{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZAN2G3SADG6OQUTCN57TW2EJEE","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":"7e13c45edbf183ed0fbbef11d33e055fbc4ff9beb7e5d752db813157ebf1d4fe","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-01T05:03:05Z","title_canon_sha256":"d5f343ca448dc347a2cd0e7d2b85540879563eb4c479a03a896b8d6bc98845ad"},"schema_version":"1.0","source":{"id":"2402.00340","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00340","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00340v2","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00340","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZAN2G3SADG6O","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZAN2G3SADG6OQUTC","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZAN2G3SA","created_at":"2026-07-05T08:31:11Z"}],"graph_snapshots":[{"event_id":"sha256:bddafbfd30e894d832e922ae8be33bd98968876d6f70a768bbe349db77fc58e2","target":"graph","created_at":"2026-07-05T08:31:11Z","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/2402.00340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised features are typically used in place of filter-bank features in speaker verification models. However, these models were originally designed to ingest filter-bank features as inputs, and thus, training them on top of self-supervised features assumes that both feature types require the same amount of learning for the task. In this work, we observe that pre-trained self-supervised speech features inherently include information required for downstream speaker verification task, and therefore, we can simplify the downstream model without sacrificing performance. To this end, we revi","authors_text":"Ahmed Hussen Abdelaziz, Barry-John Theobald, Jee-weon Jung, Shinji Watanabe, Skyler Seto, Stephen Shum, Takuya Higuchi, Tatiana Likhomanenko, Zakaria Aldeneh","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-01T05:03:05Z","title":"Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00340","kind":"arxiv","version":2},"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:b7cb94dd735cb6a33f267fdc6798e14c6fd6eb6ccbcc23dbd92fe9e8b26cd46f","target":"record","created_at":"2026-07-05T08:31:11Z","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":"7e13c45edbf183ed0fbbef11d33e055fbc4ff9beb7e5d752db813157ebf1d4fe","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-01T05:03:05Z","title_canon_sha256":"d5f343ca448dc347a2cd0e7d2b85540879563eb4c479a03a896b8d6bc98845ad"},"schema_version":"1.0","source":{"id":"2402.00340","kind":"arxiv","version":2}},"canonical_sha256":"c81ba36e4019bce852626f7f3b68892135f2728d732b8450b0804b629a1b1a69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c81ba36e4019bce852626f7f3b68892135f2728d732b8450b0804b629a1b1a69","first_computed_at":"2026-07-05T08:31:11.146134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:11.146134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Krkcckspm5jDssUsmXgVTdhAb1JGqKYZwKXkdHIuJrh2HDydr1eackvqBfGHcCORnVYtRKlOR9XhYqfA+NwHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:11.146650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.00340","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7cb94dd735cb6a33f267fdc6798e14c6fd6eb6ccbcc23dbd92fe9e8b26cd46f","sha256:bddafbfd30e894d832e922ae8be33bd98968876d6f70a768bbe349db77fc58e2"],"state_sha256":"3c6006cd051fda251a79ff86f94748e274ea241bf8ba719288863b1c068b33ee"}