{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C7XR2HGUC5IX5E2W3BMQ3PRIXF","short_pith_number":"pith:C7XR2HGU","schema_version":"1.0","canonical_sha256":"17ef1d1cd417517e9356d8590dbe28b951757d0ebd7821a9965782d7c4aa4dd9","source":{"kind":"arxiv","id":"2505.15061","version":1},"attestation_state":"computed","paper":{"title":"SHEET: A Multi-purpose Open-source Speech Human Evaluation Estimation Toolkit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Erica Cooper, Tomoki Toda, Wen-Chin Huang","submitted_at":"2025-05-21T03:30:23Z","abstract_excerpt":"We introduce SHEET, a multi-purpose open-source toolkit designed to accelerate subjective speech quality assessment (SSQA) research. SHEET stands for the Speech Human Evaluation Estimation Toolkit, which focuses on data-driven deep neural network-based models trained to predict human-labeled quality scores of speech samples. SHEET provides comprehensive training and evaluation scripts, multi-dataset and multi-model support, as well as pre-trained models accessible via Torch Hub and HuggingFace Spaces. To demonstrate its capabilities, we re-evaluated SSL-MOS, a speech self-supervised learning ("},"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":"2505.15061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-21T03:30:23Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"36567fb34a619c34c29113d91999b2a07ceccc8639b9fc10e98660864a788155","abstract_canon_sha256":"c0ff7e5a4e19b568ea1010d7c1a90090b14b49a89f8b842de2bec3a1ccc1909a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:39.959843Z","signature_b64":"cHzOdfQ7jV+gF0dBJtf1ZSdDWe9xs9iCftqEykMUsc7pvbK+JPQhDD0rdNN0U1b+nvO/EearMybAj/oIwMuhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17ef1d1cd417517e9356d8590dbe28b951757d0ebd7821a9965782d7c4aa4dd9","last_reissued_at":"2026-07-05T11:06:39.959389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:39.959389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SHEET: A Multi-purpose Open-source Speech Human Evaluation Estimation Toolkit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Erica Cooper, Tomoki Toda, Wen-Chin Huang","submitted_at":"2025-05-21T03:30:23Z","abstract_excerpt":"We introduce SHEET, a multi-purpose open-source toolkit designed to accelerate subjective speech quality assessment (SSQA) research. SHEET stands for the Speech Human Evaluation Estimation Toolkit, which focuses on data-driven deep neural network-based models trained to predict human-labeled quality scores of speech samples. SHEET provides comprehensive training and evaluation scripts, multi-dataset and multi-model support, as well as pre-trained models accessible via Torch Hub and HuggingFace Spaces. To demonstrate its capabilities, we re-evaluated SSL-MOS, a speech self-supervised learning ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15061","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/2505.15061/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":"2505.15061","created_at":"2026-07-05T11:06:39.959449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15061v1","created_at":"2026-07-05T11:06:39.959449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15061","created_at":"2026-07-05T11:06:39.959449+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7XR2HGUC5IX","created_at":"2026-07-05T11:06:39.959449+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7XR2HGUC5IX5E2W","created_at":"2026-07-05T11:06:39.959449+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7XR2HGU","created_at":"2026-07-05T11:06:39.959449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12260","citing_title":"Improving Speech Enhancement with Multi-Metric Supervision from Learned Quality Assessment","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7XR2HGUC5IX5E2W3BMQ3PRIXF","json":"https://pith.science/pith/C7XR2HGUC5IX5E2W3BMQ3PRIXF.json","graph_json":"https://pith.science/api/pith-number/C7XR2HGUC5IX5E2W3BMQ3PRIXF/graph.json","events_json":"https://pith.science/api/pith-number/C7XR2HGUC5IX5E2W3BMQ3PRIXF/events.json","paper":"https://pith.science/paper/C7XR2HGU"},"agent_actions":{"view_html":"https://pith.science/pith/C7XR2HGUC5IX5E2W3BMQ3PRIXF","download_json":"https://pith.science/pith/C7XR2HGUC5IX5E2W3BMQ3PRIXF.json","view_paper":"https://pith.science/paper/C7XR2HGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15061&json=true","fetch_graph":"https://pith.science/api/pith-number/C7XR2HGUC5IX5E2W3BMQ3PRIXF/graph.json","fetch_events":"https://pith.science/api/pith-number/C7XR2HGUC5IX5E2W3BMQ3PRIXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7XR2HGUC5IX5E2W3BMQ3PRIXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7XR2HGUC5IX5E2W3BMQ3PRIXF/action/storage_attestation","attest_author":"https://pith.science/pith/C7XR2HGUC5IX5E2W3BMQ3PRIXF/action/author_attestation","sign_citation":"https://pith.science/pith/C7XR2HGUC5IX5E2W3BMQ3PRIXF/action/citation_signature","submit_replication":"https://pith.science/pith/C7XR2HGUC5IX5E2W3BMQ3PRIXF/action/replication_record"}},"created_at":"2026-07-05T11:06:39.959449+00:00","updated_at":"2026-07-05T11:06:39.959449+00:00"}