCV3ED4"},"agent_actions":{"view_html":"https://pith.science/pith/VOCV3ED4OAP4LRKPCHLJA2VPYG","download_json":"https://pith.science/pith/VOCV3ED4OAP4LRKPCHLJA2VPYG.json","view_paper":"https://pith.science/paper/VOCV3ED4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.07985&json=true","fetch_graph":"https://pith.science/api/pith-number/VOCV3ED4OAP4LRKPCHLJA2VPYG/graph.json","fetch_events":"https://pith.science/api/pith-number/VOCV3ED4OAP4LRKPCHLJA2VPYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOCV3ED4OAP4LRKPCHLJA2VPYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOCV3ED4OAP4LRKPCHLJA2VPYG/action/storage_attestation","attest_author":"https://pith.science/pith/VOCV3ED4OAP4LRKPCHLJA2VPYG/action/author_attestation","sign_citation":"https://pith.science/pith/VOCV3ED4OAP4LRKPCHLJA2VPYG/action/citation_signature","submit_replication":"https://pith.science/pith/VOCV3ED4OAP4LRKPCHLJA2VPYG/action/replication_record"}},"created_at":"2026-07-10T00:19:06.606655+00:00","updated_at":"2026-07-10T00:19:06.606655+00:00"}