{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HOQMGFNGSK2SSQYFPJHKEHJ32O","short_pith_number":"pith:HOQMGFNG","schema_version":"1.0","canonical_sha256":"3ba0c315a692b52943057a4ea21d3bd3b443969c93cfe30f234a4b5654f2ca28","source":{"kind":"arxiv","id":"2607.10146","version":1},"attestation_state":"computed","paper":{"title":"Evaluating SSL and ViViT Architectures for Cross-Corpus Audio MOS Prediction via LODO Validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ahmet Emir Dirik, Mustafa Ozan Duman","submitted_at":"2026-07-11T06:10:17Z","abstract_excerpt":"Automatic Mean Opinion Score (MOS) prediction is essential for evaluating large-scale synthetic speech and audio enhancement systems, yet models frequently struggle with domain shift. This study presents a comprehensive benchmarking of three architectural frameworks: Frozen Self-Supervised Learning (SSL-FRZ), Fine-Tuned SSL (SSL-FT), and a Video Vision Transformer (ViViT). Evaluation is conducted in two phases: Part I utilizes a consolidated corpus of 130,000 samples across 19 diverse datasets, while Part II focuses on a purified 17-dataset English-only corpus. To assess robustness, a systemat"},"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":"2607.10146","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-11T06:10:17Z","cross_cats_sorted":[],"title_canon_sha256":"4c84910049f0e0bdfcce21b87a00023d02be13961152ef0811a792cf73f1a58b","abstract_canon_sha256":"c779c32d536e0df79879cd2a80e1baf0c970daa1c027dc4a728e341c15fb5dba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:27.558677Z","signature_b64":"v3531Im+96UBMYKJ2ON00Mky8W3EV8MNuJ0CgmBmHmqhIf7ajxssTjJJ+LGwwiSwBd4g/NR0ZEWxikMBxAj3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ba0c315a692b52943057a4ea21d3bd3b443969c93cfe30f234a4b5654f2ca28","last_reissued_at":"2026-07-14T01:20:27.557876Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:27.557876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating SSL and ViViT Architectures for Cross-Corpus Audio MOS Prediction via LODO Validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ahmet Emir Dirik, Mustafa Ozan Duman","submitted_at":"2026-07-11T06:10:17Z","abstract_excerpt":"Automatic Mean Opinion Score (MOS) prediction is essential for evaluating large-scale synthetic speech and audio enhancement systems, yet models frequently struggle with domain shift. This study presents a comprehensive benchmarking of three architectural frameworks: Frozen Self-Supervised Learning (SSL-FRZ), Fine-Tuned SSL (SSL-FT), and a Video Vision Transformer (ViViT). Evaluation is conducted in two phases: Part I utilizes a consolidated corpus of 130,000 samples across 19 diverse datasets, while Part II focuses on a purified 17-dataset English-only corpus. To assess robustness, a systemat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10146","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/2607.10146/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":"2607.10146","created_at":"2026-07-14T01:20:27.558289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10146v1","created_at":"2026-07-14T01:20:27.558289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10146","created_at":"2026-07-14T01:20:27.558289+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOQMGFNGSK2S","created_at":"2026-07-14T01:20:27.558289+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOQMGFNGSK2SSQYF","created_at":"2026-07-14T01:20:27.558289+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOQMGFNG","created_at":"2026-07-14T01:20:27.558289+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/HOQMGFNGSK2SSQYFPJHKEHJ32O","json":"https://pith.science/pith/HOQMGFNGSK2SSQYFPJHKEHJ32O.json","graph_json":"https://pith.science/api/pith-number/HOQMGFNGSK2SSQYFPJHKEHJ32O/graph.json","events_json":"https://pith.science/api/pith-number/HOQMGFNGSK2SSQYFPJHKEHJ32O/events.json","paper":"https://pith.science/paper/HOQMGFNG"},"agent_actions":{"view_html":"https://pith.science/pith/HOQMGFNGSK2SSQYFPJHKEHJ32O","download_json":"https://pith.science/pith/HOQMGFNGSK2SSQYFPJHKEHJ32O.json","view_paper":"https://pith.science/paper/HOQMGFNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10146&json=true","fetch_graph":"https://pith.science/api/pith-number/HOQMGFNGSK2SSQYFPJHKEHJ32O/graph.json","fetch_events":"https://pith.science/api/pith-number/HOQMGFNGSK2SSQYFPJHKEHJ32O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOQMGFNGSK2SSQYFPJHKEHJ32O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOQMGFNGSK2SSQYFPJHKEHJ32O/action/storage_attestation","attest_author":"https://pith.science/pith/HOQMGFNGSK2SSQYFPJHKEHJ32O/action/author_attestation","sign_citation":"https://pith.science/pith/HOQMGFNGSK2SSQYFPJHKEHJ32O/action/citation_signature","submit_replication":"https://pith.science/pith/HOQMGFNGSK2SSQYFPJHKEHJ32O/action/replication_record"}},"created_at":"2026-07-14T01:20:27.558289+00:00","updated_at":"2026-07-14T01:20:27.558289+00:00"}