{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HAKITHMCCOTEOA6HSAP4M7JADG","short_pith_number":"pith:HAKITHMC","canonical_record":{"source":{"id":"2005.06166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-13T06:06:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7f5c5503df6e71846a0d00336e67527a91ccb3c038d0524b4194abef6d4da634","abstract_canon_sha256":"6988c6b73aab244498bf338d082217dd192cfdf535350945c1bdbf127f30afdb"},"schema_version":"1.0"},"canonical_sha256":"3814899d8213a64703c7901fc67d2019812e2dcc1af6963ac7b442ec4c079b31","source":{"kind":"arxiv","id":"2005.06166","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.06166","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2005.06166v1","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.06166","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"HAKITHMCCOTE","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"HAKITHMCCOTEOA6H","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"HAKITHMC","created_at":"2026-07-05T01:02:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HAKITHMCCOTEOA6HSAP4M7JADG","target":"record","payload":{"canonical_record":{"source":{"id":"2005.06166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-13T06:06:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7f5c5503df6e71846a0d00336e67527a91ccb3c038d0524b4194abef6d4da634","abstract_canon_sha256":"6988c6b73aab244498bf338d082217dd192cfdf535350945c1bdbf127f30afdb"},"schema_version":"1.0"},"canonical_sha256":"3814899d8213a64703c7901fc67d2019812e2dcc1af6963ac7b442ec4c079b31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:32.713271Z","signature_b64":"53ZWXvL1Pxcx6VcN6c7MVGEwQltA9eJlE6pDs28lOlv8JWiiZZYamfG0I73fRcflWh8cHw5l6FZv2/WukwllDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3814899d8213a64703c7901fc67d2019812e2dcc1af6963ac7b442ec4c079b31","last_reissued_at":"2026-07-05T01:02:32.712707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:32.712707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.06166","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":"2026-07-05T01:02:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RJoah7oRmNR+x+Hkmu39/JFtGzNSKFA39MaUMnbdgN9/PxM1lzjo34+65aLw/YbzdTpxqpCnWE4irOwzzkLgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:22:20.420998Z"},"content_sha256":"f7d614fa3e0b67d3946f7d3414c518c1f62a95a4964667f7c39a6bc1b6bfba97","schema_version":"1.0","event_id":"sha256:f7d614fa3e0b67d3946f7d3414c518c1f62a95a4964667f7c39a6bc1b6bfba97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HAKITHMCCOTEOA6HSAP4M7JADG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parallel Corpus Filtering via Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ajay Nagesh, Boliang Zhang, Kevin Knight","submitted_at":"2020-05-13T06:06:23Z","abstract_excerpt":"Web-crawled data provides a good source of parallel corpora for training machine translation models. It is automatically obtained, but extremely noisy, and recent work shows that neural machine translation systems are more sensitive to noise than traditional statistical machine translation methods. In this paper, we propose a novel approach to filter out noisy sentence pairs from web-crawled corpora via pre-trained language models. We measure sentence parallelism by leveraging the multilingual capability of BERT and use the Generative Pre-training (GPT) language model as a domain filter to bal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.06166","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/2005.06166/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":"2026-07-05T01:02:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmEocszlmZHsb7FptHF0OteGgXJbV1JQ4CNLUwVmvayHGB5mRwIkR7zfaBZBVVVREyBSccEW5pFnm/jRaKkwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:22:20.421380Z"},"content_sha256":"0035620960c84c43c0fef709dc81b7dd1702d84b35cb6c96d6c6a6733cf77fbb","schema_version":"1.0","event_id":"sha256:0035620960c84c43c0fef709dc81b7dd1702d84b35cb6c96d6c6a6733cf77fbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HAKITHMCCOTEOA6HSAP4M7JADG/bundle.json","state_url":"https://pith.science/pith/HAKITHMCCOTEOA6HSAP4M7JADG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HAKITHMCCOTEOA6HSAP4M7JADG/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":"2026-07-07T13:22:20Z","links":{"resolver":"https://pith.science/pith/HAKITHMCCOTEOA6HSAP4M7JADG","bundle":"https://pith.science/pith/HAKITHMCCOTEOA6HSAP4M7JADG/bundle.json","state":"https://pith.science/pith/HAKITHMCCOTEOA6HSAP4M7JADG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HAKITHMCCOTEOA6HSAP4M7JADG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HAKITHMCCOTEOA6HSAP4M7JADG","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":"6988c6b73aab244498bf338d082217dd192cfdf535350945c1bdbf127f30afdb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-13T06:06:23Z","title_canon_sha256":"7f5c5503df6e71846a0d00336e67527a91ccb3c038d0524b4194abef6d4da634"},"schema_version":"1.0","source":{"id":"2005.06166","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.06166","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2005.06166v1","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.06166","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"HAKITHMCCOTE","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"HAKITHMCCOTEOA6H","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"HAKITHMC","created_at":"2026-07-05T01:02:32Z"}],"graph_snapshots":[{"event_id":"sha256:0035620960c84c43c0fef709dc81b7dd1702d84b35cb6c96d6c6a6733cf77fbb","target":"graph","created_at":"2026-07-05T01:02:32Z","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/2005.06166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Web-crawled data provides a good source of parallel corpora for training machine translation models. It is automatically obtained, but extremely noisy, and recent work shows that neural machine translation systems are more sensitive to noise than traditional statistical machine translation methods. In this paper, we propose a novel approach to filter out noisy sentence pairs from web-crawled corpora via pre-trained language models. We measure sentence parallelism by leveraging the multilingual capability of BERT and use the Generative Pre-training (GPT) language model as a domain filter to bal","authors_text":"Ajay Nagesh, Boliang Zhang, Kevin Knight","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-13T06:06:23Z","title":"Parallel Corpus Filtering via Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.06166","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:f7d614fa3e0b67d3946f7d3414c518c1f62a95a4964667f7c39a6bc1b6bfba97","target":"record","created_at":"2026-07-05T01:02:32Z","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":"6988c6b73aab244498bf338d082217dd192cfdf535350945c1bdbf127f30afdb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-13T06:06:23Z","title_canon_sha256":"7f5c5503df6e71846a0d00336e67527a91ccb3c038d0524b4194abef6d4da634"},"schema_version":"1.0","source":{"id":"2005.06166","kind":"arxiv","version":1}},"canonical_sha256":"3814899d8213a64703c7901fc67d2019812e2dcc1af6963ac7b442ec4c079b31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3814899d8213a64703c7901fc67d2019812e2dcc1af6963ac7b442ec4c079b31","first_computed_at":"2026-07-05T01:02:32.712707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:02:32.712707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"53ZWXvL1Pxcx6VcN6c7MVGEwQltA9eJlE6pDs28lOlv8JWiiZZYamfG0I73fRcflWh8cHw5l6FZv2/WukwllDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:02:32.713271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.06166","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7d614fa3e0b67d3946f7d3414c518c1f62a95a4964667f7c39a6bc1b6bfba97","sha256:0035620960c84c43c0fef709dc81b7dd1702d84b35cb6c96d6c6a6733cf77fbb"],"state_sha256":"1b1cd01e8834b845fa1336bff7878b3c6358bb5d823e322e0df6b15de567799e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ycoOCy/lyF3NldqL0tnEdBmmsZNY5vrskRQEtDlbrPbiuPs9L6MzJ6pXH1bv2ZUeTnxSXQLvsqdqL+GYdwfLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:22:20.423605Z","bundle_sha256":"78be545f4341fae95e88c4eb4b293805481fb05af94be6c000757c9466e852fc"}}