{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Y2RSG5QK5IWXGHEL3IYAH5WJ5C","short_pith_number":"pith:Y2RSG5QK","canonical_record":{"source":{"id":"2203.13867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:08:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ee98597cb2bbf2565ee5b0069eb1d98fda4754f0aa6401497e1588d48934a503","abstract_canon_sha256":"fb444972bbfc6964fe4f1775a786cb0585f08fafaae6eb31d488e66cc7f01786"},"schema_version":"1.0"},"canonical_sha256":"c6a323760aea2d731c8bda3003f6c9e884be2469f059d81d520121e067cc61a1","source":{"kind":"arxiv","id":"2203.13867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.13867","created_at":"2026-07-05T04:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2203.13867v1","created_at":"2026-07-05T04:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13867","created_at":"2026-07-05T04:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"Y2RSG5QK5IWX","created_at":"2026-07-05T04:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"Y2RSG5QK5IWXGHEL","created_at":"2026-07-05T04:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"Y2RSG5QK","created_at":"2026-07-05T04:08:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Y2RSG5QK5IWXGHEL3IYAH5WJ5C","target":"record","payload":{"canonical_record":{"source":{"id":"2203.13867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:08:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ee98597cb2bbf2565ee5b0069eb1d98fda4754f0aa6401497e1588d48934a503","abstract_canon_sha256":"fb444972bbfc6964fe4f1775a786cb0585f08fafaae6eb31d488e66cc7f01786"},"schema_version":"1.0"},"canonical_sha256":"c6a323760aea2d731c8bda3003f6c9e884be2469f059d81d520121e067cc61a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:44.320790Z","signature_b64":"5NCUqAPxP8Uh2Q7iSAnMAzVqm9e2vDm7F67Ur1SApOi1fUEo8+Ys4X0X9tUbbHbkzj3AfjNElbPWBnQiv6SECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6a323760aea2d731c8bda3003f6c9e884be2469f059d81d520121e067cc61a1","last_reissued_at":"2026-07-05T04:08:44.320435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:44.320435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.13867","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":"2026-07-05T04:08:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UoYBxqD7TUh3rkS0uN94gflZQL8zHMQof3DLQh6Ijk1ml/YYMb5ZfJgK1PTXccGQKFCdh992Q7z0HOrw3KlmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:58:28.810409Z"},"content_sha256":"a0c1596264eb1f35171ed0f4f4cfb852d59b9ce5f74374a1aca43a8444f40ad9","schema_version":"1.0","event_id":"sha256:a0c1596264eb1f35171ed0f4f4cfb852d59b9ce5f74374a1aca43a8444f40ad9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Y2RSG5QK5IWXGHEL3IYAH5WJ5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Selection Curriculum for Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"James Cross, Philipp Koehn, Shafiq Joty, Shruti Bhosale, Tasnim Mohiuddin, Vishrav Chaudhary","submitted_at":"2022-03-25T19:08:30Z","abstract_excerpt":"Neural Machine Translation (NMT) models are typically trained on heterogeneous data that are concatenated and randomly shuffled. However, not all of the training data are equally useful to the model. Curriculum training aims to present the data to the NMT models in a meaningful order. In this work, we introduce a two-stage curriculum training framework for NMT where we fine-tune a base NMT model on subsets of data, selected by both deterministic scoring using pre-trained methods and online scoring that considers prediction scores of the emerging NMT model. Through comprehensive experiments on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13867","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/2203.13867/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":"2026-07-05T04:08:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wc9JpJx/gyzg0umDoLu9tjuJH2+S8/fhScaXhQlJztwFYwojAlhwNRigiCiK/YEq87AJAovQAnvDXYXXbCMjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:58:28.810933Z"},"content_sha256":"7c927dd240bf0c3e1bd91c4b528a49fc3e45ac80808d5c79953e8f1ebd17b81f","schema_version":"1.0","event_id":"sha256:7c927dd240bf0c3e1bd91c4b528a49fc3e45ac80808d5c79953e8f1ebd17b81f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2RSG5QK5IWXGHEL3IYAH5WJ5C/bundle.json","state_url":"https://pith.science/pith/Y2RSG5QK5IWXGHEL3IYAH5WJ5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2RSG5QK5IWXGHEL3IYAH5WJ5C/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":"2026-08-20T02:58:28Z","links":{"resolver":"https://pith.science/pith/Y2RSG5QK5IWXGHEL3IYAH5WJ5C","bundle":"https://pith.science/pith/Y2RSG5QK5IWXGHEL3IYAH5WJ5C/bundle.json","state":"https://pith.science/pith/Y2RSG5QK5IWXGHEL3IYAH5WJ5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2RSG5QK5IWXGHEL3IYAH5WJ5C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Y2RSG5QK5IWXGHEL3IYAH5WJ5C","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":"fb444972bbfc6964fe4f1775a786cb0585f08fafaae6eb31d488e66cc7f01786","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:08:30Z","title_canon_sha256":"ee98597cb2bbf2565ee5b0069eb1d98fda4754f0aa6401497e1588d48934a503"},"schema_version":"1.0","source":{"id":"2203.13867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.13867","created_at":"2026-07-05T04:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2203.13867v1","created_at":"2026-07-05T04:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13867","created_at":"2026-07-05T04:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"Y2RSG5QK5IWX","created_at":"2026-07-05T04:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"Y2RSG5QK5IWXGHEL","created_at":"2026-07-05T04:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"Y2RSG5QK","created_at":"2026-07-05T04:08:44Z"}],"graph_snapshots":[{"event_id":"sha256:7c927dd240bf0c3e1bd91c4b528a49fc3e45ac80808d5c79953e8f1ebd17b81f","target":"graph","created_at":"2026-07-05T04:08:44Z","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/2203.13867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural Machine Translation (NMT) models are typically trained on heterogeneous data that are concatenated and randomly shuffled. However, not all of the training data are equally useful to the model. Curriculum training aims to present the data to the NMT models in a meaningful order. In this work, we introduce a two-stage curriculum training framework for NMT where we fine-tune a base NMT model on subsets of data, selected by both deterministic scoring using pre-trained methods and online scoring that considers prediction scores of the emerging NMT model. Through comprehensive experiments on ","authors_text":"James Cross, Philipp Koehn, Shafiq Joty, Shruti Bhosale, Tasnim Mohiuddin, Vishrav Chaudhary","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:08:30Z","title":"Data Selection Curriculum for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13867","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:a0c1596264eb1f35171ed0f4f4cfb852d59b9ce5f74374a1aca43a8444f40ad9","target":"record","created_at":"2026-07-05T04:08:44Z","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":"fb444972bbfc6964fe4f1775a786cb0585f08fafaae6eb31d488e66cc7f01786","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-25T19:08:30Z","title_canon_sha256":"ee98597cb2bbf2565ee5b0069eb1d98fda4754f0aa6401497e1588d48934a503"},"schema_version":"1.0","source":{"id":"2203.13867","kind":"arxiv","version":1}},"canonical_sha256":"c6a323760aea2d731c8bda3003f6c9e884be2469f059d81d520121e067cc61a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6a323760aea2d731c8bda3003f6c9e884be2469f059d81d520121e067cc61a1","first_computed_at":"2026-07-05T04:08:44.320435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:44.320435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5NCUqAPxP8Uh2Q7iSAnMAzVqm9e2vDm7F67Ur1SApOi1fUEo8+Ys4X0X9tUbbHbkzj3AfjNElbPWBnQiv6SECA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:44.320790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.13867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0c1596264eb1f35171ed0f4f4cfb852d59b9ce5f74374a1aca43a8444f40ad9","sha256:7c927dd240bf0c3e1bd91c4b528a49fc3e45ac80808d5c79953e8f1ebd17b81f"],"state_sha256":"6faa4953ba404534ed5434eb99bd1513f2805ebf656e9d2c2b01bbee0adaef18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LllFqWttTfWmLK+OtIsu6GxFz8nt62GJhlInRG0dMypBec7SM3i7rXbBG/h8lYybLY8Hbvr/wlCvaFBCD95xCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T02:58:28.817414Z","bundle_sha256":"6636a91341c5503ebdf39c15942b616a5f474e07a3c1a469ac2c2017e54d350e"}}