{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QKIRF7LRHSYI3TSXWX5JDXVLHA","short_pith_number":"pith:QKIRF7LR","canonical_record":{"source":{"id":"2502.00127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T19:21:43Z","cross_cats_sorted":[],"title_canon_sha256":"51caf17a83d718bc3fc2a280ed5e8e02c57cfa37711328a16d856b4ec9b64743","abstract_canon_sha256":"3e6a5bd27159189f70694195da44b05f66cb25c7ce9d6248b7e072b83a2f32d2"},"schema_version":"1.0"},"canonical_sha256":"829112fd713cb08dce57b5fa91deab382d2afa50f062934d11b5508b246b5ca9","source":{"kind":"arxiv","id":"2502.00127","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00127","created_at":"2026-07-05T10:08:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00127v1","created_at":"2026-07-05T10:08:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00127","created_at":"2026-07-05T10:08:03Z"},{"alias_kind":"pith_short_12","alias_value":"QKIRF7LRHSYI","created_at":"2026-07-05T10:08:03Z"},{"alias_kind":"pith_short_16","alias_value":"QKIRF7LRHSYI3TSX","created_at":"2026-07-05T10:08:03Z"},{"alias_kind":"pith_short_8","alias_value":"QKIRF7LR","created_at":"2026-07-05T10:08:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QKIRF7LRHSYI3TSXWX5JDXVLHA","target":"record","payload":{"canonical_record":{"source":{"id":"2502.00127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T19:21:43Z","cross_cats_sorted":[],"title_canon_sha256":"51caf17a83d718bc3fc2a280ed5e8e02c57cfa37711328a16d856b4ec9b64743","abstract_canon_sha256":"3e6a5bd27159189f70694195da44b05f66cb25c7ce9d6248b7e072b83a2f32d2"},"schema_version":"1.0"},"canonical_sha256":"829112fd713cb08dce57b5fa91deab382d2afa50f062934d11b5508b246b5ca9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:03.286715Z","signature_b64":"bKf4Z11M/DEjZUWplP96DiJX3cUZMBdnK80adkIvo3y0ohK3mDzehOVMFZpiiLXWhcd9kF1Fw0xzGnEk4OBoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"829112fd713cb08dce57b5fa91deab382d2afa50f062934d11b5508b246b5ca9","last_reissued_at":"2026-07-05T10:08:03.286273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:03.286273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.00127","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":"2026-07-05T10:08:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hg91zoD70/27PoTBsBsVv7g49YU3iy977h7OETALDafF9sUPiYwRYNiHBDaphKlzw/+Q5E+bGDqifj4zJ3ckCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:52:23.078980Z"},"content_sha256":"6384ce29918a33c18ffe2f477e02d98f600f0c2f38536b8006b87c7af03a4d31","schema_version":"1.0","event_id":"sha256:6384ce29918a33c18ffe2f477e02d98f600f0c2f38536b8006b87c7af03a4d31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QKIRF7LRHSYI3TSXWX5JDXVLHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Autoencoder Insights on Voice Embeddings","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Pluth, Vijay K. Gurbani, Yu Zhou","submitted_at":"2025-01-31T19:21:43Z","abstract_excerpt":"Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM) embeddings, the applicability of this technique to other domains remains largely unexplored. This study applies sparse autoencoders to speaker embeddings generated from a Titanet model, demonstrating the effectiveness of this technique in extracting mono-semantic features from non-textual embedded data. The results show that the extracted features exhibit characteri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00127","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/2502.00127/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":"2026-07-05T10:08:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZQbqsxVbhoOnV3QtvIoFL+XZ1gcFq2+LD9B9P7uU0MOYC0UILnFpicOcXdG+PYS47CuNsziE3upjNqk8X4ylBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:52:23.079507Z"},"content_sha256":"2bd2f29d6d071f9a1686f66c79edf4a5a5a018431eb7afab176e724bbb1d50af","schema_version":"1.0","event_id":"sha256:2bd2f29d6d071f9a1686f66c79edf4a5a5a018431eb7afab176e724bbb1d50af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QKIRF7LRHSYI3TSXWX5JDXVLHA/bundle.json","state_url":"https://pith.science/pith/QKIRF7LRHSYI3TSXWX5JDXVLHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QKIRF7LRHSYI3TSXWX5JDXVLHA/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":"2026-08-10T03:52:23Z","links":{"resolver":"https://pith.science/pith/QKIRF7LRHSYI3TSXWX5JDXVLHA","bundle":"https://pith.science/pith/QKIRF7LRHSYI3TSXWX5JDXVLHA/bundle.json","state":"https://pith.science/pith/QKIRF7LRHSYI3TSXWX5JDXVLHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QKIRF7LRHSYI3TSXWX5JDXVLHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QKIRF7LRHSYI3TSXWX5JDXVLHA","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":"3e6a5bd27159189f70694195da44b05f66cb25c7ce9d6248b7e072b83a2f32d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T19:21:43Z","title_canon_sha256":"51caf17a83d718bc3fc2a280ed5e8e02c57cfa37711328a16d856b4ec9b64743"},"schema_version":"1.0","source":{"id":"2502.00127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00127","created_at":"2026-07-05T10:08:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00127v1","created_at":"2026-07-05T10:08:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00127","created_at":"2026-07-05T10:08:03Z"},{"alias_kind":"pith_short_12","alias_value":"QKIRF7LRHSYI","created_at":"2026-07-05T10:08:03Z"},{"alias_kind":"pith_short_16","alias_value":"QKIRF7LRHSYI3TSX","created_at":"2026-07-05T10:08:03Z"},{"alias_kind":"pith_short_8","alias_value":"QKIRF7LR","created_at":"2026-07-05T10:08:03Z"}],"graph_snapshots":[{"event_id":"sha256:2bd2f29d6d071f9a1686f66c79edf4a5a5a018431eb7afab176e724bbb1d50af","target":"graph","created_at":"2026-07-05T10:08:03Z","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/2502.00127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM) embeddings, the applicability of this technique to other domains remains largely unexplored. This study applies sparse autoencoders to speaker embeddings generated from a Titanet model, demonstrating the effectiveness of this technique in extracting mono-semantic features from non-textual embedded data. The results show that the extracted features exhibit characteri","authors_text":"Daniel Pluth, Vijay K. Gurbani, Yu Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T19:21:43Z","title":"Sparse Autoencoder Insights on Voice Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00127","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":"sha256:6384ce29918a33c18ffe2f477e02d98f600f0c2f38536b8006b87c7af03a4d31","target":"record","created_at":"2026-07-05T10:08:03Z","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":"3e6a5bd27159189f70694195da44b05f66cb25c7ce9d6248b7e072b83a2f32d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T19:21:43Z","title_canon_sha256":"51caf17a83d718bc3fc2a280ed5e8e02c57cfa37711328a16d856b4ec9b64743"},"schema_version":"1.0","source":{"id":"2502.00127","kind":"arxiv","version":1}},"canonical_sha256":"829112fd713cb08dce57b5fa91deab382d2afa50f062934d11b5508b246b5ca9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"829112fd713cb08dce57b5fa91deab382d2afa50f062934d11b5508b246b5ca9","first_computed_at":"2026-07-05T10:08:03.286273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:03.286273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bKf4Z11M/DEjZUWplP96DiJX3cUZMBdnK80adkIvo3y0ohK3mDzehOVMFZpiiLXWhcd9kF1Fw0xzGnEk4OBoAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:03.286715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6384ce29918a33c18ffe2f477e02d98f600f0c2f38536b8006b87c7af03a4d31","sha256:2bd2f29d6d071f9a1686f66c79edf4a5a5a018431eb7afab176e724bbb1d50af"],"state_sha256":"192961eb311eef3e8e60c5c3f9b086aaa721621d8cf9c53ac7e969cb144ce643"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ukdQiXwNXnFNljhqz48wK1YbMpLnoB1/Nxefi9ExlvAOU9vf34D4s4UkBpM7TgjpDzU7rZhsEX440U0ND3coAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:52:23.082896Z","bundle_sha256":"e106233fa6663ddf6eb1938bd169d60598f50848fecba47dd34fe0d62f6996c2"}}