{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IVUYVNGGHZOZXV4BEZJAVNEKAN","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":"772d5a5c05c0b533567c20b4e389d3b20adda803ced9fab74b84b1e83bcf1d23","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T04:00:14Z","title_canon_sha256":"1fe106ac6989c01156e8244edf82f2fd2e90f0973872c46f1b96ee6568fb53ca"},"schema_version":"1.0","source":{"id":"2606.31105","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31105","created_at":"2026-07-01T01:17:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31105v1","created_at":"2026-07-01T01:17:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31105","created_at":"2026-07-01T01:17:29Z"},{"alias_kind":"pith_short_12","alias_value":"IVUYVNGGHZOZ","created_at":"2026-07-01T01:17:29Z"},{"alias_kind":"pith_short_16","alias_value":"IVUYVNGGHZOZXV4B","created_at":"2026-07-01T01:17:29Z"},{"alias_kind":"pith_short_8","alias_value":"IVUYVNGG","created_at":"2026-07-01T01:17:29Z"}],"graph_snapshots":[{"event_id":"sha256:4377d459a592bdabd515e4a910ea3fb41c86d0ac2c4490753cbe28153ca5c75e","target":"graph","created_at":"2026-07-01T01:17:29Z","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/2606.31105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"UTMOS has become one of the most commonly used deep neural network-based speech quality assessment (SQA) metrics in speech processing research. In this paper, we attack UTMOS to probe its robustness. Starting from high-quality speech samples, we optimize the input in two directions: a score-preserving attack, which degrades perceived quality while maintaining the predicted score, and a quality-preserving attack, which lowers the predicted score while maintaining perceived quality. We consider three input spaces: raw waveform, mel spectrogram with a HiFi-GAN vocoder, and the latent space of EnC","authors_text":"Tomoki Toda, Wen-Chin Huang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T04:00:14Z","title":"Attacking UTMOS: Probing the Robustness of a Speech Quality Assessment Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31105","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":"sha256:0e419e20097f4907b225415dac3a9625d3493b5bd6f39b24d579bb3c2f3b5f12","target":"record","created_at":"2026-07-01T01:17:29Z","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":"772d5a5c05c0b533567c20b4e389d3b20adda803ced9fab74b84b1e83bcf1d23","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-30T04:00:14Z","title_canon_sha256":"1fe106ac6989c01156e8244edf82f2fd2e90f0973872c46f1b96ee6568fb53ca"},"schema_version":"1.0","source":{"id":"2606.31105","kind":"arxiv","version":1}},"canonical_sha256":"45698ab4c63e5d9bd78126520ab48a0346971c55d2aace0533e8e7d021793b17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45698ab4c63e5d9bd78126520ab48a0346971c55d2aace0533e8e7d021793b17","first_computed_at":"2026-07-01T01:17:29.322230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:29.322230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EuwEG/kTGaeYX2kMki+H3bgZfcfFf3W+z2u90vrfIKZru5UHkPKaYeDBT3TEVCeYAw5a1ztQPTMNLKz0TzcnDw==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:29.322664Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31105","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e419e20097f4907b225415dac3a9625d3493b5bd6f39b24d579bb3c2f3b5f12","sha256:4377d459a592bdabd515e4a910ea3fb41c86d0ac2c4490753cbe28153ca5c75e"],"state_sha256":"bdc8df7c85d63b35003eb84a0f053070e3e74872632da678b98731692dd39120"}