{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QRQKHGEVVX5O4S2RNNABDIFDTM","short_pith_number":"pith:QRQKHGEV","canonical_record":{"source":{"id":"1809.03132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-10T04:41:44Z","cross_cats_sorted":[],"title_canon_sha256":"b2b7ce80f845bda7f81deda63ae36a9714e4893cba8c3b2b9ab972df9a23cb32","abstract_canon_sha256":"f4102d82e8c7eb5b2fc0ec37cca4c356f1bc094bf00dac17b06fed0b162fb551"},"schema_version":"1.0"},"canonical_sha256":"8460a39895adfaee4b516b4011a0a39b232a6f6864ff79cbe24d7240755723df","source":{"kind":"arxiv","id":"1809.03132","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.03132","created_at":"2026-05-18T00:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"1809.03132v1","created_at":"2026-05-18T00:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03132","created_at":"2026-05-18T00:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"QRQKHGEVVX5O","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QRQKHGEVVX5O4S2R","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QRQKHGEV","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QRQKHGEVVX5O4S2RNNABDIFDTM","target":"record","payload":{"canonical_record":{"source":{"id":"1809.03132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-10T04:41:44Z","cross_cats_sorted":[],"title_canon_sha256":"b2b7ce80f845bda7f81deda63ae36a9714e4893cba8c3b2b9ab972df9a23cb32","abstract_canon_sha256":"f4102d82e8c7eb5b2fc0ec37cca4c356f1bc094bf00dac17b06fed0b162fb551"},"schema_version":"1.0"},"canonical_sha256":"8460a39895adfaee4b516b4011a0a39b232a6f6864ff79cbe24d7240755723df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:09.890646Z","signature_b64":"jwl7Cw6+Tz/xoEVT87BLv1BTHyWFQ2dqw3pJtnKm3W6VLDgW1gkapy15DwyojLILjcGqhhDw7dhgoCPAYkViDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8460a39895adfaee4b516b4011a0a39b232a6f6864ff79cbe24d7240755723df","last_reissued_at":"2026-05-18T00:06:09.889970Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:09.889970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.03132","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":"2026-05-18T00:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7a4jeot+no6Q8AqYFxQZZQn+r5CgZHWQKV2BEHxmflqze/ZdbaYlIsR7p1xV1JGy6qAxD8cJtyneZscfPAN0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T14:57:24.732059Z"},"content_sha256":"f302849bd25367c8e0fb59e9cdd95f78aa62dfbe72c6f2b2ae99e08741edf4ad","schema_version":"1.0","event_id":"sha256:f302849bd25367c8e0fb59e9cdd95f78aa62dfbe72c6f2b2ae99e08741edf4ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QRQKHGEVVX5O4S2RNNABDIFDTM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenze Shao, Xilin Chen, Yang Feng","submitted_at":"2018-09-10T04:41:44Z","abstract_excerpt":"Neural machine translation (NMT) models are usually trained with the word-level loss using the teacher forcing algorithm, which not only evaluates the translation improperly but also suffers from exposure bias. Sequence-level training under the reinforcement framework can mitigate the problems of the word-level loss, but its performance is unstable due to the high variance of the gradient estimation. On these grounds, we present a method with a differentiable sequence-level training objective based on probabilistic n-gram matching which can avoid the reinforcement framework. In addition, this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03132","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":""},"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":"2026-05-18T00:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fQiyTtwo7xaxBmrYUYbbXax2gx+my/Y469U9ICFIcAxeiybl/O/KPLMNGwEgdO9g5cWJpOwMNyYyPF0xgfqHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T14:57:24.732781Z"},"content_sha256":"67f9e6fb9e6da3423399c5ff6dc40cf6572e939d7d75b1ae466d2e882ef4bbef","schema_version":"1.0","event_id":"sha256:67f9e6fb9e6da3423399c5ff6dc40cf6572e939d7d75b1ae466d2e882ef4bbef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QRQKHGEVVX5O4S2RNNABDIFDTM/bundle.json","state_url":"https://pith.science/pith/QRQKHGEVVX5O4S2RNNABDIFDTM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QRQKHGEVVX5O4S2RNNABDIFDTM/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":"2026-05-29T14:57:24Z","links":{"resolver":"https://pith.science/pith/QRQKHGEVVX5O4S2RNNABDIFDTM","bundle":"https://pith.science/pith/QRQKHGEVVX5O4S2RNNABDIFDTM/bundle.json","state":"https://pith.science/pith/QRQKHGEVVX5O4S2RNNABDIFDTM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QRQKHGEVVX5O4S2RNNABDIFDTM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QRQKHGEVVX5O4S2RNNABDIFDTM","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":"f4102d82e8c7eb5b2fc0ec37cca4c356f1bc094bf00dac17b06fed0b162fb551","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-10T04:41:44Z","title_canon_sha256":"b2b7ce80f845bda7f81deda63ae36a9714e4893cba8c3b2b9ab972df9a23cb32"},"schema_version":"1.0","source":{"id":"1809.03132","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.03132","created_at":"2026-05-18T00:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"1809.03132v1","created_at":"2026-05-18T00:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03132","created_at":"2026-05-18T00:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"QRQKHGEVVX5O","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QRQKHGEVVX5O4S2R","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QRQKHGEV","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:67f9e6fb9e6da3423399c5ff6dc40cf6572e939d7d75b1ae466d2e882ef4bbef","target":"graph","created_at":"2026-05-18T00:06:09Z","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":"Neural machine translation (NMT) models are usually trained with the word-level loss using the teacher forcing algorithm, which not only evaluates the translation improperly but also suffers from exposure bias. Sequence-level training under the reinforcement framework can mitigate the problems of the word-level loss, but its performance is unstable due to the high variance of the gradient estimation. On these grounds, we present a method with a differentiable sequence-level training objective based on probabilistic n-gram matching which can avoid the reinforcement framework. In addition, this ","authors_text":"Chenze Shao, Xilin Chen, Yang Feng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-10T04:41:44Z","title":"Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03132","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:f302849bd25367c8e0fb59e9cdd95f78aa62dfbe72c6f2b2ae99e08741edf4ad","target":"record","created_at":"2026-05-18T00:06:09Z","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":"f4102d82e8c7eb5b2fc0ec37cca4c356f1bc094bf00dac17b06fed0b162fb551","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-10T04:41:44Z","title_canon_sha256":"b2b7ce80f845bda7f81deda63ae36a9714e4893cba8c3b2b9ab972df9a23cb32"},"schema_version":"1.0","source":{"id":"1809.03132","kind":"arxiv","version":1}},"canonical_sha256":"8460a39895adfaee4b516b4011a0a39b232a6f6864ff79cbe24d7240755723df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8460a39895adfaee4b516b4011a0a39b232a6f6864ff79cbe24d7240755723df","first_computed_at":"2026-05-18T00:06:09.889970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:09.889970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jwl7Cw6+Tz/xoEVT87BLv1BTHyWFQ2dqw3pJtnKm3W6VLDgW1gkapy15DwyojLILjcGqhhDw7dhgoCPAYkViDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:09.890646Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.03132","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f302849bd25367c8e0fb59e9cdd95f78aa62dfbe72c6f2b2ae99e08741edf4ad","sha256:67f9e6fb9e6da3423399c5ff6dc40cf6572e939d7d75b1ae466d2e882ef4bbef"],"state_sha256":"c81ef629003c7010dd64fdea6faac0458909548727ae3a675d4766f349ba4906"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/2YbM9ERgHEmm3Ehc8BWr9DrrfyVRVHyIDsT3ak0tcV8hco8GMbFAsOEINphH4soHVrsq2wo+NfWw7ior9w+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T14:57:24.736521Z","bundle_sha256":"0e700c66b6a51d91141bfb30bf77c734e82cadf690a259521333fb0310ef48d9"}}