{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UGFILF3V5Q5AU2GZ562Z5IDSRG","short_pith_number":"pith:UGFILF3V","canonical_record":{"source":{"id":"2607.07579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-08T16:03:44Z","cross_cats_sorted":[],"title_canon_sha256":"5b9ff6ff44f327166f6c5bf0f5ad5c83d02cae14ef9220d0e566d5c3ca80297f","abstract_canon_sha256":"8bd766a357a0eb7cc04837dae0b5d6ece6cb3ac0700201d4b216e37ee207a3e7"},"schema_version":"1.0"},"canonical_sha256":"a18a859775ec3a0a68d9efb59ea07289a23561217637410991cbc05421c74818","source":{"kind":"arxiv","id":"2607.07579","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07579","created_at":"2026-07-09T01:20:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07579v1","created_at":"2026-07-09T01:20:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07579","created_at":"2026-07-09T01:20:30Z"},{"alias_kind":"pith_short_12","alias_value":"UGFILF3V5Q5A","created_at":"2026-07-09T01:20:30Z"},{"alias_kind":"pith_short_16","alias_value":"UGFILF3V5Q5AU2GZ","created_at":"2026-07-09T01:20:30Z"},{"alias_kind":"pith_short_8","alias_value":"UGFILF3V","created_at":"2026-07-09T01:20:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UGFILF3V5Q5AU2GZ562Z5IDSRG","target":"record","payload":{"canonical_record":{"source":{"id":"2607.07579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-08T16:03:44Z","cross_cats_sorted":[],"title_canon_sha256":"5b9ff6ff44f327166f6c5bf0f5ad5c83d02cae14ef9220d0e566d5c3ca80297f","abstract_canon_sha256":"8bd766a357a0eb7cc04837dae0b5d6ece6cb3ac0700201d4b216e37ee207a3e7"},"schema_version":"1.0"},"canonical_sha256":"a18a859775ec3a0a68d9efb59ea07289a23561217637410991cbc05421c74818","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:30.089096Z","signature_b64":"7+asS5JEqdoXilz2jZpNn6POiXxozuwTAl2ma7xQ6Yetki6XHrV2s++LbX2Z/o8buUssXE2yJIB1qDlzB06KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a18a859775ec3a0a68d9efb59ea07289a23561217637410991cbc05421c74818","last_reissued_at":"2026-07-09T01:20:30.088673Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:30.088673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.07579","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T01:20:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iU0Xeeizji9RM1svWlWNK2L9pwLavtJhJRrsPzSPkY/aFczL/qURyi/v/J/4cHTEFJclo0KkRNbaLQdYq9aqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:30:23.904648Z"},"content_sha256":"957631e4f8d30f5ea3553aeeca77cdee11875f14156748c9b25fc977348684b7","schema_version":"1.0","event_id":"sha256:957631e4f8d30f5ea3553aeeca77cdee11875f14156748c9b25fc977348684b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UGFILF3V5Q5AU2GZ562Z5IDSRG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-Independent Speaker Verification Using Discrete Audio Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Junjie Li, Kong Aik Lee, Zheng Liang","submitted_at":"2026-07-08T16:03:44Z","abstract_excerpt":"Neural audio codecs (NACs) enable efficient audio compression and have achieved success in downstream tasks such as speech synthesis. However, their discrete representations consistently underperform traditional spectral features in automatic speaker verification (ASV). We empirically demonstrate that speaker cues are implicitly preserved in discrete tokens but remain underutilized by conventional ASV training paradigms. To address this, we propose a Cross-Feature Knowledge Distillation (CFKD) framework. By guiding the codec-based student to mimic the embedding space of a strong Fbank-based te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07579","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/2607.07579/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T01:20:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sDoJQi0DNGoAQVLl21CTag19Fg25s5WC8Q8fRcFgujoEbJJOmQZfGzHPXNxa8dQNwz1dGU3StqEH3vn6f6VUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:30:23.905267Z"},"content_sha256":"10fad8e3c77ae0d6bf57d9d100127f4822d6b1815b9957b9af4b905547598156","schema_version":"1.0","event_id":"sha256:10fad8e3c77ae0d6bf57d9d100127f4822d6b1815b9957b9af4b905547598156"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UGFILF3V5Q5AU2GZ562Z5IDSRG/bundle.json","state_url":"https://pith.science/pith/UGFILF3V5Q5AU2GZ562Z5IDSRG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UGFILF3V5Q5AU2GZ562Z5IDSRG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T16:30:23Z","links":{"resolver":"https://pith.science/pith/UGFILF3V5Q5AU2GZ562Z5IDSRG","bundle":"https://pith.science/pith/UGFILF3V5Q5AU2GZ562Z5IDSRG/bundle.json","state":"https://pith.science/pith/UGFILF3V5Q5AU2GZ562Z5IDSRG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UGFILF3V5Q5AU2GZ562Z5IDSRG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UGFILF3V5Q5AU2GZ562Z5IDSRG","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":"8bd766a357a0eb7cc04837dae0b5d6ece6cb3ac0700201d4b216e37ee207a3e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-08T16:03:44Z","title_canon_sha256":"5b9ff6ff44f327166f6c5bf0f5ad5c83d02cae14ef9220d0e566d5c3ca80297f"},"schema_version":"1.0","source":{"id":"2607.07579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07579","created_at":"2026-07-09T01:20:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07579v1","created_at":"2026-07-09T01:20:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07579","created_at":"2026-07-09T01:20:30Z"},{"alias_kind":"pith_short_12","alias_value":"UGFILF3V5Q5A","created_at":"2026-07-09T01:20:30Z"},{"alias_kind":"pith_short_16","alias_value":"UGFILF3V5Q5AU2GZ","created_at":"2026-07-09T01:20:30Z"},{"alias_kind":"pith_short_8","alias_value":"UGFILF3V","created_at":"2026-07-09T01:20:30Z"}],"graph_snapshots":[{"event_id":"sha256:10fad8e3c77ae0d6bf57d9d100127f4822d6b1815b9957b9af4b905547598156","target":"graph","created_at":"2026-07-09T01:20:30Z","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/2607.07579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural audio codecs (NACs) enable efficient audio compression and have achieved success in downstream tasks such as speech synthesis. However, their discrete representations consistently underperform traditional spectral features in automatic speaker verification (ASV). We empirically demonstrate that speaker cues are implicitly preserved in discrete tokens but remain underutilized by conventional ASV training paradigms. To address this, we propose a Cross-Feature Knowledge Distillation (CFKD) framework. By guiding the codec-based student to mimic the embedding space of a strong Fbank-based te","authors_text":"Junjie Li, Kong Aik Lee, Zheng Liang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-08T16:03:44Z","title":"Text-Independent Speaker Verification Using Discrete Audio Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07579","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":"sha256:957631e4f8d30f5ea3553aeeca77cdee11875f14156748c9b25fc977348684b7","target":"record","created_at":"2026-07-09T01:20:30Z","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":"8bd766a357a0eb7cc04837dae0b5d6ece6cb3ac0700201d4b216e37ee207a3e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-08T16:03:44Z","title_canon_sha256":"5b9ff6ff44f327166f6c5bf0f5ad5c83d02cae14ef9220d0e566d5c3ca80297f"},"schema_version":"1.0","source":{"id":"2607.07579","kind":"arxiv","version":1}},"canonical_sha256":"a18a859775ec3a0a68d9efb59ea07289a23561217637410991cbc05421c74818","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a18a859775ec3a0a68d9efb59ea07289a23561217637410991cbc05421c74818","first_computed_at":"2026-07-09T01:20:30.088673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:30.088673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7+asS5JEqdoXilz2jZpNn6POiXxozuwTAl2ma7xQ6Yetki6XHrV2s++LbX2Z/o8buUssXE2yJIB1qDlzB06KCw==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:30.089096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:957631e4f8d30f5ea3553aeeca77cdee11875f14156748c9b25fc977348684b7","sha256:10fad8e3c77ae0d6bf57d9d100127f4822d6b1815b9957b9af4b905547598156"],"state_sha256":"7a85b6b2bac399421be232fa753a1997c9f014c34e5b6354e17330c4508e4e36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hj2eo1zvEN+5BSXmR6OjBlEIZD+qhng4Z2lrqykhH4zmVDmoIQ0hpXU6wtiL3ti4ZaQQqV8GqiAwNNIPfB4zDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:30:23.909813Z","bundle_sha256":"b956b66d9a64109f0afd2434522a2b98dc1fb74add917cd49b2daab16ec14c14"}}