{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5M5ICWHADVAFVMLX4V7FIEHSFE","short_pith_number":"pith:5M5ICWHA","canonical_record":{"source":{"id":"2505.09661","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-14T13:46:46Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"cc7020b0ef9dc1ecd084ae700282633b3e07f89e6c15163b0cf6fbd152cbd5bd","abstract_canon_sha256":"5d8d3b88426228dd45651c4254f91e9c6aee9d4e3f11af9c57efe0e35e13d328"},"schema_version":"1.0"},"canonical_sha256":"eb3a8158e01d405ab177e57e5410f22912da7e21233a0c2992d9799d6c8018aa","source":{"kind":"arxiv","id":"2505.09661","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09661","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09661v2","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09661","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"5M5ICWHADVAF","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"5M5ICWHADVAFVMLX","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"5M5ICWHA","created_at":"2026-07-05T11:25:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5M5ICWHADVAFVMLX4V7FIEHSFE","target":"record","payload":{"canonical_record":{"source":{"id":"2505.09661","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-14T13:46:46Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"cc7020b0ef9dc1ecd084ae700282633b3e07f89e6c15163b0cf6fbd152cbd5bd","abstract_canon_sha256":"5d8d3b88426228dd45651c4254f91e9c6aee9d4e3f11af9c57efe0e35e13d328"},"schema_version":"1.0"},"canonical_sha256":"eb3a8158e01d405ab177e57e5410f22912da7e21233a0c2992d9799d6c8018aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:10.565702Z","signature_b64":"9guBkZTkZ2ZxT9NNjdMpXCKGtxvELkUD63wdlNb1Huxt43iFlci6eJNe+7VK4gVN2/uicSoRX599DHYbPuTGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb3a8158e01d405ab177e57e5410f22912da7e21233a0c2992d9799d6c8018aa","last_reissued_at":"2026-07-05T11:25:10.565071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:10.565071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.09661","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEx1crw8gdT8AQ4jxRmROb/GH0PY3pKkL1DZeLi0MjcCNjuqoL6kL3lrAYMZCdpFNnHQBVNXNv+YH3gcqHVmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:14:13.919413Z"},"content_sha256":"1ddc5333bb764148d3c7b0312d61137e46f5b04fa0317ee22e9dfb135a30dd2d","schema_version":"1.0","event_id":"sha256:1ddc5333bb764148d3c7b0312d61137e46f5b04fa0317ee22e9dfb135a30dd2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5M5ICWHADVAFVMLX4V7FIEHSFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Introducing voice timbre attribute detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinghao He, Kong Aik Lee, Liping Chen, Zhengyan Sheng, Zhen-Hua Ling","submitted_at":"2025-05-14T13:46:46Z","abstract_excerpt":"This paper focuses on explaining the timbre conveyed by speech signals and introduces a task termed voice timbre attribute detection (vTAD). In this task, voice timbre is explained with a set of sensory attributes describing its human perception. A pair of speech utterances is processed, and their intensity is compared in a designated timbre descriptor. Moreover, a framework is proposed, which is built upon the speaker embeddings extracted from the speech utterances. The investigation is conducted on the VCTK-RVA dataset. Experimental examinations on the ECAPA-TDNN and FACodec speaker encoders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09661","kind":"arxiv","version":2},"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/2505.09661/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":"2026-07-05T11:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ASFfxVCPvFBxU0dJlLMChm5Uus3YjaCtsxaK1uNfbgvJ27rwqUDJ76ed+CwTohz0DKt4vTsQRJMCBnNeT5zABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:14:13.919923Z"},"content_sha256":"11ab4a191f23f06e8a8dd6c50a857b26ac782c23b65c4eb569c2ed2a7bb35c7d","schema_version":"1.0","event_id":"sha256:11ab4a191f23f06e8a8dd6c50a857b26ac782c23b65c4eb569c2ed2a7bb35c7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5M5ICWHADVAFVMLX4V7FIEHSFE/bundle.json","state_url":"https://pith.science/pith/5M5ICWHADVAFVMLX4V7FIEHSFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5M5ICWHADVAFVMLX4V7FIEHSFE/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":"2026-08-06T11:14:13Z","links":{"resolver":"https://pith.science/pith/5M5ICWHADVAFVMLX4V7FIEHSFE","bundle":"https://pith.science/pith/5M5ICWHADVAFVMLX4V7FIEHSFE/bundle.json","state":"https://pith.science/pith/5M5ICWHADVAFVMLX4V7FIEHSFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5M5ICWHADVAFVMLX4V7FIEHSFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5M5ICWHADVAFVMLX4V7FIEHSFE","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":"5d8d3b88426228dd45651c4254f91e9c6aee9d4e3f11af9c57efe0e35e13d328","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-14T13:46:46Z","title_canon_sha256":"cc7020b0ef9dc1ecd084ae700282633b3e07f89e6c15163b0cf6fbd152cbd5bd"},"schema_version":"1.0","source":{"id":"2505.09661","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09661","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09661v2","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09661","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"5M5ICWHADVAF","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"5M5ICWHADVAFVMLX","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"5M5ICWHA","created_at":"2026-07-05T11:25:10Z"}],"graph_snapshots":[{"event_id":"sha256:11ab4a191f23f06e8a8dd6c50a857b26ac782c23b65c4eb569c2ed2a7bb35c7d","target":"graph","created_at":"2026-07-05T11:25:10Z","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/2505.09661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper focuses on explaining the timbre conveyed by speech signals and introduces a task termed voice timbre attribute detection (vTAD). In this task, voice timbre is explained with a set of sensory attributes describing its human perception. A pair of speech utterances is processed, and their intensity is compared in a designated timbre descriptor. Moreover, a framework is proposed, which is built upon the speaker embeddings extracted from the speech utterances. The investigation is conducted on the VCTK-RVA dataset. Experimental examinations on the ECAPA-TDNN and FACodec speaker encoders","authors_text":"Jinghao He, Kong Aik Lee, Liping Chen, Zhengyan Sheng, Zhen-Hua Ling","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-14T13:46:46Z","title":"Introducing voice timbre attribute detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09661","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":"sha256:1ddc5333bb764148d3c7b0312d61137e46f5b04fa0317ee22e9dfb135a30dd2d","target":"record","created_at":"2026-07-05T11:25:10Z","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":"5d8d3b88426228dd45651c4254f91e9c6aee9d4e3f11af9c57efe0e35e13d328","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-14T13:46:46Z","title_canon_sha256":"cc7020b0ef9dc1ecd084ae700282633b3e07f89e6c15163b0cf6fbd152cbd5bd"},"schema_version":"1.0","source":{"id":"2505.09661","kind":"arxiv","version":2}},"canonical_sha256":"eb3a8158e01d405ab177e57e5410f22912da7e21233a0c2992d9799d6c8018aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb3a8158e01d405ab177e57e5410f22912da7e21233a0c2992d9799d6c8018aa","first_computed_at":"2026-07-05T11:25:10.565071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:10.565071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9guBkZTkZ2ZxT9NNjdMpXCKGtxvELkUD63wdlNb1Huxt43iFlci6eJNe+7VK4gVN2/uicSoRX599DHYbPuTGAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:10.565702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.09661","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ddc5333bb764148d3c7b0312d61137e46f5b04fa0317ee22e9dfb135a30dd2d","sha256:11ab4a191f23f06e8a8dd6c50a857b26ac782c23b65c4eb569c2ed2a7bb35c7d"],"state_sha256":"f2b33f7ad10ac13da027d3e43bce52132401bb1f6195f0fb9b0b6c39d17e1944"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kcj0eE8ThbSf25S4zM3hEKjjl99qQM0aHGqyhGRjZFK6u11e3xva9iusHKMoFT7vUgqfLwCwAhZnuo7uuNiLAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T11:14:13.923602Z","bundle_sha256":"825d48eb10a90e2938914c322156a122d5b8e11c11ed99b2511d01fd3b7ad724"}}