{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XNRRL5FA73JSYFEY2BZUXUK6NI","short_pith_number":"pith:XNRRL5FA","canonical_record":{"source":{"id":"1903.09848","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T17:33:38Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"cdeb495060c38a46c9f543e4d6e53fc0963057e98d83d118b262532a367c207b","abstract_canon_sha256":"af7e5f191b52f8f1ee1e223604f88fffebd24b65496cb919279a22369e96c66c"},"schema_version":"1.0"},"canonical_sha256":"bb6315f4a0fed32c1498d0734bd15e6a0cacd5c3ffb1f2d493a5fa40fe8f1776","source":{"kind":"arxiv","id":"1903.09848","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09848","created_at":"2026-05-17T23:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09848v2","created_at":"2026-05-17T23:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09848","created_at":"2026-05-17T23:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"XNRRL5FA73JS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XNRRL5FA73JSYFEY","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XNRRL5FA","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XNRRL5FA73JSYFEY2BZUXUK6NI","target":"record","payload":{"canonical_record":{"source":{"id":"1903.09848","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T17:33:38Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"cdeb495060c38a46c9f543e4d6e53fc0963057e98d83d118b262532a367c207b","abstract_canon_sha256":"af7e5f191b52f8f1ee1e223604f88fffebd24b65496cb919279a22369e96c66c"},"schema_version":"1.0"},"canonical_sha256":"bb6315f4a0fed32c1498d0734bd15e6a0cacd5c3ffb1f2d493a5fa40fe8f1776","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:18.652954Z","signature_b64":"/XujM2otMD6mxdPQcd7dKSMtkSUGf+nesITj/+AVVpJNROu7pDLqQ0/AqGdfmwXEgFub/RWRCnD918WM8dTABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb6315f4a0fed32c1498d0734bd15e6a0cacd5c3ffb1f2d493a5fa40fe8f1776","last_reissued_at":"2026-05-17T23:50:18.652213Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:18.652213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.09848","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RoayNiKYIUSnFzOeBAnwbuT03Q0T3Lpxl8MjMtTZwqv0acbMFTNrfHfwrLVpG64Ka+3LeuRDqqCHpfKTv+MQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:46:33.472547Z"},"content_sha256":"118f71b8ca081df51014e2272c20e0f7b9e3fe5162f32f4efff3a799bfebfd48","schema_version":"1.0","event_id":"sha256:118f71b8ca081df51014e2272c20e0f7b9e3fe5162f32f4efff3a799bfebfd48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XNRRL5FA73JSYFEY2BZUXUK6NI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Competence-based Curriculum Learning for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Barnabas Poczos, Emmanouil Antonios Platanios, Graham Neubig, Otilia Stretcu, Tom M. Mitchell","submitted_at":"2019-03-23T17:33:38Z","abstract_excerpt":"Current state-of-the-art NMT systems use large neural networks that are not only slow to train, but also often require many heuristics and optimization tricks, such as specialized learning rate schedules and large batch sizes. This is undesirable as it requires extensive hyperparameter tuning. In this paper, we propose a curriculum learning framework for NMT that reduces training time, reduces the need for specialized heuristics or large batch sizes, and results in overall better performance. Our framework consists of a principled way of deciding which training samples are shown to the model a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09848","kind":"arxiv","version":2},"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":"2026-05-17T23:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qE0X7a2twQd322bZgcQy4TFkUDeI5c671LcYkDNpDT5QpVJZrJcKYnlmXQiI37JmSm0KVWKPb2rr2XqwlaDlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:46:33.473268Z"},"content_sha256":"559027eceae39a5678d99fe8cff6bab4b1a51c4c4b11127a07d2e37dccfe778c","schema_version":"1.0","event_id":"sha256:559027eceae39a5678d99fe8cff6bab4b1a51c4c4b11127a07d2e37dccfe778c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XNRRL5FA73JSYFEY2BZUXUK6NI/bundle.json","state_url":"https://pith.science/pith/XNRRL5FA73JSYFEY2BZUXUK6NI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XNRRL5FA73JSYFEY2BZUXUK6NI/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":"2026-05-30T17:46:33Z","links":{"resolver":"https://pith.science/pith/XNRRL5FA73JSYFEY2BZUXUK6NI","bundle":"https://pith.science/pith/XNRRL5FA73JSYFEY2BZUXUK6NI/bundle.json","state":"https://pith.science/pith/XNRRL5FA73JSYFEY2BZUXUK6NI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XNRRL5FA73JSYFEY2BZUXUK6NI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XNRRL5FA73JSYFEY2BZUXUK6NI","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":"af7e5f191b52f8f1ee1e223604f88fffebd24b65496cb919279a22369e96c66c","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T17:33:38Z","title_canon_sha256":"cdeb495060c38a46c9f543e4d6e53fc0963057e98d83d118b262532a367c207b"},"schema_version":"1.0","source":{"id":"1903.09848","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09848","created_at":"2026-05-17T23:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09848v2","created_at":"2026-05-17T23:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09848","created_at":"2026-05-17T23:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"XNRRL5FA73JS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XNRRL5FA73JSYFEY","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XNRRL5FA","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:559027eceae39a5678d99fe8cff6bab4b1a51c4c4b11127a07d2e37dccfe778c","target":"graph","created_at":"2026-05-17T23:50:18Z","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":"Current state-of-the-art NMT systems use large neural networks that are not only slow to train, but also often require many heuristics and optimization tricks, such as specialized learning rate schedules and large batch sizes. This is undesirable as it requires extensive hyperparameter tuning. In this paper, we propose a curriculum learning framework for NMT that reduces training time, reduces the need for specialized heuristics or large batch sizes, and results in overall better performance. Our framework consists of a principled way of deciding which training samples are shown to the model a","authors_text":"Barnabas Poczos, Emmanouil Antonios Platanios, Graham Neubig, Otilia Stretcu, Tom M. Mitchell","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T17:33:38Z","title":"Competence-based Curriculum Learning for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09848","kind":"arxiv","version":2},"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":"sha256:118f71b8ca081df51014e2272c20e0f7b9e3fe5162f32f4efff3a799bfebfd48","target":"record","created_at":"2026-05-17T23:50:18Z","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":"af7e5f191b52f8f1ee1e223604f88fffebd24b65496cb919279a22369e96c66c","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T17:33:38Z","title_canon_sha256":"cdeb495060c38a46c9f543e4d6e53fc0963057e98d83d118b262532a367c207b"},"schema_version":"1.0","source":{"id":"1903.09848","kind":"arxiv","version":2}},"canonical_sha256":"bb6315f4a0fed32c1498d0734bd15e6a0cacd5c3ffb1f2d493a5fa40fe8f1776","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb6315f4a0fed32c1498d0734bd15e6a0cacd5c3ffb1f2d493a5fa40fe8f1776","first_computed_at":"2026-05-17T23:50:18.652213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:18.652213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/XujM2otMD6mxdPQcd7dKSMtkSUGf+nesITj/+AVVpJNROu7pDLqQ0/AqGdfmwXEgFub/RWRCnD918WM8dTABA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:18.652954Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.09848","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:118f71b8ca081df51014e2272c20e0f7b9e3fe5162f32f4efff3a799bfebfd48","sha256:559027eceae39a5678d99fe8cff6bab4b1a51c4c4b11127a07d2e37dccfe778c"],"state_sha256":"dc596c4adf33f2ff8cb1d8d3a5390cc575b486546e33f13118919c8a803c0611"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mfWZRdWi60IBXox/XCYg3az8gx0KmFoseU48Ugdqvl1qMLI32irDhWV+tYzp/S17BYFlga0fpZ2xT+iVi01uAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T17:46:33.477242Z","bundle_sha256":"97291252437bfadd073353fe7e112499a39af70699cdff1f4e2db8097b8b5374"}}