{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VOCV3ED4OAP4LRKPCHLJA2VPYG","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":"acb35799c8dc209a279b4266b2deb26d1b5a058afbd8bfe1da52b6a71f4f73d2","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T23:24:55Z","title_canon_sha256":"744ee8d445e0702d208e36c0dfc8495535aec8a4fd38718d205b88a0484e5238"},"schema_version":"1.0","source":{"id":"2607.07985","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07985","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07985v1","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07985","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"VOCV3ED4OAP4","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"VOCV3ED4OAP4LRKP","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"VOCV3ED4","created_at":"2026-07-10T00:19:06Z"}],"graph_snapshots":[{"event_id":"sha256:8f89d3849278e1d407ebb34d9e82eacae77dc395e3146e3d186b14dcc5d82715","target":"graph","created_at":"2026-07-10T00:19:06Z","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/2607.07985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"A. Sayyad, H. Krishnan, J. Emmons, S. Jones, T. Lin","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T23:24:55Z","title":"A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07985","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":"sha256:31bc3b16e906809dd1f1c81cac1fba48b5defab635d0591fa468f175f37338e9","target":"record","created_at":"2026-07-10T00:19:06Z","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":"acb35799c8dc209a279b4266b2deb26d1b5a058afbd8bfe1da52b6a71f4f73d2","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T23:24:55Z","title_canon_sha256":"744ee8d445e0702d208e36c0dfc8495535aec8a4fd38718d205b88a0484e5238"},"schema_version":"1.0","source":{"id":"2607.07985","kind":"arxiv","version":1}},"canonical_sha256":"ab855d907c701fc5c54f11d6906aafc19169e16e8a8911dc9dd9ce45abd134bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab855d907c701fc5c54f11d6906aafc19169e16e8a8911dc9dd9ce45abd134bb","first_computed_at":"2026-07-10T00:19:06.606591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T00:19:06.606591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZdzmdTlq9NwU+AUCug00n0IqvYAd7xutDB/0F604F65pcSISTaGIXXWHPWlybcTGqPTORVGvDZ//tyuxi209Cg==","signature_status":"signed_v1","signed_at":"2026-07-10T00:19:06.606992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07985","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31bc3b16e906809dd1f1c81cac1fba48b5defab635d0591fa468f175f37338e9","sha256:8f89d3849278e1d407ebb34d9e82eacae77dc395e3146e3d186b14dcc5d82715"],"state_sha256":"acc632093fb40f9a745263155df18e20204c2faf449af02a4cd66d96a145eceb"}