{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VOR3S37BGUMEBAZIFXF6CUAN6T","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":"bf5183829dde14d9353846332737c7d322b03e5b0e56e0facf52b81180f92468","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T06:04:18Z","title_canon_sha256":"228c2b04bc50208fec33ab35076fa51b010ea590ca7812b77b6648d318d358bf"},"schema_version":"1.0","source":{"id":"2606.05739","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05739","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05739v1","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05739","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"VOR3S37BGUME","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"VOR3S37BGUMEBAZI","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"VOR3S37B","created_at":"2026-06-05T01:15:01Z"}],"graph_snapshots":[{"event_id":"sha256:09d17bbdc18ba53e20302a605881d8c4dc753449b050f374305a56e0d7c04e32","target":"graph","created_at":"2026-06-05T01:15:01Z","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/2606.05739/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study presents a comparative analysis between the speaker embeddings of speech foundation models and human subjective perception of speaker similarity. Human listeners have the ability to judge speaker similarity on a continuous scale discerning how similar two voices are. In contrast, speech foundation models embed speaker characteristics into numerical representation. However, a question remains: does the numerical distance between speaker embeddings in these models truly align with the similarity perceived by humans? To address this, we conduct a comprehensive investigation using more ","authors_text":"Hayato Yagi, Minoru Kishi, Shinnosuke Takamichi, Yuki Saito","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T06:04:18Z","title":"Do speech foundation models perceive speaker similarity as humans do?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05739","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":"sha256:1a2110ba7d2a34ccdc06a348e27e64e2fd36d35d7325f0f51dcee457c0aab263","target":"record","created_at":"2026-06-05T01:15:01Z","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":"bf5183829dde14d9353846332737c7d322b03e5b0e56e0facf52b81180f92468","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T06:04:18Z","title_canon_sha256":"228c2b04bc50208fec33ab35076fa51b010ea590ca7812b77b6648d318d358bf"},"schema_version":"1.0","source":{"id":"2606.05739","kind":"arxiv","version":1}},"canonical_sha256":"aba3b96fe135184083282dcbe1500df4fda4af10621d4745808766b5ef182136","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aba3b96fe135184083282dcbe1500df4fda4af10621d4745808766b5ef182136","first_computed_at":"2026-06-05T01:15:01.276370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:01.276370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BHfhXzU0O+5yCc80anOmdfD4UQTllDUalE6BpdrG61IEcrerYQs6lqj9bALo/ttmVV17FyVwxHU+HPLvXoEtBw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:01.276891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05739","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a2110ba7d2a34ccdc06a348e27e64e2fd36d35d7325f0f51dcee457c0aab263","sha256:09d17bbdc18ba53e20302a605881d8c4dc753449b050f374305a56e0d7c04e32"],"state_sha256":"eaf2f17c7df67c448f867fb00f9f6175880d15992866d6f43862f61e6635bf8b"}