{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2ZHTQXHAXMO66AKCXEEQTMKL3Z","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":"d376a809aaeeff44ccfc0fdfa1e38e0fe9817fc9f74078ab5fe3357cdcbc2071","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-23T21:07:42Z","title_canon_sha256":"3178169d351d5dc0389442573b90a5636c32c4f307e93ffee8ba730c0c540de3"},"schema_version":"1.0","source":{"id":"2208.11194","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.11194","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"arxiv_version","alias_value":"2208.11194v1","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11194","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"pith_short_12","alias_value":"2ZHTQXHAXMO6","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"pith_short_16","alias_value":"2ZHTQXHAXMO66AKC","created_at":"2026-07-05T04:51:12Z"},{"alias_kind":"pith_short_8","alias_value":"2ZHTQXHA","created_at":"2026-07-05T04:51:12Z"}],"graph_snapshots":[{"event_id":"sha256:908f51019d7f879fbdbbe4ab203acc644220f4883f8525e896f3820f051c465c","target":"graph","created_at":"2026-07-05T04:51:12Z","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/2208.11194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mining high-quality bitexts for low-resource languages is challenging. This paper shows that sentence representation of language models fine-tuned with multiple negatives ranking loss, a contrastive objective, helps retrieve clean bitexts. Experiments show that parallel data mined from our approach substantially outperform the previous state-of-the-art method on low resource languages Khmer and Pashto.","authors_text":"Philipp Koehn, Weiting Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-23T21:07:42Z","title":"Bitext Mining for Low-Resource Languages via Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11194","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:dc010f1330ce6437d0b4a89c6032790b1a00c12498b2364c576e84a33bc34154","target":"record","created_at":"2026-07-05T04:51:12Z","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":"d376a809aaeeff44ccfc0fdfa1e38e0fe9817fc9f74078ab5fe3357cdcbc2071","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-23T21:07:42Z","title_canon_sha256":"3178169d351d5dc0389442573b90a5636c32c4f307e93ffee8ba730c0c540de3"},"schema_version":"1.0","source":{"id":"2208.11194","kind":"arxiv","version":1}},"canonical_sha256":"d64f385ce0bb1def0142b90909b14bde552473247a207f8259748a83d67482cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d64f385ce0bb1def0142b90909b14bde552473247a207f8259748a83d67482cb","first_computed_at":"2026-07-05T04:51:12.356334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:12.356334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V/heLObdBW3qn3l9KWJXbicea87CNkKGQp/uSroEyxbwXvSAEb04Vl8ID1VVB6BU7HT+OehexemjzaF3XRTDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:12.356831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.11194","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc010f1330ce6437d0b4a89c6032790b1a00c12498b2364c576e84a33bc34154","sha256:908f51019d7f879fbdbbe4ab203acc644220f4883f8525e896f3820f051c465c"],"state_sha256":"7c279a5dff9a438dac8b0dbf5a740144e70349c4f5ce97dbb114e397c687bc9c"}