{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XTDGVFDFREH52G4SVBTAUPACCH","short_pith_number":"pith:XTDGVFDF","canonical_record":{"source":{"id":"2106.03297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T01:55:34Z","cross_cats_sorted":[],"title_canon_sha256":"332c8bbe36a6e0e72921a790b8ce609e4a0ebb98ef13c37e0ee5e7bae35232e5","abstract_canon_sha256":"7ca7e6c52d616052df7a00a1edab7d869495f2100c7a036fbf38723a94957114"},"schema_version":"1.0"},"canonical_sha256":"bcc66a9465890fdd1b92a8660a3c0211cb975f83c7dfd19096fcdde33fdc1fab","source":{"kind":"arxiv","id":"2106.03297","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03297","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03297v1","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03297","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_12","alias_value":"XTDGVFDFREH5","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_16","alias_value":"XTDGVFDFREH52G4S","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_8","alias_value":"XTDGVFDF","created_at":"2026-07-05T02:46:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XTDGVFDFREH52G4SVBTAUPACCH","target":"record","payload":{"canonical_record":{"source":{"id":"2106.03297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T01:55:34Z","cross_cats_sorted":[],"title_canon_sha256":"332c8bbe36a6e0e72921a790b8ce609e4a0ebb98ef13c37e0ee5e7bae35232e5","abstract_canon_sha256":"7ca7e6c52d616052df7a00a1edab7d869495f2100c7a036fbf38723a94957114"},"schema_version":"1.0"},"canonical_sha256":"bcc66a9465890fdd1b92a8660a3c0211cb975f83c7dfd19096fcdde33fdc1fab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:48.306469Z","signature_b64":"2w5wK+/a8iruEgjYSK6Az0F/o38BNRrwkz0ObV9uYjstDVppyfmOFn3hFKfQhdtU/cDoQi5uaUcHFmCIldrfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcc66a9465890fdd1b92a8660a3c0211cb975f83c7dfd19096fcdde33fdc1fab","last_reissued_at":"2026-07-05T02:46:48.306043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:48.306043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.03297","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":"2026-07-05T02:46:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f+AGG3IS9A6l0QtyWoysPDoUFgNuLJhQ0dn0zojwFHQgQOBzfz7JKezy3QMGWkijVX3iEcTi27wlZMP28wAPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:07:24.562345Z"},"content_sha256":"3b26e5fb8ed609f134541ace301ee4416ad4af2a11712275cd28e50ad152e2a4","schema_version":"1.0","event_id":"sha256:3b26e5fb8ed609f134541ace301ee4416ad4af2a11712275cd28e50ad152e2a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XTDGVFDFREH52G4SVBTAUPACCH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Language Coverage Bias for Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maosong Sun, Shuming Shi, Shuo Wang, Yang Liu, Zhaopeng Tu, Zhixing Tan","submitted_at":"2021-06-07T01:55:34Z","abstract_excerpt":"Language coverage bias, which indicates the content-dependent differences between sentence pairs originating from the source and target languages, is important for neural machine translation (NMT) because the target-original training data is not well exploited in current practice. By carefully designing experiments, we provide comprehensive analyses of the language coverage bias in the training data, and find that using only the source-original data achieves comparable performance with using full training data. Based on these observations, we further propose two simple and effective approaches"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03297","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/2106.03297/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":"2026-07-05T02:46:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/tUJIIbhn/jSFjuQ4w93ZwuSBYBS75o6wdIlTmJKZq2gLzbZ1/4lc3MK9fz1KXaQ8FTw9VRtLNZhNBEDOrIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:07:24.562901Z"},"content_sha256":"2675c39f8cb998a8d3c4b7536dfef37656adad14395f20b5e381fcee70f2cce9","schema_version":"1.0","event_id":"sha256:2675c39f8cb998a8d3c4b7536dfef37656adad14395f20b5e381fcee70f2cce9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTDGVFDFREH52G4SVBTAUPACCH/bundle.json","state_url":"https://pith.science/pith/XTDGVFDFREH52G4SVBTAUPACCH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTDGVFDFREH52G4SVBTAUPACCH/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":"2026-08-04T05:07:24Z","links":{"resolver":"https://pith.science/pith/XTDGVFDFREH52G4SVBTAUPACCH","bundle":"https://pith.science/pith/XTDGVFDFREH52G4SVBTAUPACCH/bundle.json","state":"https://pith.science/pith/XTDGVFDFREH52G4SVBTAUPACCH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTDGVFDFREH52G4SVBTAUPACCH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XTDGVFDFREH52G4SVBTAUPACCH","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":"7ca7e6c52d616052df7a00a1edab7d869495f2100c7a036fbf38723a94957114","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T01:55:34Z","title_canon_sha256":"332c8bbe36a6e0e72921a790b8ce609e4a0ebb98ef13c37e0ee5e7bae35232e5"},"schema_version":"1.0","source":{"id":"2106.03297","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03297","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03297v1","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03297","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_12","alias_value":"XTDGVFDFREH5","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_16","alias_value":"XTDGVFDFREH52G4S","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_8","alias_value":"XTDGVFDF","created_at":"2026-07-05T02:46:48Z"}],"graph_snapshots":[{"event_id":"sha256:2675c39f8cb998a8d3c4b7536dfef37656adad14395f20b5e381fcee70f2cce9","target":"graph","created_at":"2026-07-05T02:46:48Z","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/2106.03297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language coverage bias, which indicates the content-dependent differences between sentence pairs originating from the source and target languages, is important for neural machine translation (NMT) because the target-original training data is not well exploited in current practice. By carefully designing experiments, we provide comprehensive analyses of the language coverage bias in the training data, and find that using only the source-original data achieves comparable performance with using full training data. Based on these observations, we further propose two simple and effective approaches","authors_text":"Maosong Sun, Shuming Shi, Shuo Wang, Yang Liu, Zhaopeng Tu, Zhixing Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T01:55:34Z","title":"On the Language Coverage Bias for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03297","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":"sha256:3b26e5fb8ed609f134541ace301ee4416ad4af2a11712275cd28e50ad152e2a4","target":"record","created_at":"2026-07-05T02:46:48Z","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":"7ca7e6c52d616052df7a00a1edab7d869495f2100c7a036fbf38723a94957114","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T01:55:34Z","title_canon_sha256":"332c8bbe36a6e0e72921a790b8ce609e4a0ebb98ef13c37e0ee5e7bae35232e5"},"schema_version":"1.0","source":{"id":"2106.03297","kind":"arxiv","version":1}},"canonical_sha256":"bcc66a9465890fdd1b92a8660a3c0211cb975f83c7dfd19096fcdde33fdc1fab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcc66a9465890fdd1b92a8660a3c0211cb975f83c7dfd19096fcdde33fdc1fab","first_computed_at":"2026-07-05T02:46:48.306043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:48.306043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2w5wK+/a8iruEgjYSK6Az0F/o38BNRrwkz0ObV9uYjstDVppyfmOFn3hFKfQhdtU/cDoQi5uaUcHFmCIldrfBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:48.306469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.03297","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b26e5fb8ed609f134541ace301ee4416ad4af2a11712275cd28e50ad152e2a4","sha256:2675c39f8cb998a8d3c4b7536dfef37656adad14395f20b5e381fcee70f2cce9"],"state_sha256":"6275c48671131103092f354f458bf76f16b2f4501217b23e79c2ecb9f9c37c81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sVZ9KQHJEbQesaGlF4rtVxKlN5TRhXy4Bt566te9rCKmgfB18mDdD+TDbbvPPOWaXubL2gmTv08xs50NNgaqAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:07:24.567616Z","bundle_sha256":"df230a0562f423ce7b042fd8483d4bbea5d5c920db684b564046cc5ebd13c598"}}