{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KKB6AFMEW4D5JHKV6PJOZWYZQO","short_pith_number":"pith:KKB6AFME","canonical_record":{"source":{"id":"1907.01668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T22:29:53Z","cross_cats_sorted":[],"title_canon_sha256":"6b4464ad5fef346d5c195456f1ec21c701281076035bffa69354b64b3492a8bf","abstract_canon_sha256":"1f39eb1800ebe5f1ac04af1b2ad64d94abcf60205c572fc835f7c84a30ad7ab9"},"schema_version":"1.0"},"canonical_sha256":"5283e01584b707d49d55f3d2ecdb19838999eee0a48f0fe401f5ba1e84ac9e63","source":{"kind":"arxiv","id":"1907.01668","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.01668","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"arxiv_version","alias_value":"1907.01668v1","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01668","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"pith_short_12","alias_value":"KKB6AFMEW4D5","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KKB6AFMEW4D5JHKV","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KKB6AFME","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KKB6AFMEW4D5JHKV6PJOZWYZQO","target":"record","payload":{"canonical_record":{"source":{"id":"1907.01668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T22:29:53Z","cross_cats_sorted":[],"title_canon_sha256":"6b4464ad5fef346d5c195456f1ec21c701281076035bffa69354b64b3492a8bf","abstract_canon_sha256":"1f39eb1800ebe5f1ac04af1b2ad64d94abcf60205c572fc835f7c84a30ad7ab9"},"schema_version":"1.0"},"canonical_sha256":"5283e01584b707d49d55f3d2ecdb19838999eee0a48f0fe401f5ba1e84ac9e63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:35.554269Z","signature_b64":"oy4IZebfIWAjquc/2tSVbuRrjqbcM+JbxqOJEB6YaT5hbd16OoUZpdKqLAfMjB/zXddt7t3c+opMeDUd2POIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5283e01584b707d49d55f3d2ecdb19838999eee0a48f0fe401f5ba1e84ac9e63","last_reissued_at":"2026-05-17T23:41:35.553680Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:35.553680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.01668","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":"2026-05-17T23:41:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"okkngeaABmg6OvYhU/Q+nPxzCvcp9lP7JHvMP9Q2pfrK0jUEMBLz201CBuJz9yUTX9wz7T+0BKjtjGjRp0k2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T10:39:44.224383Z"},"content_sha256":"a61b73b019e7cd9821f8bcd7251b5e1eb0efb27179447aca245f977f0405972f","schema_version":"1.0","event_id":"sha256:a61b73b019e7cd9821f8bcd7251b5e1eb0efb27179447aca245f977f0405972f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KKB6AFMEW4D5JHKV6PJOZWYZQO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data mining Mandarin tone contour shapes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shuo Zhang","submitted_at":"2019-07-02T22:29:53Z","abstract_excerpt":"In spontaneous speech, Mandarin tones that belong to the same tone category may exhibit many different contour shapes. We explore the use of data mining and NLP techniques for understanding the variability of tones in a large corpus of Mandarin newscast speech. First, we adapt a graph-based approach to characterize the clusters (fuzzy types) of tone contour shapes observed in each tone n-gram category. Second, we show correlations between these realized contour shape types and a bag of automatically extracted linguistic features. We discuss the implications of the current study within the cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01668","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":""},"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":"2026-05-17T23:41:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zOSsADo1MFTPciH7Jm5TVInN6AEHynAKN/3KXUj48CEQ7OQ9MHnmtGqhIr/c1XWXRCg4T/yh+64aNwfs2JD+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T10:39:44.224725Z"},"content_sha256":"99b8fa55c00bdc2b023ff1d5f0d2a902a6aa27236f2c0cbde6d703941dc10cb7","schema_version":"1.0","event_id":"sha256:99b8fa55c00bdc2b023ff1d5f0d2a902a6aa27236f2c0cbde6d703941dc10cb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KKB6AFMEW4D5JHKV6PJOZWYZQO/bundle.json","state_url":"https://pith.science/pith/KKB6AFMEW4D5JHKV6PJOZWYZQO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KKB6AFMEW4D5JHKV6PJOZWYZQO/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":"2026-06-28T10:39:44Z","links":{"resolver":"https://pith.science/pith/KKB6AFMEW4D5JHKV6PJOZWYZQO","bundle":"https://pith.science/pith/KKB6AFMEW4D5JHKV6PJOZWYZQO/bundle.json","state":"https://pith.science/pith/KKB6AFMEW4D5JHKV6PJOZWYZQO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KKB6AFMEW4D5JHKV6PJOZWYZQO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KKB6AFMEW4D5JHKV6PJOZWYZQO","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":"1f39eb1800ebe5f1ac04af1b2ad64d94abcf60205c572fc835f7c84a30ad7ab9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T22:29:53Z","title_canon_sha256":"6b4464ad5fef346d5c195456f1ec21c701281076035bffa69354b64b3492a8bf"},"schema_version":"1.0","source":{"id":"1907.01668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.01668","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"arxiv_version","alias_value":"1907.01668v1","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01668","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"pith_short_12","alias_value":"KKB6AFMEW4D5","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KKB6AFMEW4D5JHKV","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KKB6AFME","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:99b8fa55c00bdc2b023ff1d5f0d2a902a6aa27236f2c0cbde6d703941dc10cb7","target":"graph","created_at":"2026-05-17T23:41:35Z","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"},"paper":{"abstract_excerpt":"In spontaneous speech, Mandarin tones that belong to the same tone category may exhibit many different contour shapes. We explore the use of data mining and NLP techniques for understanding the variability of tones in a large corpus of Mandarin newscast speech. First, we adapt a graph-based approach to characterize the clusters (fuzzy types) of tone contour shapes observed in each tone n-gram category. Second, we show correlations between these realized contour shape types and a bag of automatically extracted linguistic features. We discuss the implications of the current study within the cont","authors_text":"Shuo Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T22:29:53Z","title":"Data mining Mandarin tone contour shapes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01668","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:a61b73b019e7cd9821f8bcd7251b5e1eb0efb27179447aca245f977f0405972f","target":"record","created_at":"2026-05-17T23:41:35Z","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":"1f39eb1800ebe5f1ac04af1b2ad64d94abcf60205c572fc835f7c84a30ad7ab9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T22:29:53Z","title_canon_sha256":"6b4464ad5fef346d5c195456f1ec21c701281076035bffa69354b64b3492a8bf"},"schema_version":"1.0","source":{"id":"1907.01668","kind":"arxiv","version":1}},"canonical_sha256":"5283e01584b707d49d55f3d2ecdb19838999eee0a48f0fe401f5ba1e84ac9e63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5283e01584b707d49d55f3d2ecdb19838999eee0a48f0fe401f5ba1e84ac9e63","first_computed_at":"2026-05-17T23:41:35.553680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:35.553680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oy4IZebfIWAjquc/2tSVbuRrjqbcM+JbxqOJEB6YaT5hbd16OoUZpdKqLAfMjB/zXddt7t3c+opMeDUd2POIAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:35.554269Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.01668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a61b73b019e7cd9821f8bcd7251b5e1eb0efb27179447aca245f977f0405972f","sha256:99b8fa55c00bdc2b023ff1d5f0d2a902a6aa27236f2c0cbde6d703941dc10cb7"],"state_sha256":"bb5b3410f7341f1c92daa02884907ae15e6b6c9f3277949d741cd930aacc8bbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BzVXrOvZaLNrIcojKOMqgOLEcq4e5PCX9zsU6oUG9rrM+YY68Utl9OMIwr1anQ+PcG6ke1tN1xQqMzVISTEJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T10:39:44.226685Z","bundle_sha256":"5fc564fef3d7037b25f62c0e11e893a22cef42ea3d55baeec18a7b9837a8706e"}}