{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5OEILOP2JAIETULRRCJBJVO3I3","short_pith_number":"pith:5OEILOP2","canonical_record":{"source":{"id":"2302.08137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-02-16T08:10:41Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"ea7e4aa3fee44d744f213f224faae61ff989d7115e0d5ff91ee9cea5b9c4618f","abstract_canon_sha256":"b914ef38eafa95651e3cef86de2011e78ab5aeffb5a98c017dd9ada722a756a5"},"schema_version":"1.0"},"canonical_sha256":"eb8885b9fa481049d171889214d5db46ec7d2254a160523b961d3dd78d97c388","source":{"kind":"arxiv","id":"2302.08137","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08137","created_at":"2026-07-05T05:42:34Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08137v1","created_at":"2026-07-05T05:42:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08137","created_at":"2026-07-05T05:42:34Z"},{"alias_kind":"pith_short_12","alias_value":"5OEILOP2JAIE","created_at":"2026-07-05T05:42:34Z"},{"alias_kind":"pith_short_16","alias_value":"5OEILOP2JAIETULR","created_at":"2026-07-05T05:42:34Z"},{"alias_kind":"pith_short_8","alias_value":"5OEILOP2","created_at":"2026-07-05T05:42:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5OEILOP2JAIETULRRCJBJVO3I3","target":"record","payload":{"canonical_record":{"source":{"id":"2302.08137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-02-16T08:10:41Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"ea7e4aa3fee44d744f213f224faae61ff989d7115e0d5ff91ee9cea5b9c4618f","abstract_canon_sha256":"b914ef38eafa95651e3cef86de2011e78ab5aeffb5a98c017dd9ada722a756a5"},"schema_version":"1.0"},"canonical_sha256":"eb8885b9fa481049d171889214d5db46ec7d2254a160523b961d3dd78d97c388","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:34.766850Z","signature_b64":"9aB23TJ5qTfDVaPt18zuXn0JN8jXYtUKZQaKlqCW48304Pq5Da355DQMWhYLZ0q9PJcgXV9JZi5hPpqciHcHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb8885b9fa481049d171889214d5db46ec7d2254a160523b961d3dd78d97c388","last_reissued_at":"2026-07-05T05:42:34.766220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:34.766220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.08137","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":"2026-07-05T05:42:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a0cPVwuabO4c7ZejoDsG3srPnD7zcM2lh66huRT+fKBtNcO8VPh25RR2SxLwp3I4kRLrrZXyHyeaa8hU6/+VBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:05:34.297005Z"},"content_sha256":"6998727eebfe18cb4675ff9497b656eae7e4005df325ca00b50a8dff9a9636d4","schema_version":"1.0","event_id":"sha256:6998727eebfe18cb4675ff9497b656eae7e4005df325ca00b50a8dff9a9636d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5OEILOP2JAIETULRRCJBJVO3I3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Boris Ginsburg, Jason Li, Jocelyn Huang, Paarth Neekhara, Shehzeen Hussain","submitted_at":"2023-02-16T08:10:41Z","abstract_excerpt":"In this work, we propose a zero-shot voice conversion method using speech representations trained with self-supervised learning. First, we develop a multi-task model to decompose a speech utterance into features such as linguistic content, speaker characteristics, and speaking style. To disentangle content and speaker representations, we propose a training strategy based on Siamese networks that encourages similarity between the content representations of the original and pitch-shifted audio. Next, we develop a synthesis model with pitch and duration predictors that can effectively reconstruct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08137","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/2302.08137/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":"2026-07-05T05:42:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Q11fReEVhBuKMIOguMPaHSbKiSlmLpegDJ6huWIqYFmrxUEl57lTmhAIcFoda7Ag3VyxqRXEa7lOLJzN1avBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:05:34.297642Z"},"content_sha256":"1bdbbeadf5f4d3321dbbda4ee1a5cb1c7151bd5398bcb0b8975a5c5900633f83","schema_version":"1.0","event_id":"sha256:1bdbbeadf5f4d3321dbbda4ee1a5cb1c7151bd5398bcb0b8975a5c5900633f83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5OEILOP2JAIETULRRCJBJVO3I3/bundle.json","state_url":"https://pith.science/pith/5OEILOP2JAIETULRRCJBJVO3I3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5OEILOP2JAIETULRRCJBJVO3I3/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":"2026-08-06T17:05:34Z","links":{"resolver":"https://pith.science/pith/5OEILOP2JAIETULRRCJBJVO3I3","bundle":"https://pith.science/pith/5OEILOP2JAIETULRRCJBJVO3I3/bundle.json","state":"https://pith.science/pith/5OEILOP2JAIETULRRCJBJVO3I3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5OEILOP2JAIETULRRCJBJVO3I3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5OEILOP2JAIETULRRCJBJVO3I3","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":"b914ef38eafa95651e3cef86de2011e78ab5aeffb5a98c017dd9ada722a756a5","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-02-16T08:10:41Z","title_canon_sha256":"ea7e4aa3fee44d744f213f224faae61ff989d7115e0d5ff91ee9cea5b9c4618f"},"schema_version":"1.0","source":{"id":"2302.08137","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08137","created_at":"2026-07-05T05:42:34Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08137v1","created_at":"2026-07-05T05:42:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08137","created_at":"2026-07-05T05:42:34Z"},{"alias_kind":"pith_short_12","alias_value":"5OEILOP2JAIE","created_at":"2026-07-05T05:42:34Z"},{"alias_kind":"pith_short_16","alias_value":"5OEILOP2JAIETULR","created_at":"2026-07-05T05:42:34Z"},{"alias_kind":"pith_short_8","alias_value":"5OEILOP2","created_at":"2026-07-05T05:42:34Z"}],"graph_snapshots":[{"event_id":"sha256:1bdbbeadf5f4d3321dbbda4ee1a5cb1c7151bd5398bcb0b8975a5c5900633f83","target":"graph","created_at":"2026-07-05T05:42:34Z","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/2302.08137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose a zero-shot voice conversion method using speech representations trained with self-supervised learning. First, we develop a multi-task model to decompose a speech utterance into features such as linguistic content, speaker characteristics, and speaking style. To disentangle content and speaker representations, we propose a training strategy based on Siamese networks that encourages similarity between the content representations of the original and pitch-shifted audio. Next, we develop a synthesis model with pitch and duration predictors that can effectively reconstruct","authors_text":"Boris Ginsburg, Jason Li, Jocelyn Huang, Paarth Neekhara, Shehzeen Hussain","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-02-16T08:10:41Z","title":"ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08137","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":"sha256:6998727eebfe18cb4675ff9497b656eae7e4005df325ca00b50a8dff9a9636d4","target":"record","created_at":"2026-07-05T05:42:34Z","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":"b914ef38eafa95651e3cef86de2011e78ab5aeffb5a98c017dd9ada722a756a5","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-02-16T08:10:41Z","title_canon_sha256":"ea7e4aa3fee44d744f213f224faae61ff989d7115e0d5ff91ee9cea5b9c4618f"},"schema_version":"1.0","source":{"id":"2302.08137","kind":"arxiv","version":1}},"canonical_sha256":"eb8885b9fa481049d171889214d5db46ec7d2254a160523b961d3dd78d97c388","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb8885b9fa481049d171889214d5db46ec7d2254a160523b961d3dd78d97c388","first_computed_at":"2026-07-05T05:42:34.766220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:34.766220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9aB23TJ5qTfDVaPt18zuXn0JN8jXYtUKZQaKlqCW48304Pq5Da355DQMWhYLZ0q9PJcgXV9JZi5hPpqciHcHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:34.766850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.08137","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6998727eebfe18cb4675ff9497b656eae7e4005df325ca00b50a8dff9a9636d4","sha256:1bdbbeadf5f4d3321dbbda4ee1a5cb1c7151bd5398bcb0b8975a5c5900633f83"],"state_sha256":"29e00d8c5fa870f89482bc1c2e73c48096dd63f9674d0585c867287f4b2bea1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71Mpw8NgV6mxdte1HG5jeFHuH4Em52uuzVg1zwNMLyqquxf7c5BDWPe9XP4uIgIciChSMOvUT+OThJ902shcCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:05:34.301649Z","bundle_sha256":"02feefc5b0319741f4e00cee17d42afd151c3707032128f7061e4c49c66a9bf8"}}