{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LZDTTHHKHVNMWJQ7N3YF2K23NB","short_pith_number":"pith:LZDTTHHK","canonical_record":{"source":{"id":"1710.06313","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-17T14:27:36Z","cross_cats_sorted":[],"title_canon_sha256":"88b27436f1c843a1238a1faf7c9c132858aa64bb788dcfbcdc39eec3777e41fe","abstract_canon_sha256":"f80d0dec139568ef35d0316632033d2b46195d17939bde88fa65c68b3464872c"},"schema_version":"1.0"},"canonical_sha256":"5e47399cea3d5acb261f6ef05d2b5b685a5491f88b17c8b59cece218460d51bc","source":{"kind":"arxiv","id":"1710.06313","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.06313","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"arxiv_version","alias_value":"1710.06313v2","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06313","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"pith_short_12","alias_value":"LZDTTHHKHVNM","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LZDTTHHKHVNMWJQ7","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LZDTTHHK","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LZDTTHHKHVNMWJQ7N3YF2K23NB","target":"record","payload":{"canonical_record":{"source":{"id":"1710.06313","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-17T14:27:36Z","cross_cats_sorted":[],"title_canon_sha256":"88b27436f1c843a1238a1faf7c9c132858aa64bb788dcfbcdc39eec3777e41fe","abstract_canon_sha256":"f80d0dec139568ef35d0316632033d2b46195d17939bde88fa65c68b3464872c"},"schema_version":"1.0"},"canonical_sha256":"5e47399cea3d5acb261f6ef05d2b5b685a5491f88b17c8b59cece218460d51bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:03.705490Z","signature_b64":"jiCfFN/dfUAzzYoWXopeYzHvkfJ9++ydmSl27J5m1r0P0mAqBoZonQ96obOe7LeNMG46I+XP1tbX6UhX5tjDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e47399cea3d5acb261f6ef05d2b5b685a5491f88b17c8b59cece218460d51bc","last_reissued_at":"2026-05-17T23:47:03.704975Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:03.704975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.06313","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RFGGEI4pAgcsqv2yS9fQXPhRejI9Ytb3Z5s2IxxQRDNECdxA1KrRq4691x5a7QFDLjHR+uNEFS9LdYUOgKrtAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T17:27:52.213908Z"},"content_sha256":"84dd5956d8ad56af1cfc205d850540020a2edfc2dbe1510e6bd7064d14d4488b","schema_version":"1.0","event_id":"sha256:84dd5956d8ad56af1cfc205d850540020a2edfc2dbe1510e6bd7064d14d4488b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LZDTTHHKHVNMWJQ7N3YF2K23NB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Paying Attention to Multi-Word Expressions in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mat\\=iss Rikters, Ond\\v{r}ej Bojar","submitted_at":"2017-10-17T14:27:36Z","abstract_excerpt":"Processing of multi-word expressions (MWEs) is a known problem for any natural language processing task. Even neural machine translation (NMT) struggles to overcome it. This paper presents results of experiments on investigating NMT attention allocation to the MWEs and improving automated translation of sentences that contain MWEs in English->Latvian and English->Czech NMT systems. Two improvement strategies were explored -(1) bilingual pairs of automatically extracted MWE candidates were added to the parallel corpus used to train the NMT system, and (2) full sentences containing the automatic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06313","kind":"arxiv","version":2},"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":"2026-05-17T23:47:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pBxO3HxtvWCC1vJRNMkNq1MtQApBVLc8mc/4a5e3eDNKZS50xCu8EXU2SgVIdf6PgCFTeTZ1IlULCqxf2X6FDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T17:27:52.214641Z"},"content_sha256":"bd17b0eccb7829b4135913b535faf5c253938fb7bbf0bb668a5ae93bbee3d3de","schema_version":"1.0","event_id":"sha256:bd17b0eccb7829b4135913b535faf5c253938fb7bbf0bb668a5ae93bbee3d3de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZDTTHHKHVNMWJQ7N3YF2K23NB/bundle.json","state_url":"https://pith.science/pith/LZDTTHHKHVNMWJQ7N3YF2K23NB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZDTTHHKHVNMWJQ7N3YF2K23NB/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":"2026-06-06T17:27:52Z","links":{"resolver":"https://pith.science/pith/LZDTTHHKHVNMWJQ7N3YF2K23NB","bundle":"https://pith.science/pith/LZDTTHHKHVNMWJQ7N3YF2K23NB/bundle.json","state":"https://pith.science/pith/LZDTTHHKHVNMWJQ7N3YF2K23NB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZDTTHHKHVNMWJQ7N3YF2K23NB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LZDTTHHKHVNMWJQ7N3YF2K23NB","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":"f80d0dec139568ef35d0316632033d2b46195d17939bde88fa65c68b3464872c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-17T14:27:36Z","title_canon_sha256":"88b27436f1c843a1238a1faf7c9c132858aa64bb788dcfbcdc39eec3777e41fe"},"schema_version":"1.0","source":{"id":"1710.06313","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.06313","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"arxiv_version","alias_value":"1710.06313v2","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06313","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"pith_short_12","alias_value":"LZDTTHHKHVNM","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LZDTTHHKHVNMWJQ7","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LZDTTHHK","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:bd17b0eccb7829b4135913b535faf5c253938fb7bbf0bb668a5ae93bbee3d3de","target":"graph","created_at":"2026-05-17T23:47:03Z","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":"Processing of multi-word expressions (MWEs) is a known problem for any natural language processing task. Even neural machine translation (NMT) struggles to overcome it. This paper presents results of experiments on investigating NMT attention allocation to the MWEs and improving automated translation of sentences that contain MWEs in English->Latvian and English->Czech NMT systems. Two improvement strategies were explored -(1) bilingual pairs of automatically extracted MWE candidates were added to the parallel corpus used to train the NMT system, and (2) full sentences containing the automatic","authors_text":"Mat\\=iss Rikters, Ond\\v{r}ej Bojar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-17T14:27:36Z","title":"Paying Attention to Multi-Word Expressions in Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06313","kind":"arxiv","version":2},"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":"sha256:84dd5956d8ad56af1cfc205d850540020a2edfc2dbe1510e6bd7064d14d4488b","target":"record","created_at":"2026-05-17T23:47:03Z","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":"f80d0dec139568ef35d0316632033d2b46195d17939bde88fa65c68b3464872c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-17T14:27:36Z","title_canon_sha256":"88b27436f1c843a1238a1faf7c9c132858aa64bb788dcfbcdc39eec3777e41fe"},"schema_version":"1.0","source":{"id":"1710.06313","kind":"arxiv","version":2}},"canonical_sha256":"5e47399cea3d5acb261f6ef05d2b5b685a5491f88b17c8b59cece218460d51bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e47399cea3d5acb261f6ef05d2b5b685a5491f88b17c8b59cece218460d51bc","first_computed_at":"2026-05-17T23:47:03.704975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:03.704975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jiCfFN/dfUAzzYoWXopeYzHvkfJ9++ydmSl27J5m1r0P0mAqBoZonQ96obOe7LeNMG46I+XP1tbX6UhX5tjDBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:03.705490Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.06313","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84dd5956d8ad56af1cfc205d850540020a2edfc2dbe1510e6bd7064d14d4488b","sha256:bd17b0eccb7829b4135913b535faf5c253938fb7bbf0bb668a5ae93bbee3d3de"],"state_sha256":"87cb1e2a6866c3e3946d6d8b053edaa767d82d98b8e8190e8b0e4aed4493e9dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c0Vulc3hbCUlQ1jtuvdFwpXENjyekXzcKC/mqzia4i65sHTsZ6NRUUKB+0wxj27KAwCejqSfPQGVdodw4a3PDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T17:27:52.222982Z","bundle_sha256":"883b00b56d309cca9f3a01d61aa91861afae41c8bd1e5b47c03816d7955cb7a7"}}