{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NOG5U6QQVF5BZ3TAZ5B273LZ7L","short_pith_number":"pith:NOG5U6QQ","canonical_record":{"source":{"id":"2203.01826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-01T05:29:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b318e358b48f0f622cb8fde1255e9292e4ad92c915cab8b5877550d61e9a2795","abstract_canon_sha256":"6c0a0603c4f6eb386c2eec22d348ab69bcc585e24751c720fd10c95aeea5ca25"},"schema_version":"1.0"},"canonical_sha256":"6b8dda7a10a97a1cee60cf43afed79facc36e314f34c428ce2c7547c6e98c6db","source":{"kind":"arxiv","id":"2203.01826","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.01826","created_at":"2026-07-05T04:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"2203.01826v1","created_at":"2026-07-05T04:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01826","created_at":"2026-07-05T04:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"NOG5U6QQVF5B","created_at":"2026-07-05T04:01:52Z"},{"alias_kind":"pith_short_16","alias_value":"NOG5U6QQVF5BZ3TA","created_at":"2026-07-05T04:01:52Z"},{"alias_kind":"pith_short_8","alias_value":"NOG5U6QQ","created_at":"2026-07-05T04:01:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NOG5U6QQVF5BZ3TAZ5B273LZ7L","target":"record","payload":{"canonical_record":{"source":{"id":"2203.01826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-01T05:29:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b318e358b48f0f622cb8fde1255e9292e4ad92c915cab8b5877550d61e9a2795","abstract_canon_sha256":"6c0a0603c4f6eb386c2eec22d348ab69bcc585e24751c720fd10c95aeea5ca25"},"schema_version":"1.0"},"canonical_sha256":"6b8dda7a10a97a1cee60cf43afed79facc36e314f34c428ce2c7547c6e98c6db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:52.284224Z","signature_b64":"GtH4rEVQIhewaJ6j24bonZXWEPU27dfxOM7ncgZhcfmsRQJ0JWaIwi5y6fFm8XNISE7Ndmj7QJxc6EREtqA8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b8dda7a10a97a1cee60cf43afed79facc36e314f34c428ce2c7547c6e98c6db","last_reissued_at":"2026-07-05T04:01:52.283744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:52.283744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.01826","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":"2026-07-05T04:01:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zEPzzVe5PMTXmezVKBW8KZL4mvVUAW8QCHMSf0Q2f6hhTt+HKikGeMWa98tjC9Fhh/iFHTwNi8n8zS0IFXd+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:02:29.268467Z"},"content_sha256":"1c7f7ea220e824482d14e9704cc5da1b8f407e9f59082bfc2e0e546d3918c808","schema_version":"1.0","event_id":"sha256:1c7f7ea220e824482d14e9704cc5da1b8f407e9f59082bfc2e0e546d3918c808"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NOG5U6QQVF5BZ3TAZ5B273LZ7L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Kaiqi Fu, Kai Wang, Shaojun Gao, Wei Li, Xiaohai Tian, Zejun Ma","submitted_at":"2022-03-01T05:29:57Z","abstract_excerpt":"Deep learning-based pronunciation scoring models highly rely on the availability of the annotated non-native data, which is costly and has scalability issues. To deal with the data scarcity problem, data augmentation is commonly used for model pretraining. In this paper, we propose a phone-level mixup, a simple yet effective data augmentation method, to improve the performance of word-level pronunciation scoring. Specifically, given a phoneme sequence from lexicon, the artificial augmented word sample can be generated by randomly sampling from the corresponding phone-level features in training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01826","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/2203.01826/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":"2026-07-05T04:01:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hct4KSlIUqmN7CgQY5ABva0jWJBso3fVJZqm7zkfhaLKIXnP3+VgIpumaRGePmp69BKWF2jiVGMJfE66ZYyWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:02:29.268847Z"},"content_sha256":"ad9bfc2741f41beb152629d0928270194255d2f84d65423640a376cc8d91b7e8","schema_version":"1.0","event_id":"sha256:ad9bfc2741f41beb152629d0928270194255d2f84d65423640a376cc8d91b7e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NOG5U6QQVF5BZ3TAZ5B273LZ7L/bundle.json","state_url":"https://pith.science/pith/NOG5U6QQVF5BZ3TAZ5B273LZ7L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NOG5U6QQVF5BZ3TAZ5B273LZ7L/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":"2026-07-07T08:02:29Z","links":{"resolver":"https://pith.science/pith/NOG5U6QQVF5BZ3TAZ5B273LZ7L","bundle":"https://pith.science/pith/NOG5U6QQVF5BZ3TAZ5B273LZ7L/bundle.json","state":"https://pith.science/pith/NOG5U6QQVF5BZ3TAZ5B273LZ7L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NOG5U6QQVF5BZ3TAZ5B273LZ7L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NOG5U6QQVF5BZ3TAZ5B273LZ7L","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":"6c0a0603c4f6eb386c2eec22d348ab69bcc585e24751c720fd10c95aeea5ca25","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-01T05:29:57Z","title_canon_sha256":"b318e358b48f0f622cb8fde1255e9292e4ad92c915cab8b5877550d61e9a2795"},"schema_version":"1.0","source":{"id":"2203.01826","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.01826","created_at":"2026-07-05T04:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"2203.01826v1","created_at":"2026-07-05T04:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01826","created_at":"2026-07-05T04:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"NOG5U6QQVF5B","created_at":"2026-07-05T04:01:52Z"},{"alias_kind":"pith_short_16","alias_value":"NOG5U6QQVF5BZ3TA","created_at":"2026-07-05T04:01:52Z"},{"alias_kind":"pith_short_8","alias_value":"NOG5U6QQ","created_at":"2026-07-05T04:01:52Z"}],"graph_snapshots":[{"event_id":"sha256:ad9bfc2741f41beb152629d0928270194255d2f84d65423640a376cc8d91b7e8","target":"graph","created_at":"2026-07-05T04:01:52Z","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/2203.01826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning-based pronunciation scoring models highly rely on the availability of the annotated non-native data, which is costly and has scalability issues. To deal with the data scarcity problem, data augmentation is commonly used for model pretraining. In this paper, we propose a phone-level mixup, a simple yet effective data augmentation method, to improve the performance of word-level pronunciation scoring. Specifically, given a phoneme sequence from lexicon, the artificial augmented word sample can be generated by randomly sampling from the corresponding phone-level features in training","authors_text":"Kaiqi Fu, Kai Wang, Shaojun Gao, Wei Li, Xiaohai Tian, Zejun Ma","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-01T05:29:57Z","title":"Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01826","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":"sha256:1c7f7ea220e824482d14e9704cc5da1b8f407e9f59082bfc2e0e546d3918c808","target":"record","created_at":"2026-07-05T04:01:52Z","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":"6c0a0603c4f6eb386c2eec22d348ab69bcc585e24751c720fd10c95aeea5ca25","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-01T05:29:57Z","title_canon_sha256":"b318e358b48f0f622cb8fde1255e9292e4ad92c915cab8b5877550d61e9a2795"},"schema_version":"1.0","source":{"id":"2203.01826","kind":"arxiv","version":1}},"canonical_sha256":"6b8dda7a10a97a1cee60cf43afed79facc36e314f34c428ce2c7547c6e98c6db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b8dda7a10a97a1cee60cf43afed79facc36e314f34c428ce2c7547c6e98c6db","first_computed_at":"2026-07-05T04:01:52.283744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:52.283744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GtH4rEVQIhewaJ6j24bonZXWEPU27dfxOM7ncgZhcfmsRQJ0JWaIwi5y6fFm8XNISE7Ndmj7QJxc6EREtqA8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:52.284224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.01826","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c7f7ea220e824482d14e9704cc5da1b8f407e9f59082bfc2e0e546d3918c808","sha256:ad9bfc2741f41beb152629d0928270194255d2f84d65423640a376cc8d91b7e8"],"state_sha256":"3320cb3c55c5147885965083b3a9957bcc4d45cdba6fb714515d649e96198da4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ni5z15Ki3B8wOowSn2szAxWzMBCiWmT/tddnoQ7F5Rzgmb3EaGk2KjLuLAEVZnqCHnnGayHSlkCsl6OZJAWyDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:02:29.270761Z","bundle_sha256":"07c3c3f322a850c5d3f081d13bc61c7db258932e5258dcebc71588c4ab29c271"}}