{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HLTYMZZAAHERHTVUA5TIWODIBV","short_pith_number":"pith:HLTYMZZA","canonical_record":{"source":{"id":"2010.02552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T08:57:31Z","cross_cats_sorted":[],"title_canon_sha256":"0f3c29cb215fdd2d1ab2a0d92bb247be3496d5bc1506ded226ef7f6040bc8315","abstract_canon_sha256":"3b038582591ae0c8d70400f5fb9e6a449418586d0d2c7199fdaeaa1b9626815b"},"schema_version":"1.0"},"canonical_sha256":"3ae786672001c913ceb407668b38680d70074965fa1f960baeb957ba84b68805","source":{"kind":"arxiv","id":"2010.02552","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02552","created_at":"2026-07-05T01:40:51Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02552v1","created_at":"2026-07-05T01:40:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02552","created_at":"2026-07-05T01:40:51Z"},{"alias_kind":"pith_short_12","alias_value":"HLTYMZZAAHER","created_at":"2026-07-05T01:40:51Z"},{"alias_kind":"pith_short_16","alias_value":"HLTYMZZAAHERHTVU","created_at":"2026-07-05T01:40:51Z"},{"alias_kind":"pith_short_8","alias_value":"HLTYMZZA","created_at":"2026-07-05T01:40:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HLTYMZZAAHERHTVUA5TIWODIBV","target":"record","payload":{"canonical_record":{"source":{"id":"2010.02552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T08:57:31Z","cross_cats_sorted":[],"title_canon_sha256":"0f3c29cb215fdd2d1ab2a0d92bb247be3496d5bc1506ded226ef7f6040bc8315","abstract_canon_sha256":"3b038582591ae0c8d70400f5fb9e6a449418586d0d2c7199fdaeaa1b9626815b"},"schema_version":"1.0"},"canonical_sha256":"3ae786672001c913ceb407668b38680d70074965fa1f960baeb957ba84b68805","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:51.256254Z","signature_b64":"QrXSMDAXhYT8ruPDAM85pm7KsC/TfmtGbVqkGitpT1r3ysfmJtmo0lTPaDv/fQQhlHjsUkns5KS11Hq/Vp9lBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ae786672001c913ceb407668b38680d70074965fa1f960baeb957ba84b68805","last_reissued_at":"2026-07-05T01:40:51.255871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:51.255871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.02552","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":"2026-07-05T01:40:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GP34NrialGyZduZM2X+5CnBJT+Eb7cirt0Sd92CqF27oxneKA5dOTjvhwp327unUBY096q2hwDXp2coziB5UAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:18:06.360991Z"},"content_sha256":"7e1b525d6220d95dce7db3a0166a1beab962ab997e0c6658413700fc96a84787","schema_version":"1.0","event_id":"sha256:7e1b525d6220d95dce7db3a0166a1beab962ab997e0c6658413700fc96a84787"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HLTYMZZAAHERHTVUA5TIWODIBV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Irwin King, Michael R. Lyu, Shilin He, Wenxiang Jiao, Xing Wang, Zhaopeng Tu","submitted_at":"2020-10-06T08:57:31Z","abstract_excerpt":"Large-scale training datasets lie at the core of the recent success of neural machine translation (NMT) models. However, the complex patterns and potential noises in the large-scale data make training NMT models difficult. In this work, we explore to identify the inactive training examples which contribute less to the model performance, and show that the existence of inactive examples depends on the data distribution. We further introduce data rejuvenation to improve the training of NMT models on large-scale datasets by exploiting inactive examples. The proposed framework consists of three pha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02552","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/2010.02552/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":"2026-07-05T01:40:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q8METTIrj7tHQrng7yEhjJSteBCqfpz0Sa5bVVEAran5pGkptF3pLwzW8kjr/kAFwUl2Jgq05S8hk11wuJEfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:18:06.361811Z"},"content_sha256":"fe57c9776d4c5b7b96324edeea962e50d8aaddfd14a782a076f0bcd4880a0a22","schema_version":"1.0","event_id":"sha256:fe57c9776d4c5b7b96324edeea962e50d8aaddfd14a782a076f0bcd4880a0a22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HLTYMZZAAHERHTVUA5TIWODIBV/bundle.json","state_url":"https://pith.science/pith/HLTYMZZAAHERHTVUA5TIWODIBV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HLTYMZZAAHERHTVUA5TIWODIBV/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":"2026-08-07T12:18:06Z","links":{"resolver":"https://pith.science/pith/HLTYMZZAAHERHTVUA5TIWODIBV","bundle":"https://pith.science/pith/HLTYMZZAAHERHTVUA5TIWODIBV/bundle.json","state":"https://pith.science/pith/HLTYMZZAAHERHTVUA5TIWODIBV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HLTYMZZAAHERHTVUA5TIWODIBV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HLTYMZZAAHERHTVUA5TIWODIBV","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":"3b038582591ae0c8d70400f5fb9e6a449418586d0d2c7199fdaeaa1b9626815b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T08:57:31Z","title_canon_sha256":"0f3c29cb215fdd2d1ab2a0d92bb247be3496d5bc1506ded226ef7f6040bc8315"},"schema_version":"1.0","source":{"id":"2010.02552","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02552","created_at":"2026-07-05T01:40:51Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02552v1","created_at":"2026-07-05T01:40:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02552","created_at":"2026-07-05T01:40:51Z"},{"alias_kind":"pith_short_12","alias_value":"HLTYMZZAAHER","created_at":"2026-07-05T01:40:51Z"},{"alias_kind":"pith_short_16","alias_value":"HLTYMZZAAHERHTVU","created_at":"2026-07-05T01:40:51Z"},{"alias_kind":"pith_short_8","alias_value":"HLTYMZZA","created_at":"2026-07-05T01:40:51Z"}],"graph_snapshots":[{"event_id":"sha256:fe57c9776d4c5b7b96324edeea962e50d8aaddfd14a782a076f0bcd4880a0a22","target":"graph","created_at":"2026-07-05T01:40:51Z","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/2010.02552/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale training datasets lie at the core of the recent success of neural machine translation (NMT) models. However, the complex patterns and potential noises in the large-scale data make training NMT models difficult. In this work, we explore to identify the inactive training examples which contribute less to the model performance, and show that the existence of inactive examples depends on the data distribution. We further introduce data rejuvenation to improve the training of NMT models on large-scale datasets by exploiting inactive examples. The proposed framework consists of three pha","authors_text":"Irwin King, Michael R. Lyu, Shilin He, Wenxiang Jiao, Xing Wang, Zhaopeng Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T08:57:31Z","title":"Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02552","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":"sha256:7e1b525d6220d95dce7db3a0166a1beab962ab997e0c6658413700fc96a84787","target":"record","created_at":"2026-07-05T01:40:51Z","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":"3b038582591ae0c8d70400f5fb9e6a449418586d0d2c7199fdaeaa1b9626815b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-06T08:57:31Z","title_canon_sha256":"0f3c29cb215fdd2d1ab2a0d92bb247be3496d5bc1506ded226ef7f6040bc8315"},"schema_version":"1.0","source":{"id":"2010.02552","kind":"arxiv","version":1}},"canonical_sha256":"3ae786672001c913ceb407668b38680d70074965fa1f960baeb957ba84b68805","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ae786672001c913ceb407668b38680d70074965fa1f960baeb957ba84b68805","first_computed_at":"2026-07-05T01:40:51.255871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:51.255871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QrXSMDAXhYT8ruPDAM85pm7KsC/TfmtGbVqkGitpT1r3ysfmJtmo0lTPaDv/fQQhlHjsUkns5KS11Hq/Vp9lBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:51.256254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.02552","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e1b525d6220d95dce7db3a0166a1beab962ab997e0c6658413700fc96a84787","sha256:fe57c9776d4c5b7b96324edeea962e50d8aaddfd14a782a076f0bcd4880a0a22"],"state_sha256":"da1fc49f0be3dbd560528a51811ee281ca60b31c93960e0ea96e139f7b54624e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XzRuhEYR1s8ChgI6m4h/+kgJELBvsR/ideK8jyCvMRh/ObhsvqQpMsKgcMRry4tLI+FRo75dRI0ICadk9qIGDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:18:06.374289Z","bundle_sha256":"305c7333410679d906df9a15571a4b37b03eb5c1fddc25ec9af039a4fcd97986"}}