{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:L4HFSCBBKGA3MKZIN2S2VJLSIN","short_pith_number":"pith:L4HFSCBB","schema_version":"1.0","canonical_sha256":"5f0e5908215181b62b286ea5aaa572436e4cfdd22d5824958891225929630e3b","source":{"kind":"arxiv","id":"2108.07118","version":1},"attestation_state":"computed","paper":{"title":"NIST SRE CTS Superset: A large-scale dataset for telephony speaker recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Seyed Omid Sadjadi","submitted_at":"2021-08-16T14:39:23Z","abstract_excerpt":"This document provides a brief description of the National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) conversational telephone speech (CTS) Superset. The CTS Superset has been created in an attempt to provide the research community with a large-scale dataset along with uniform metadata that can be used to effectively train and develop telephony (narrowband) speaker recognition systems. It contains a large number of telephony speech segments from more than 6800 speakers with speech durations distributed uniformly in the [10s, 60s] range. The segments have "},"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":"2108.07118","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-08-16T14:39:23Z","cross_cats_sorted":["cs.AI","eess.AS","stat.ML"],"title_canon_sha256":"76eac8d8c95ed5956da4bc9793b5c7125089025f47fa7c1ce4f66ba44e1e962c","abstract_canon_sha256":"3b453923974ad684793ee61445f5ea5205b790ebbe80ff25db26a9103c644e7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:01.501071Z","signature_b64":"pu2hk+/CniN5Tyr+AoyZpzExd/u4S6j66YVTcxqSNEz/FDm0C/PqwU5sP3/VUQmHkH1IU0hV8D5RdCx7X/9JAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f0e5908215181b62b286ea5aaa572436e4cfdd22d5824958891225929630e3b","last_reissued_at":"2026-07-05T03:06:01.500680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:01.500680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NIST SRE CTS Superset: A large-scale dataset for telephony speaker recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Seyed Omid Sadjadi","submitted_at":"2021-08-16T14:39:23Z","abstract_excerpt":"This document provides a brief description of the National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) conversational telephone speech (CTS) Superset. The CTS Superset has been created in an attempt to provide the research community with a large-scale dataset along with uniform metadata that can be used to effectively train and develop telephony (narrowband) speaker recognition systems. It contains a large number of telephony speech segments from more than 6800 speakers with speech durations distributed uniformly in the [10s, 60s] range. The segments have "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.07118","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/2108.07118/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":"2108.07118","created_at":"2026-07-05T03:06:01.500736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.07118v1","created_at":"2026-07-05T03:06:01.500736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.07118","created_at":"2026-07-05T03:06:01.500736+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4HFSCBBKGA3","created_at":"2026-07-05T03:06:01.500736+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4HFSCBBKGA3MKZI","created_at":"2026-07-05T03:06:01.500736+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4HFSCBB","created_at":"2026-07-05T03:06:01.500736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16441","citing_title":"SoCov: Semi-Orthogonal Parametric Pooling of Covariance Matrix for Speaker Recognition","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4HFSCBBKGA3MKZIN2S2VJLSIN","json":"https://pith.science/pith/L4HFSCBBKGA3MKZIN2S2VJLSIN.json","graph_json":"https://pith.science/api/pith-number/L4HFSCBBKGA3MKZIN2S2VJLSIN/graph.json","events_json":"https://pith.science/api/pith-number/L4HFSCBBKGA3MKZIN2S2VJLSIN/events.json","paper":"https://pith.science/paper/L4HFSCBB"},"agent_actions":{"view_html":"https://pith.science/pith/L4HFSCBBKGA3MKZIN2S2VJLSIN","download_json":"https://pith.science/pith/L4HFSCBBKGA3MKZIN2S2VJLSIN.json","view_paper":"https://pith.science/paper/L4HFSCBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.07118&json=true","fetch_graph":"https://pith.science/api/pith-number/L4HFSCBBKGA3MKZIN2S2VJLSIN/graph.json","fetch_events":"https://pith.science/api/pith-number/L4HFSCBBKGA3MKZIN2S2VJLSIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4HFSCBBKGA3MKZIN2S2VJLSIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4HFSCBBKGA3MKZIN2S2VJLSIN/action/storage_attestation","attest_author":"https://pith.science/pith/L4HFSCBBKGA3MKZIN2S2VJLSIN/action/author_attestation","sign_citation":"https://pith.science/pith/L4HFSCBBKGA3MKZIN2S2VJLSIN/action/citation_signature","submit_replication":"https://pith.science/pith/L4HFSCBBKGA3MKZIN2S2VJLSIN/action/replication_record"}},"created_at":"2026-07-05T03:06:01.500736+00:00","updated_at":"2026-07-05T03:06:01.500736+00:00"}