{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QYQN7ZBFQAKTEWNOU6QGZJPT5M","short_pith_number":"pith:QYQN7ZBF","canonical_record":{"source":{"id":"2410.19935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T19:13:25Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"03db75cf19c104baa8d3108641fa944f3f9b326a81462a47b0039dc456fe202a","abstract_canon_sha256":"2c741373d5dccbac11e9fa75a65407aef23d5da553a8a439edbc33c537675d40"},"schema_version":"1.0"},"canonical_sha256":"8620dfe42580153259aea7a06ca5f3eb3c524be88e1cc7c6b8dfbd5a215ddb89","source":{"kind":"arxiv","id":"2410.19935","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19935","created_at":"2026-07-05T09:26:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19935v1","created_at":"2026-07-05T09:26:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19935","created_at":"2026-07-05T09:26:35Z"},{"alias_kind":"pith_short_12","alias_value":"QYQN7ZBFQAKT","created_at":"2026-07-05T09:26:35Z"},{"alias_kind":"pith_short_16","alias_value":"QYQN7ZBFQAKTEWNO","created_at":"2026-07-05T09:26:35Z"},{"alias_kind":"pith_short_8","alias_value":"QYQN7ZBF","created_at":"2026-07-05T09:26:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QYQN7ZBFQAKTEWNOU6QGZJPT5M","target":"record","payload":{"canonical_record":{"source":{"id":"2410.19935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T19:13:25Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"03db75cf19c104baa8d3108641fa944f3f9b326a81462a47b0039dc456fe202a","abstract_canon_sha256":"2c741373d5dccbac11e9fa75a65407aef23d5da553a8a439edbc33c537675d40"},"schema_version":"1.0"},"canonical_sha256":"8620dfe42580153259aea7a06ca5f3eb3c524be88e1cc7c6b8dfbd5a215ddb89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:35.862262Z","signature_b64":"Q2hx/ulPZdPhVb0ANzu+QoZecID5kb6TbWAao0hwmtRNZZoiH5XH2bxe6FAYoWC68KVdMmqCMzg/fCLwK7j2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8620dfe42580153259aea7a06ca5f3eb3c524be88e1cc7c6b8dfbd5a215ddb89","last_reissued_at":"2026-07-05T09:26:35.861788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:35.861788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.19935","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":"2026-07-05T09:26:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xBjMMRKAk9u5el6O5ITvWEOjIefIUKIZ36Tq0lZ+kFRwSYJDRpIQbNIgkNP1BoQOwonwo1jBqVyT48XjC4hTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:02:11.128317Z"},"content_sha256":"df52582df2ae6c4c3b2bc48d126c8b9f8c8e62dd03d7cd8abfed9a4ab47bfa8e","schema_version":"1.0","event_id":"sha256:df52582df2ae6c4c3b2bc48d126c8b9f8c8e62dd03d7cd8abfed9a4ab47bfa8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QYQN7ZBFQAKTEWNOU6QGZJPT5M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Discrete Self-Supervised Representations of Speech Capture Tone Distinctions?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Opeyemi Osakuade, Simon King","submitted_at":"2024-10-25T19:13:25Z","abstract_excerpt":"Discrete representations of speech, obtained from Self-Supervised Learning (SSL) foundation models, are widely used, especially where there are limited data for the downstream task, such as for a low-resource language. Typically, discretization of speech into a sequence of symbols is achieved by unsupervised clustering of the latents from an SSL model. Our study evaluates whether discrete symbols - found using k-means - adequately capture tone in two example languages, Mandarin and Yoruba. We compare latent vectors with discrete symbols, obtained from HuBERT base, MandarinHuBERT, or XLS-R, for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19935","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/2410.19935/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":"2026-07-05T09:26:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ePWmteRFNiZdqM7lyeKFU5I9Q8C/LQcRj50oqDaSXdqi7BViU8dUmBsFOhwArLUItH9DouPdco2SRtr8uhChBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:02:11.128926Z"},"content_sha256":"b8015f28b45de6d309d1c633f470efeade958ac3819e09a6fc22bc67a7095b8d","schema_version":"1.0","event_id":"sha256:b8015f28b45de6d309d1c633f470efeade958ac3819e09a6fc22bc67a7095b8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QYQN7ZBFQAKTEWNOU6QGZJPT5M/bundle.json","state_url":"https://pith.science/pith/QYQN7ZBFQAKTEWNOU6QGZJPT5M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QYQN7ZBFQAKTEWNOU6QGZJPT5M/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":"2026-08-22T12:02:11Z","links":{"resolver":"https://pith.science/pith/QYQN7ZBFQAKTEWNOU6QGZJPT5M","bundle":"https://pith.science/pith/QYQN7ZBFQAKTEWNOU6QGZJPT5M/bundle.json","state":"https://pith.science/pith/QYQN7ZBFQAKTEWNOU6QGZJPT5M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QYQN7ZBFQAKTEWNOU6QGZJPT5M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QYQN7ZBFQAKTEWNOU6QGZJPT5M","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":"2c741373d5dccbac11e9fa75a65407aef23d5da553a8a439edbc33c537675d40","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T19:13:25Z","title_canon_sha256":"03db75cf19c104baa8d3108641fa944f3f9b326a81462a47b0039dc456fe202a"},"schema_version":"1.0","source":{"id":"2410.19935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19935","created_at":"2026-07-05T09:26:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19935v1","created_at":"2026-07-05T09:26:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19935","created_at":"2026-07-05T09:26:35Z"},{"alias_kind":"pith_short_12","alias_value":"QYQN7ZBFQAKT","created_at":"2026-07-05T09:26:35Z"},{"alias_kind":"pith_short_16","alias_value":"QYQN7ZBFQAKTEWNO","created_at":"2026-07-05T09:26:35Z"},{"alias_kind":"pith_short_8","alias_value":"QYQN7ZBF","created_at":"2026-07-05T09:26:35Z"}],"graph_snapshots":[{"event_id":"sha256:b8015f28b45de6d309d1c633f470efeade958ac3819e09a6fc22bc67a7095b8d","target":"graph","created_at":"2026-07-05T09:26:35Z","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/2410.19935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Discrete representations of speech, obtained from Self-Supervised Learning (SSL) foundation models, are widely used, especially where there are limited data for the downstream task, such as for a low-resource language. Typically, discretization of speech into a sequence of symbols is achieved by unsupervised clustering of the latents from an SSL model. Our study evaluates whether discrete symbols - found using k-means - adequately capture tone in two example languages, Mandarin and Yoruba. We compare latent vectors with discrete symbols, obtained from HuBERT base, MandarinHuBERT, or XLS-R, for","authors_text":"Opeyemi Osakuade, Simon King","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T19:13:25Z","title":"Do Discrete Self-Supervised Representations of Speech Capture Tone Distinctions?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19935","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:df52582df2ae6c4c3b2bc48d126c8b9f8c8e62dd03d7cd8abfed9a4ab47bfa8e","target":"record","created_at":"2026-07-05T09:26:35Z","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":"2c741373d5dccbac11e9fa75a65407aef23d5da553a8a439edbc33c537675d40","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T19:13:25Z","title_canon_sha256":"03db75cf19c104baa8d3108641fa944f3f9b326a81462a47b0039dc456fe202a"},"schema_version":"1.0","source":{"id":"2410.19935","kind":"arxiv","version":1}},"canonical_sha256":"8620dfe42580153259aea7a06ca5f3eb3c524be88e1cc7c6b8dfbd5a215ddb89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8620dfe42580153259aea7a06ca5f3eb3c524be88e1cc7c6b8dfbd5a215ddb89","first_computed_at":"2026-07-05T09:26:35.861788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:35.861788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q2hx/ulPZdPhVb0ANzu+QoZecID5kb6TbWAao0hwmtRNZZoiH5XH2bxe6FAYoWC68KVdMmqCMzg/fCLwK7j2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:35.862262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df52582df2ae6c4c3b2bc48d126c8b9f8c8e62dd03d7cd8abfed9a4ab47bfa8e","sha256:b8015f28b45de6d309d1c633f470efeade958ac3819e09a6fc22bc67a7095b8d"],"state_sha256":"44538afa2397e511ce7fe79fa07d8dab1ddf3e739219551003014ae1c1f8ee3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LIwXdBTDIRM0saS4tTkwE0ehRmljmIJEaiV4afCc8Fg6YDc9WwRW++Gw5836hXQF3yNt8GcdsIq+CpSb6njlCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T12:02:11.132832Z","bundle_sha256":"9b87cc60a819257165f7fb75601b115a07251321275129902dd068132392aecb"}}