{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LO2UHQRTXDQDK53XVJRPQSG6BE","short_pith_number":"pith:LO2UHQRT","canonical_record":{"source":{"id":"2304.00557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-02T15:24:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"645f5cc3c26122717717bcd0db06bb8434b3386b1c63fdf8b7fecf5ca614422e","abstract_canon_sha256":"04e30683ba54da634f4d0d94d713a9faabc97656b01606b6f0266a45cc3906ca"},"schema_version":"1.0"},"canonical_sha256":"5bb543c233b8e0357777aa62f848de09235106cedd6f977eb088d5dd73eedc99","source":{"kind":"arxiv","id":"2304.00557","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00557","created_at":"2026-07-05T05:57:19Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00557v1","created_at":"2026-07-05T05:57:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00557","created_at":"2026-07-05T05:57:19Z"},{"alias_kind":"pith_short_12","alias_value":"LO2UHQRTXDQD","created_at":"2026-07-05T05:57:19Z"},{"alias_kind":"pith_short_16","alias_value":"LO2UHQRTXDQDK53X","created_at":"2026-07-05T05:57:19Z"},{"alias_kind":"pith_short_8","alias_value":"LO2UHQRT","created_at":"2026-07-05T05:57:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LO2UHQRTXDQDK53XVJRPQSG6BE","target":"record","payload":{"canonical_record":{"source":{"id":"2304.00557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-02T15:24:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"645f5cc3c26122717717bcd0db06bb8434b3386b1c63fdf8b7fecf5ca614422e","abstract_canon_sha256":"04e30683ba54da634f4d0d94d713a9faabc97656b01606b6f0266a45cc3906ca"},"schema_version":"1.0"},"canonical_sha256":"5bb543c233b8e0357777aa62f848de09235106cedd6f977eb088d5dd73eedc99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:19.146965Z","signature_b64":"nk6sP5wKkKvCztX4ICWZ3J4E4Z7f9jkrQiv6Kzpwk6mb/wxhD4swPuVfLnFTRqgVkQXK+TDzi/H5AVrKxhhRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bb543c233b8e0357777aa62f848de09235106cedd6f977eb088d5dd73eedc99","last_reissued_at":"2026-07-05T05:57:19.146561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:19.146561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.00557","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":"2026-07-05T05:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AdxLKzDImQ8pThB7CM5+DbZVwc1RFYIY80z7pdov/G66axdAQgcUr3bbCnO/W/Rcnif7FhZjP8OBlpk3EJlBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:44:01.729949Z"},"content_sha256":"0d96c88d99179fcb5be8ee993cdd58e61ac061aa173683a8c0099df325a7132f","schema_version":"1.0","event_id":"sha256:0d96c88d99179fcb5be8ee993cdd58e61ac061aa173683a8c0099df325a7132f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LO2UHQRTXDQDK53XVJRPQSG6BE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised Neural Machine Translation with Consistency Regularization for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dien Dinh, Giang Nguyen, Long Nguyen, Thang M. Pham, Viet H. Pham","submitted_at":"2023-04-02T15:24:08Z","abstract_excerpt":"The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper presents a simple yet effective method to tackle this problem for low-resource languages by augmenting high-quality sentence pairs and training NMT models in a semi-supervised manner. Specifically, our approach combines the cross-entropy loss for supervised learning with KL Divergence for unsupervised fashion given pseudo and augmented target sentences deriv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00557","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/2304.00557/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":"2026-07-05T05:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L9XSbAQ5YUtZka0eyiW8VhILaOEg4Nz/S/pj8Vh0iEMzzA5y59B3fqEzyzfwTQEt4HWr5cZu951WpAd1dBDIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:44:01.730450Z"},"content_sha256":"ef17345fabd7e8e8793dcf986b6b4417842faf0cd33b01410f30d62806980459","schema_version":"1.0","event_id":"sha256:ef17345fabd7e8e8793dcf986b6b4417842faf0cd33b01410f30d62806980459"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LO2UHQRTXDQDK53XVJRPQSG6BE/bundle.json","state_url":"https://pith.science/pith/LO2UHQRTXDQDK53XVJRPQSG6BE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LO2UHQRTXDQDK53XVJRPQSG6BE/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":"2026-08-18T01:44:01Z","links":{"resolver":"https://pith.science/pith/LO2UHQRTXDQDK53XVJRPQSG6BE","bundle":"https://pith.science/pith/LO2UHQRTXDQDK53XVJRPQSG6BE/bundle.json","state":"https://pith.science/pith/LO2UHQRTXDQDK53XVJRPQSG6BE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LO2UHQRTXDQDK53XVJRPQSG6BE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LO2UHQRTXDQDK53XVJRPQSG6BE","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":"04e30683ba54da634f4d0d94d713a9faabc97656b01606b6f0266a45cc3906ca","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-02T15:24:08Z","title_canon_sha256":"645f5cc3c26122717717bcd0db06bb8434b3386b1c63fdf8b7fecf5ca614422e"},"schema_version":"1.0","source":{"id":"2304.00557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00557","created_at":"2026-07-05T05:57:19Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00557v1","created_at":"2026-07-05T05:57:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00557","created_at":"2026-07-05T05:57:19Z"},{"alias_kind":"pith_short_12","alias_value":"LO2UHQRTXDQD","created_at":"2026-07-05T05:57:19Z"},{"alias_kind":"pith_short_16","alias_value":"LO2UHQRTXDQDK53X","created_at":"2026-07-05T05:57:19Z"},{"alias_kind":"pith_short_8","alias_value":"LO2UHQRT","created_at":"2026-07-05T05:57:19Z"}],"graph_snapshots":[{"event_id":"sha256:ef17345fabd7e8e8793dcf986b6b4417842faf0cd33b01410f30d62806980459","target":"graph","created_at":"2026-07-05T05:57:19Z","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/2304.00557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper presents a simple yet effective method to tackle this problem for low-resource languages by augmenting high-quality sentence pairs and training NMT models in a semi-supervised manner. Specifically, our approach combines the cross-entropy loss for supervised learning with KL Divergence for unsupervised fashion given pseudo and augmented target sentences deriv","authors_text":"Dien Dinh, Giang Nguyen, Long Nguyen, Thang M. Pham, Viet H. Pham","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-02T15:24:08Z","title":"Semi-supervised Neural Machine Translation with Consistency Regularization for Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00557","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":"sha256:0d96c88d99179fcb5be8ee993cdd58e61ac061aa173683a8c0099df325a7132f","target":"record","created_at":"2026-07-05T05:57:19Z","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":"04e30683ba54da634f4d0d94d713a9faabc97656b01606b6f0266a45cc3906ca","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-02T15:24:08Z","title_canon_sha256":"645f5cc3c26122717717bcd0db06bb8434b3386b1c63fdf8b7fecf5ca614422e"},"schema_version":"1.0","source":{"id":"2304.00557","kind":"arxiv","version":1}},"canonical_sha256":"5bb543c233b8e0357777aa62f848de09235106cedd6f977eb088d5dd73eedc99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bb543c233b8e0357777aa62f848de09235106cedd6f977eb088d5dd73eedc99","first_computed_at":"2026-07-05T05:57:19.146561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:57:19.146561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nk6sP5wKkKvCztX4ICWZ3J4E4Z7f9jkrQiv6Kzpwk6mb/wxhD4swPuVfLnFTRqgVkQXK+TDzi/H5AVrKxhhRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:57:19.146965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d96c88d99179fcb5be8ee993cdd58e61ac061aa173683a8c0099df325a7132f","sha256:ef17345fabd7e8e8793dcf986b6b4417842faf0cd33b01410f30d62806980459"],"state_sha256":"4cf78c6a17d90e15a0ad0cba1cc57cedad72b48f4c17db40d17c913f50f93c6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g0K1RzP17ZC/ibsi0ggjXTIR23gDMcwygT2Zs5ycZxMVW1on+fdw89lPC2ThQkWTYHr+Wuiy7ftRl03iSX1GBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:44:01.736075Z","bundle_sha256":"9e07a6c657d5a1023484696e3d833aff85b50d0353d21015651433993d64854f"}}