{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:V57KUEZ7MLMXAPLNSMT2W2VMOA","short_pith_number":"pith:V57KUEZ7","canonical_record":{"source":{"id":"2109.01583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-03T15:44:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d902d57eec54ba35578d300476d2db1b916476e5ea512917336088f8563e1e8","abstract_canon_sha256":"0dfa18ad44ce8a04b5c1f2ef4b0241cd62c074a5dcf6327c6b7cc2e8b6b06dd7"},"schema_version":"1.0"},"canonical_sha256":"af7eaa133f62d9703d6d9327ab6aac7033b6ae4333db071565a9b9f79782322a","source":{"kind":"arxiv","id":"2109.01583","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01583","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01583v1","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01583","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"V57KUEZ7MLMX","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"V57KUEZ7MLMXAPLN","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"V57KUEZ7","created_at":"2026-07-05T03:11:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:V57KUEZ7MLMXAPLNSMT2W2VMOA","target":"record","payload":{"canonical_record":{"source":{"id":"2109.01583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-03T15:44:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d902d57eec54ba35578d300476d2db1b916476e5ea512917336088f8563e1e8","abstract_canon_sha256":"0dfa18ad44ce8a04b5c1f2ef4b0241cd62c074a5dcf6327c6b7cc2e8b6b06dd7"},"schema_version":"1.0"},"canonical_sha256":"af7eaa133f62d9703d6d9327ab6aac7033b6ae4333db071565a9b9f79782322a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:19.927818Z","signature_b64":"ubCiVhYKoxYv5W/hdgTOp0TI/43BaFAspep1hjVCUnZMbIZtrH01aSBOvHAc+B6bG9iRU0DfS9jB7elVZlO4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af7eaa133f62d9703d6d9327ab6aac7033b6ae4333db071565a9b9f79782322a","last_reissued_at":"2026-07-05T03:11:19.927453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:19.927453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.01583","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":"2026-07-05T03:11:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XsIm5YUv2jZQcJmZWW0xAlGz9vadMm3G2BWBEq3O2Ign5s+pKM/avsLnrAjJUviXwTyxvSfwmXUVhHaT9zloCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:41:10.845850Z"},"content_sha256":"87b3ce42ca3f0f7b8d0ce1a0e19971073d8c088407b8c8d404c6be1b0649f48a","schema_version":"1.0","event_id":"sha256:87b3ce42ca3f0f7b8d0ce1a0e19971073d8c088407b8c8d404c6be1b0649f48a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:V57KUEZ7MLMXAPLNSMT2W2VMOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daxin Jiang, Jian Pei, Linjun Shou, Ming Gong, Mingxing Xu, Yingmei Guo, Zhiyong Wu","submitted_at":"2021-09-03T15:44:15Z","abstract_excerpt":"Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource target languages, the augmented data sets are often noisy, and thus impede the performance of SLU models. In this paper we focus on mitigating noise in augmented data. We develop a denoising training approach. Multiple models are trained with data produced by various augmented methods. Those models provide supervision signals to each other. The experimental resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01583","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/2109.01583/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":"2026-07-05T03:11:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l1AnspOOmQuK/Fo9WWNCJU1/ObHTlFlAxRUsTkA30WYs8207NpdWbzN8gZk3rQuCAjp1gkZRaXMChuBJXGn8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:41:10.846225Z"},"content_sha256":"9c2e3cd00ad926d1390d308152c577c4aee397b90de6bcd24ba9fd341f08ae17","schema_version":"1.0","event_id":"sha256:9c2e3cd00ad926d1390d308152c577c4aee397b90de6bcd24ba9fd341f08ae17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V57KUEZ7MLMXAPLNSMT2W2VMOA/bundle.json","state_url":"https://pith.science/pith/V57KUEZ7MLMXAPLNSMT2W2VMOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V57KUEZ7MLMXAPLNSMT2W2VMOA/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":"2026-07-07T13:41:10Z","links":{"resolver":"https://pith.science/pith/V57KUEZ7MLMXAPLNSMT2W2VMOA","bundle":"https://pith.science/pith/V57KUEZ7MLMXAPLNSMT2W2VMOA/bundle.json","state":"https://pith.science/pith/V57KUEZ7MLMXAPLNSMT2W2VMOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V57KUEZ7MLMXAPLNSMT2W2VMOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:V57KUEZ7MLMXAPLNSMT2W2VMOA","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":"0dfa18ad44ce8a04b5c1f2ef4b0241cd62c074a5dcf6327c6b7cc2e8b6b06dd7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-03T15:44:15Z","title_canon_sha256":"4d902d57eec54ba35578d300476d2db1b916476e5ea512917336088f8563e1e8"},"schema_version":"1.0","source":{"id":"2109.01583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01583","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01583v1","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01583","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"V57KUEZ7MLMX","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"V57KUEZ7MLMXAPLN","created_at":"2026-07-05T03:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"V57KUEZ7","created_at":"2026-07-05T03:11:19Z"}],"graph_snapshots":[{"event_id":"sha256:9c2e3cd00ad926d1390d308152c577c4aee397b90de6bcd24ba9fd341f08ae17","target":"graph","created_at":"2026-07-05T03:11:19Z","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/2109.01583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource target languages, the augmented data sets are often noisy, and thus impede the performance of SLU models. In this paper we focus on mitigating noise in augmented data. We develop a denoising training approach. Multiple models are trained with data produced by various augmented methods. Those models provide supervision signals to each other. The experimental resu","authors_text":"Daxin Jiang, Jian Pei, Linjun Shou, Ming Gong, Mingxing Xu, Yingmei Guo, Zhiyong Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-03T15:44:15Z","title":"Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01583","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":"sha256:87b3ce42ca3f0f7b8d0ce1a0e19971073d8c088407b8c8d404c6be1b0649f48a","target":"record","created_at":"2026-07-05T03:11:19Z","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":"0dfa18ad44ce8a04b5c1f2ef4b0241cd62c074a5dcf6327c6b7cc2e8b6b06dd7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-03T15:44:15Z","title_canon_sha256":"4d902d57eec54ba35578d300476d2db1b916476e5ea512917336088f8563e1e8"},"schema_version":"1.0","source":{"id":"2109.01583","kind":"arxiv","version":1}},"canonical_sha256":"af7eaa133f62d9703d6d9327ab6aac7033b6ae4333db071565a9b9f79782322a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af7eaa133f62d9703d6d9327ab6aac7033b6ae4333db071565a9b9f79782322a","first_computed_at":"2026-07-05T03:11:19.927453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:19.927453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ubCiVhYKoxYv5W/hdgTOp0TI/43BaFAspep1hjVCUnZMbIZtrH01aSBOvHAc+B6bG9iRU0DfS9jB7elVZlO4CA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:19.927818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.01583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87b3ce42ca3f0f7b8d0ce1a0e19971073d8c088407b8c8d404c6be1b0649f48a","sha256:9c2e3cd00ad926d1390d308152c577c4aee397b90de6bcd24ba9fd341f08ae17"],"state_sha256":"eda40e098dc6f25570c5cadc41a21cc389b3605671168eb5b96700ecaf347808"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tr+ptoKpwL3oYNRMbmBCXE/EIKisAQZCRqavJtNkGJyIoCTWokdrqtRKyTROlhYy9/huZ2q7wxOTqQeSrbr5DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:41:10.848202Z","bundle_sha256":"bcfc8ac5e9617137d665ad78998bc6418ef26a8cb041312af82ba59485b34358"}}