{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AKM7SE6P3ZFPX3HJHPWIQ2GSVP","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":"f5365e1c22ad02e8e627226d0cc6c83ff64e793ccaee920ae1af1fd869bf0ddc","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T09:01:03Z","title_canon_sha256":"26ea71d0a6bf7db81f3c470bd98b616e1f2116126e0424828b65a70464595a6d"},"schema_version":"1.0","source":{"id":"2607.08256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08256","created_at":"2026-07-10T01:19:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08256v1","created_at":"2026-07-10T01:19:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08256","created_at":"2026-07-10T01:19:31Z"},{"alias_kind":"pith_short_12","alias_value":"AKM7SE6P3ZFP","created_at":"2026-07-10T01:19:31Z"},{"alias_kind":"pith_short_16","alias_value":"AKM7SE6P3ZFPX3HJ","created_at":"2026-07-10T01:19:31Z"},{"alias_kind":"pith_short_8","alias_value":"AKM7SE6P","created_at":"2026-07-10T01:19:31Z"}],"graph_snapshots":[{"event_id":"sha256:96e797bd6709e77df9b51ed6d08257ca7e4ee63bc3b82faac8623152c8a09a36","target":"graph","created_at":"2026-07-10T01:19:31Z","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/2607.08256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Best-of-$N$ (BoN) inference improves content consistency in zero-shot text-to-speech by selecting from $N$ candidates with an automatic speech recognition (ASR) verifier. We identify an underexplored evaluation confound: a verifier's apparent quality depends strongly on which ASR family judges it. On LibriSpeech-PC test-clean~\\citep{librispeechpc} with F5-TTS~\\citep{f5tts}, verifier rankings reverse across Whisper, wav2vec~2.0, and HuBERT evaluators, and same-family verifier-evaluator pairs recover 2-3$\\times$ more oracle headroom than cross-family pairs despite near-identical representations ","authors_text":"Seongjae Kang, Taehyung Yu","cross_cats":["cs.AI","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T09:01:03Z","title":"Best-of-$N$ TTS Evaluation is Confounded by ASR Family Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08256","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":"sha256:0273606667a47a9ade2f2673cc24b9fd99b1e193c2fabe509ed6db8daa49844e","target":"record","created_at":"2026-07-10T01:19:31Z","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":"f5365e1c22ad02e8e627226d0cc6c83ff64e793ccaee920ae1af1fd869bf0ddc","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T09:01:03Z","title_canon_sha256":"26ea71d0a6bf7db81f3c470bd98b616e1f2116126e0424828b65a70464595a6d"},"schema_version":"1.0","source":{"id":"2607.08256","kind":"arxiv","version":1}},"canonical_sha256":"0299f913cfde4afbece93bec8868d2abd50cbd1989ae00e13e9331b0f469929e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0299f913cfde4afbece93bec8868d2abd50cbd1989ae00e13e9331b0f469929e","first_computed_at":"2026-07-10T01:19:31.030733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:31.030733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RXV61hAK22QBopdmIgn3CECtUR/704FTxL5Ldo+3/i2NU8/+jq0PiwgPyRed6mCRosSAc1pxMaxm5zCfF15WDg==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:31.031136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0273606667a47a9ade2f2673cc24b9fd99b1e193c2fabe509ed6db8daa49844e","sha256:96e797bd6709e77df9b51ed6d08257ca7e4ee63bc3b82faac8623152c8a09a36"],"state_sha256":"a24b09d080b38f8b0fd678d03c97aa5f2e7dce731fdd4b5e1045ea0b442c8548"}