{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VWU2QO5BY7QP4RARER6Y75RD25","short_pith_number":"pith:VWU2QO5B","canonical_record":{"source":{"id":"2501.06562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T14:45:03Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"title_canon_sha256":"0c43d49cdc3a6250b4ce3ada8889a9ae16da201dd731b11f0f9a11bc5df672d7","abstract_canon_sha256":"f552bf4a8d0824b0e1358526ab60623b8ab058c31e3c243acae7010190411b35"},"schema_version":"1.0"},"canonical_sha256":"ada9a83ba1c7e0fe4411247d8ff623d77d47379a119beaeb5013db3985a1189e","source":{"kind":"arxiv","id":"2501.06562","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06562","created_at":"2026-07-05T10:00:05Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06562v1","created_at":"2026-07-05T10:00:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06562","created_at":"2026-07-05T10:00:05Z"},{"alias_kind":"pith_short_12","alias_value":"VWU2QO5BY7QP","created_at":"2026-07-05T10:00:05Z"},{"alias_kind":"pith_short_16","alias_value":"VWU2QO5BY7QP4RAR","created_at":"2026-07-05T10:00:05Z"},{"alias_kind":"pith_short_8","alias_value":"VWU2QO5B","created_at":"2026-07-05T10:00:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VWU2QO5BY7QP4RARER6Y75RD25","target":"record","payload":{"canonical_record":{"source":{"id":"2501.06562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T14:45:03Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"title_canon_sha256":"0c43d49cdc3a6250b4ce3ada8889a9ae16da201dd731b11f0f9a11bc5df672d7","abstract_canon_sha256":"f552bf4a8d0824b0e1358526ab60623b8ab058c31e3c243acae7010190411b35"},"schema_version":"1.0"},"canonical_sha256":"ada9a83ba1c7e0fe4411247d8ff623d77d47379a119beaeb5013db3985a1189e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:05.343060Z","signature_b64":"Gs2jMZiYr86HIkASt+pv/y1vFMI8QAf/CKDpRDOiusZKn5aMJA3oB9oVKNzci/Cn1rAEYk6AnnMHcII+6FxeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ada9a83ba1c7e0fe4411247d8ff623d77d47379a119beaeb5013db3985a1189e","last_reissued_at":"2026-07-05T10:00:05.342481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:05.342481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.06562","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":"2026-07-05T10:00:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qJPi3zE9bgYxwV1ZZNXK5xleVmOrpqd4umJHEdYvSo0TOBXMnXnzhjgtw1SD3PNVOdYVE0gZyii1AcvBMYSeAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:10:01.083343Z"},"content_sha256":"43e360e658fd662f367d619891e6e8f91ff943a2c8f9463da1033bf8bbf24afb","schema_version":"1.0","event_id":"sha256:43e360e658fd662f367d619891e6e8f91ff943a2c8f9463da1033bf8bbf24afb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VWU2QO5BY7QP4RARER6Y75RD25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discrete Speech Unit Extraction via Independent Component Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Keigo Hojo, Kwanghee Choi, Satoru Fukayama, Shinji Watanabe, Tomohiko Nakamura, Yoshiaki Bando","submitted_at":"2025-01-11T14:45:03Z","abstract_excerpt":"Self-supervised speech models (S3Ms) have become a common tool for the speech processing community, leveraging representations for downstream tasks. Clustering S3M representations yields discrete speech units (DSUs), which serve as compact representations for speech signals. DSUs are typically obtained by k-means clustering. Using DSUs often leads to strong performance in various tasks, including automatic speech recognition (ASR). However, even with the high dimensionality and redundancy of S3M representations, preprocessing S3M representations for better clustering remains unexplored, even t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06562","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/2501.06562/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":"2026-07-05T10:00:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H48MM5nNVYS8Em1RMEBbtm33ZVI/1z8QacI8IufNwj2VIxmj0QMRyLeATwEIHP8+IZy3WfoeExLRskLKguA7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:10:01.084967Z"},"content_sha256":"062957aaa1b616f05d762fc902c277fed7740a75c29d5dca7a3c68516e504960","schema_version":"1.0","event_id":"sha256:062957aaa1b616f05d762fc902c277fed7740a75c29d5dca7a3c68516e504960"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VWU2QO5BY7QP4RARER6Y75RD25/bundle.json","state_url":"https://pith.science/pith/VWU2QO5BY7QP4RARER6Y75RD25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VWU2QO5BY7QP4RARER6Y75RD25/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":"2026-08-20T13:10:01Z","links":{"resolver":"https://pith.science/pith/VWU2QO5BY7QP4RARER6Y75RD25","bundle":"https://pith.science/pith/VWU2QO5BY7QP4RARER6Y75RD25/bundle.json","state":"https://pith.science/pith/VWU2QO5BY7QP4RARER6Y75RD25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VWU2QO5BY7QP4RARER6Y75RD25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VWU2QO5BY7QP4RARER6Y75RD25","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":"f552bf4a8d0824b0e1358526ab60623b8ab058c31e3c243acae7010190411b35","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T14:45:03Z","title_canon_sha256":"0c43d49cdc3a6250b4ce3ada8889a9ae16da201dd731b11f0f9a11bc5df672d7"},"schema_version":"1.0","source":{"id":"2501.06562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06562","created_at":"2026-07-05T10:00:05Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06562v1","created_at":"2026-07-05T10:00:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06562","created_at":"2026-07-05T10:00:05Z"},{"alias_kind":"pith_short_12","alias_value":"VWU2QO5BY7QP","created_at":"2026-07-05T10:00:05Z"},{"alias_kind":"pith_short_16","alias_value":"VWU2QO5BY7QP4RAR","created_at":"2026-07-05T10:00:05Z"},{"alias_kind":"pith_short_8","alias_value":"VWU2QO5B","created_at":"2026-07-05T10:00:05Z"}],"graph_snapshots":[{"event_id":"sha256:062957aaa1b616f05d762fc902c277fed7740a75c29d5dca7a3c68516e504960","target":"graph","created_at":"2026-07-05T10:00:05Z","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/2501.06562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised speech models (S3Ms) have become a common tool for the speech processing community, leveraging representations for downstream tasks. Clustering S3M representations yields discrete speech units (DSUs), which serve as compact representations for speech signals. DSUs are typically obtained by k-means clustering. Using DSUs often leads to strong performance in various tasks, including automatic speech recognition (ASR). However, even with the high dimensionality and redundancy of S3M representations, preprocessing S3M representations for better clustering remains unexplored, even t","authors_text":"Keigo Hojo, Kwanghee Choi, Satoru Fukayama, Shinji Watanabe, Tomohiko Nakamura, Yoshiaki Bando","cross_cats":["cs.AI","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T14:45:03Z","title":"Discrete Speech Unit Extraction via Independent Component Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06562","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":"sha256:43e360e658fd662f367d619891e6e8f91ff943a2c8f9463da1033bf8bbf24afb","target":"record","created_at":"2026-07-05T10:00:05Z","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":"f552bf4a8d0824b0e1358526ab60623b8ab058c31e3c243acae7010190411b35","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T14:45:03Z","title_canon_sha256":"0c43d49cdc3a6250b4ce3ada8889a9ae16da201dd731b11f0f9a11bc5df672d7"},"schema_version":"1.0","source":{"id":"2501.06562","kind":"arxiv","version":1}},"canonical_sha256":"ada9a83ba1c7e0fe4411247d8ff623d77d47379a119beaeb5013db3985a1189e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ada9a83ba1c7e0fe4411247d8ff623d77d47379a119beaeb5013db3985a1189e","first_computed_at":"2026-07-05T10:00:05.342481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:05.342481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gs2jMZiYr86HIkASt+pv/y1vFMI8QAf/CKDpRDOiusZKn5aMJA3oB9oVKNzci/Cn1rAEYk6AnnMHcII+6FxeCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:05.343060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43e360e658fd662f367d619891e6e8f91ff943a2c8f9463da1033bf8bbf24afb","sha256:062957aaa1b616f05d762fc902c277fed7740a75c29d5dca7a3c68516e504960"],"state_sha256":"76cbdd8834ca653386ed246195dbad409e1f05d986322cf96602a1621f1fbe21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qw+97pUdoTf+GgSwmUtxBtnlOnpMrWdmboE0ang4EXvO1Hb4TGfhDvCu6ZmR+ojqGF9TIUmi/sm2AT5FIFRZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T13:10:01.094163Z","bundle_sha256":"4db134666f0acb9055166c22c703f1b510e33f3cddd6e3a79c29d3d0b5245acd"}}