{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YMGVGUSU6RWOEF27NFGCIRADOE","short_pith_number":"pith:YMGVGUSU","canonical_record":{"source":{"id":"2203.12210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-23T05:54:37Z","cross_cats_sorted":[],"title_canon_sha256":"cc9a36f114e4fe84676d4327085140fd8ed0787232253488179d49f5fb9f0d0a","abstract_canon_sha256":"48779f06346057231b0673412da9368ad88e51bf83c93ccc5f243edc218354c7"},"schema_version":"1.0"},"canonical_sha256":"c30d535254f46ce2175f694c244403713aab2a0ac402bf41541e077bcb370ebb","source":{"kind":"arxiv","id":"2203.12210","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.12210","created_at":"2026-07-05T04:07:56Z"},{"alias_kind":"arxiv_version","alias_value":"2203.12210v1","created_at":"2026-07-05T04:07:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12210","created_at":"2026-07-05T04:07:56Z"},{"alias_kind":"pith_short_12","alias_value":"YMGVGUSU6RWO","created_at":"2026-07-05T04:07:56Z"},{"alias_kind":"pith_short_16","alias_value":"YMGVGUSU6RWOEF27","created_at":"2026-07-05T04:07:56Z"},{"alias_kind":"pith_short_8","alias_value":"YMGVGUSU","created_at":"2026-07-05T04:07:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YMGVGUSU6RWOEF27NFGCIRADOE","target":"record","payload":{"canonical_record":{"source":{"id":"2203.12210","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-23T05:54:37Z","cross_cats_sorted":[],"title_canon_sha256":"cc9a36f114e4fe84676d4327085140fd8ed0787232253488179d49f5fb9f0d0a","abstract_canon_sha256":"48779f06346057231b0673412da9368ad88e51bf83c93ccc5f243edc218354c7"},"schema_version":"1.0"},"canonical_sha256":"c30d535254f46ce2175f694c244403713aab2a0ac402bf41541e077bcb370ebb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:56.972327Z","signature_b64":"pz/uGGNfa8QCyVXusFHm6soiBiLdEfOFd/DRTj+LkCzDugd1kb8bvf0oH7KH7IzgYbs5Euh8LQEdS3LjwTilAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c30d535254f46ce2175f694c244403713aab2a0ac402bf41541e077bcb370ebb","last_reissued_at":"2026-07-05T04:07:56.971820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:56.971820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.12210","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":"2026-07-05T04:07:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xFTBA3GXXj18s+ln7ejf5qWuieLpBFwv+m/GUdCMiXiLEMr5FlAeu4Tx3yxykRAoRBcwgXeCF2mCMy++k/+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:06:00.479901Z"},"content_sha256":"a8ddc02b52af496e90d9f05a6db7c363de32461970738f0d43717cec6dbb2ad2","schema_version":"1.0","event_id":"sha256:a8ddc02b52af496e90d9f05a6db7c363de32461970738f0d43717cec6dbb2ad2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YMGVGUSU6RWOEF27NFGCIRADOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Integrating Vectorized Lexical Constraints for Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shuo Wang, Yang Liu, Zhixing Tan","submitted_at":"2022-03-23T05:54:37Z","abstract_excerpt":"Lexically constrained neural machine translation (NMT), which controls the generation of NMT models with pre-specified constraints, is important in many practical scenarios. Due to the representation gap between discrete constraints and continuous vectors in NMT models, most existing works choose to construct synthetic data or modify the decoding algorithm to impose lexical constraints, treating the NMT model as a black box. In this work, we propose to open this black box by directly integrating the constraints into NMT models. Specifically, we vectorize source and target constraints into cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12210","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/2203.12210/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":"2026-07-05T04:07:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZemKqIhOHbkF7iKETFs64jKZQLMvydlspUAh9iNfNG2F+zApONWRboR9XvKOVjPvE8DGlFRSv8wv1PsIgGuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:06:00.480384Z"},"content_sha256":"895f6e5f805931dc2b2abc516af7daba709ea6b31a7997901d515dffef5c2c82","schema_version":"1.0","event_id":"sha256:895f6e5f805931dc2b2abc516af7daba709ea6b31a7997901d515dffef5c2c82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YMGVGUSU6RWOEF27NFGCIRADOE/bundle.json","state_url":"https://pith.science/pith/YMGVGUSU6RWOEF27NFGCIRADOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YMGVGUSU6RWOEF27NFGCIRADOE/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":"2026-08-04T09:06:00Z","links":{"resolver":"https://pith.science/pith/YMGVGUSU6RWOEF27NFGCIRADOE","bundle":"https://pith.science/pith/YMGVGUSU6RWOEF27NFGCIRADOE/bundle.json","state":"https://pith.science/pith/YMGVGUSU6RWOEF27NFGCIRADOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YMGVGUSU6RWOEF27NFGCIRADOE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YMGVGUSU6RWOEF27NFGCIRADOE","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":"48779f06346057231b0673412da9368ad88e51bf83c93ccc5f243edc218354c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-23T05:54:37Z","title_canon_sha256":"cc9a36f114e4fe84676d4327085140fd8ed0787232253488179d49f5fb9f0d0a"},"schema_version":"1.0","source":{"id":"2203.12210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.12210","created_at":"2026-07-05T04:07:56Z"},{"alias_kind":"arxiv_version","alias_value":"2203.12210v1","created_at":"2026-07-05T04:07:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12210","created_at":"2026-07-05T04:07:56Z"},{"alias_kind":"pith_short_12","alias_value":"YMGVGUSU6RWO","created_at":"2026-07-05T04:07:56Z"},{"alias_kind":"pith_short_16","alias_value":"YMGVGUSU6RWOEF27","created_at":"2026-07-05T04:07:56Z"},{"alias_kind":"pith_short_8","alias_value":"YMGVGUSU","created_at":"2026-07-05T04:07:56Z"}],"graph_snapshots":[{"event_id":"sha256:895f6e5f805931dc2b2abc516af7daba709ea6b31a7997901d515dffef5c2c82","target":"graph","created_at":"2026-07-05T04:07:56Z","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/2203.12210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lexically constrained neural machine translation (NMT), which controls the generation of NMT models with pre-specified constraints, is important in many practical scenarios. Due to the representation gap between discrete constraints and continuous vectors in NMT models, most existing works choose to construct synthetic data or modify the decoding algorithm to impose lexical constraints, treating the NMT model as a black box. In this work, we propose to open this black box by directly integrating the constraints into NMT models. Specifically, we vectorize source and target constraints into cont","authors_text":"Shuo Wang, Yang Liu, Zhixing Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-23T05:54:37Z","title":"Integrating Vectorized Lexical Constraints for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12210","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:a8ddc02b52af496e90d9f05a6db7c363de32461970738f0d43717cec6dbb2ad2","target":"record","created_at":"2026-07-05T04:07:56Z","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":"48779f06346057231b0673412da9368ad88e51bf83c93ccc5f243edc218354c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-23T05:54:37Z","title_canon_sha256":"cc9a36f114e4fe84676d4327085140fd8ed0787232253488179d49f5fb9f0d0a"},"schema_version":"1.0","source":{"id":"2203.12210","kind":"arxiv","version":1}},"canonical_sha256":"c30d535254f46ce2175f694c244403713aab2a0ac402bf41541e077bcb370ebb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c30d535254f46ce2175f694c244403713aab2a0ac402bf41541e077bcb370ebb","first_computed_at":"2026-07-05T04:07:56.971820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:07:56.971820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pz/uGGNfa8QCyVXusFHm6soiBiLdEfOFd/DRTj+LkCzDugd1kb8bvf0oH7KH7IzgYbs5Euh8LQEdS3LjwTilAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:07:56.972327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.12210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8ddc02b52af496e90d9f05a6db7c363de32461970738f0d43717cec6dbb2ad2","sha256:895f6e5f805931dc2b2abc516af7daba709ea6b31a7997901d515dffef5c2c82"],"state_sha256":"6beb95f093c1ad99ff7b6d82b95df27a5562cd6a12ee753fb97ddc79477f72bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+IOQ446wAg/HM8m8yhbkZD5qgz77Ccw+uXdoFeFlrt/uTEaUoBlzwcagY4q075wEob7gwQ/v2R0HRxZhzsvIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:06:00.484192Z","bundle_sha256":"0d0e97a31b4ab404fb2152cc8e6e30cab2d542360a6e80fed488129673fb5453"}}