{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PCMWTGFKIZ7GT5JNEH63RLKJDP","short_pith_number":"pith:PCMWTGFK","canonical_record":{"source":{"id":"2105.05498","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T08:11:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7bfd44b7b7eea85326c211ca909651e5574569fa0c8fc7ff724cff4d62e3cf77","abstract_canon_sha256":"5dd3bd6ddf0c410a8dc8918ccad8c576a458a12edbd69cd908486eee77fa44f4"},"schema_version":"1.0"},"canonical_sha256":"78996998aa467e69f52d21fdb8ad491bc982e79eada5c6b3411f9c4c0c2a683a","source":{"kind":"arxiv","id":"2105.05498","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05498","created_at":"2026-07-05T03:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05498v3","created_at":"2026-07-05T03:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05498","created_at":"2026-07-05T03:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"PCMWTGFKIZ7G","created_at":"2026-07-05T03:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"PCMWTGFKIZ7GT5JN","created_at":"2026-07-05T03:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"PCMWTGFK","created_at":"2026-07-05T03:05:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PCMWTGFKIZ7GT5JNEH63RLKJDP","target":"record","payload":{"canonical_record":{"source":{"id":"2105.05498","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T08:11:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7bfd44b7b7eea85326c211ca909651e5574569fa0c8fc7ff724cff4d62e3cf77","abstract_canon_sha256":"5dd3bd6ddf0c410a8dc8918ccad8c576a458a12edbd69cd908486eee77fa44f4"},"schema_version":"1.0"},"canonical_sha256":"78996998aa467e69f52d21fdb8ad491bc982e79eada5c6b3411f9c4c0c2a683a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:12.917822Z","signature_b64":"ImKkEIuR5r7xX+HWoYFfDB1ylrqwUc1FiWKsu64Wcp85wbQWIESpXUR3DMOL7EzjcaU1q+PMfy8q6ivI4AX1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78996998aa467e69f52d21fdb8ad491bc982e79eada5c6b3411f9c4c0c2a683a","last_reissued_at":"2026-07-05T03:05:12.917474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:12.917474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.05498","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HCTOiZc7mLdgGDrZjVDrzKA0bRDqzYwRAUJo1kByMuQ0KipiHKkZSituspgkV2ePZ41spwDRaF0A7G3XKnKOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:37:30.636183Z"},"content_sha256":"2866294bd1744b1010bc7a65af6553cedec3e614473ffc11a972113b665531af","schema_version":"1.0","event_id":"sha256:2866294bd1744b1010bc7a65af6553cedec3e614473ffc11a972113b665531af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PCMWTGFKIZ7GT5JNEH63RLKJDP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Edward Choi, Gyubok Lee, Seongjun Yang","submitted_at":"2021-05-12T08:11:33Z","abstract_excerpt":"Accurate terminology translation is crucial for ensuring the practicality and reliability of neural machine translation (NMT) systems. To address this, lexically constrained NMT explores various methods to ensure pre-specified words and phrases appear in the translation output. However, in many cases, those methods are studied on general domain corpora, where the terms are mostly uni- and bi-grams (>98%). In this paper, we instead tackle a more challenging setup consisting of domain-specific corpora with much longer n-gram and highly specialized terms. Inspired by the recent success of masked "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05498","kind":"arxiv","version":3},"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/2105.05498/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":"2026-07-05T03:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PI+6/xVt+lbfy0t45uONU36oDbThFkuWRGWyKSKsNLGtBmWjK/Bz5lWFxOmC4H9pp1aOk9hAMN1wwqTX92vsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:37:30.637054Z"},"content_sha256":"1fa8b17c3187bf5aed7d13fa52d8587076279b4db08f69fb6e06289e4467476c","schema_version":"1.0","event_id":"sha256:1fa8b17c3187bf5aed7d13fa52d8587076279b4db08f69fb6e06289e4467476c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PCMWTGFKIZ7GT5JNEH63RLKJDP/bundle.json","state_url":"https://pith.science/pith/PCMWTGFKIZ7GT5JNEH63RLKJDP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PCMWTGFKIZ7GT5JNEH63RLKJDP/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":"2026-08-04T12:37:30Z","links":{"resolver":"https://pith.science/pith/PCMWTGFKIZ7GT5JNEH63RLKJDP","bundle":"https://pith.science/pith/PCMWTGFKIZ7GT5JNEH63RLKJDP/bundle.json","state":"https://pith.science/pith/PCMWTGFKIZ7GT5JNEH63RLKJDP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PCMWTGFKIZ7GT5JNEH63RLKJDP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PCMWTGFKIZ7GT5JNEH63RLKJDP","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":"5dd3bd6ddf0c410a8dc8918ccad8c576a458a12edbd69cd908486eee77fa44f4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T08:11:33Z","title_canon_sha256":"7bfd44b7b7eea85326c211ca909651e5574569fa0c8fc7ff724cff4d62e3cf77"},"schema_version":"1.0","source":{"id":"2105.05498","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05498","created_at":"2026-07-05T03:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05498v3","created_at":"2026-07-05T03:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05498","created_at":"2026-07-05T03:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"PCMWTGFKIZ7G","created_at":"2026-07-05T03:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"PCMWTGFKIZ7GT5JN","created_at":"2026-07-05T03:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"PCMWTGFK","created_at":"2026-07-05T03:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:1fa8b17c3187bf5aed7d13fa52d8587076279b4db08f69fb6e06289e4467476c","target":"graph","created_at":"2026-07-05T03:05:12Z","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/2105.05498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate terminology translation is crucial for ensuring the practicality and reliability of neural machine translation (NMT) systems. To address this, lexically constrained NMT explores various methods to ensure pre-specified words and phrases appear in the translation output. However, in many cases, those methods are studied on general domain corpora, where the terms are mostly uni- and bi-grams (>98%). In this paper, we instead tackle a more challenging setup consisting of domain-specific corpora with much longer n-gram and highly specialized terms. Inspired by the recent success of masked ","authors_text":"Edward Choi, Gyubok Lee, Seongjun Yang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T08:11:33Z","title":"Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05498","kind":"arxiv","version":3},"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":"sha256:2866294bd1744b1010bc7a65af6553cedec3e614473ffc11a972113b665531af","target":"record","created_at":"2026-07-05T03:05:12Z","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":"5dd3bd6ddf0c410a8dc8918ccad8c576a458a12edbd69cd908486eee77fa44f4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T08:11:33Z","title_canon_sha256":"7bfd44b7b7eea85326c211ca909651e5574569fa0c8fc7ff724cff4d62e3cf77"},"schema_version":"1.0","source":{"id":"2105.05498","kind":"arxiv","version":3}},"canonical_sha256":"78996998aa467e69f52d21fdb8ad491bc982e79eada5c6b3411f9c4c0c2a683a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78996998aa467e69f52d21fdb8ad491bc982e79eada5c6b3411f9c4c0c2a683a","first_computed_at":"2026-07-05T03:05:12.917474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:12.917474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ImKkEIuR5r7xX+HWoYFfDB1ylrqwUc1FiWKsu64Wcp85wbQWIESpXUR3DMOL7EzjcaU1q+PMfy8q6ivI4AX1AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:12.917822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.05498","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2866294bd1744b1010bc7a65af6553cedec3e614473ffc11a972113b665531af","sha256:1fa8b17c3187bf5aed7d13fa52d8587076279b4db08f69fb6e06289e4467476c"],"state_sha256":"b13c7c69126c431a46386b1c3b363ed1be5192d85e936804ab913c78acea987e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fgiks7bIAoYNPJzNkXZY4agKv9sWcpXt76tfIpN6spo2Bfg3fkvjoRYLXvFUHFjawUQZ8qhg2Sit7I4XdlFrDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:37:30.644091Z","bundle_sha256":"dbfb518bf780fb2f46f2dd7b9e8e3502ca8bc7f64923e302eb16f7172fa57ea4"}}