{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4GENHVMKGOMPJANH6FFXDTOKI6","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":"ea33ddd7699b051ac0ca9414868d282d88121b1e3066d9510b920cd412c19990","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-20T22:39:44Z","title_canon_sha256":"ce0b5c39369f1b804446b663c3d4a428250dd4626bf504f1beaf273b263d77e6"},"schema_version":"1.0","source":{"id":"1906.08885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08885","created_at":"2026-05-17T23:42:47Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08885v1","created_at":"2026-05-17T23:42:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08885","created_at":"2026-05-17T23:42:47Z"},{"alias_kind":"pith_short_12","alias_value":"4GENHVMKGOMP","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4GENHVMKGOMPJANH","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4GENHVMK","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:c33500eb3f6071c76ed88b58326e16c863f038490f462517fa252bb714232155","target":"graph","created_at":"2026-05-17T23:42:47Z","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":"In this paper, we describe our submission to the WMT19 low-resource parallel corpus filtering shared task. Our main approach is based on the LASER toolkit (Language-Agnostic SEntence Representations), which uses an encoder-decoder architecture trained on a parallel corpus to obtain multilingual sentence representations. We then use the representations directly to score and filter the noisy parallel sentences without additionally training a scoring function. We contrast our approach to other promising methods and show that LASER yields strong results. Finally, we produce an ensemble of differen","authors_text":"Francisco Guzm\\'an, Holger Schwenk, Philipp Koehn, Vishrav Chaudhary, Yuqing Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-20T22:39:44Z","title":"Low-Resource Corpus Filtering using Multilingual Sentence Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08885","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":"sha256:325df6ea81fc89ff07978863555d8ab609836f9d9d4f16a9a5645c223b13860a","target":"record","created_at":"2026-05-17T23:42:47Z","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":"ea33ddd7699b051ac0ca9414868d282d88121b1e3066d9510b920cd412c19990","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-20T22:39:44Z","title_canon_sha256":"ce0b5c39369f1b804446b663c3d4a428250dd4626bf504f1beaf273b263d77e6"},"schema_version":"1.0","source":{"id":"1906.08885","kind":"arxiv","version":1}},"canonical_sha256":"e188d3d58a3398f481a7f14b71cdca478268699f53e432be8e1f1c5281457ed0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e188d3d58a3398f481a7f14b71cdca478268699f53e432be8e1f1c5281457ed0","first_computed_at":"2026-05-17T23:42:47.541826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:47.541826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z3qGkav3pRMRsPuSk/jQcmU61tbnIObtHHbiPxypsRRFmH9I0JdG5Q6os6N5PjJdeKUUqnANPaQVNR6kduYtBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:47.542355Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:325df6ea81fc89ff07978863555d8ab609836f9d9d4f16a9a5645c223b13860a","sha256:c33500eb3f6071c76ed88b58326e16c863f038490f462517fa252bb714232155"],"state_sha256":"587f9326852a7f280e610b132529520fd282c93fbfe70a997d906d28dd3c1121"}