{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MOR365S2LMLXWSYYMQEF4QAYDZ","short_pith_number":"pith:MOR365S2","canonical_record":{"source":{"id":"2311.14838","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-24T20:24:00Z","cross_cats_sorted":[],"title_canon_sha256":"7ec557754660c4109f41af9bfdd8df84d15aa00bbcc9dcbd6b33e9a30cb881d2","abstract_canon_sha256":"003af91364195c790afc052bee7f4f97fc3d28784c15d57d9e77fbf7dda9dd82"},"schema_version":"1.0"},"canonical_sha256":"63a3bf765a5b177b4b1864085e40181e58e25b3a18e94595af8f62046a4eb044","source":{"kind":"arxiv","id":"2311.14838","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14838","created_at":"2026-07-05T07:16:53Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14838v1","created_at":"2026-07-05T07:16:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14838","created_at":"2026-07-05T07:16:53Z"},{"alias_kind":"pith_short_12","alias_value":"MOR365S2LMLX","created_at":"2026-07-05T07:16:53Z"},{"alias_kind":"pith_short_16","alias_value":"MOR365S2LMLXWSYY","created_at":"2026-07-05T07:16:53Z"},{"alias_kind":"pith_short_8","alias_value":"MOR365S2","created_at":"2026-07-05T07:16:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MOR365S2LMLXWSYYMQEF4QAYDZ","target":"record","payload":{"canonical_record":{"source":{"id":"2311.14838","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-24T20:24:00Z","cross_cats_sorted":[],"title_canon_sha256":"7ec557754660c4109f41af9bfdd8df84d15aa00bbcc9dcbd6b33e9a30cb881d2","abstract_canon_sha256":"003af91364195c790afc052bee7f4f97fc3d28784c15d57d9e77fbf7dda9dd82"},"schema_version":"1.0"},"canonical_sha256":"63a3bf765a5b177b4b1864085e40181e58e25b3a18e94595af8f62046a4eb044","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:53.449710Z","signature_b64":"Ni/kFGnUZgs5VP9ug/6mBRiT1nruRwQ60sDaA134q5bHbjLspanlYUKvvXCeQbsI5odhnX77TEaEKp4KkcY5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63a3bf765a5b177b4b1864085e40181e58e25b3a18e94595af8f62046a4eb044","last_reissued_at":"2026-07-05T07:16:53.449293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:53.449293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.14838","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":"2026-07-05T07:16:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MoyI6bTbvsXAjExWJfVw+h/J48mUSoZGQq0JMFwXsVchdJ+jixYcEEgvp/07ploMOcHoaTwgAkScvtE0aHUfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:55:10.590460Z"},"content_sha256":"3d99b496ec6c0d88096111ef3a7ac39a7ccedfaf10941fe2996ddf74328ba007","schema_version":"1.0","event_id":"sha256:3d99b496ec6c0d88096111ef3a7ac39a7ccedfaf10941fe2996ddf74328ba007"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MOR365S2LMLXWSYYMQEF4QAYDZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OpusCleaner and OpusTrainer, open source toolkits for training Machine Translation and Large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barry Haddow, Gema Ram\\'irez-S\\'anchez, Graeme Nail, Jaume Zaragoza-Bernabeu, Jelmer van der Linde, Jind\\v{r}ich Helcl, Lukas Weymann, Mikko Aulamo, Nikolay Bogoychev, Tudor Nicolae Mateiu","submitted_at":"2023-11-24T20:24:00Z","abstract_excerpt":"Developing high quality machine translation systems is a labour intensive, challenging and confusing process for newcomers to the field. We present a pair of tools OpusCleaner and OpusTrainer that aim to simplify the process, reduce the amount of work and lower the entry barrier for newcomers.\n  OpusCleaner is a data downloading, cleaning, and proprocessing toolkit. It is designed to allow researchers to quickly download, visualise and preprocess bilingual (or monolingual) data that comes from many different sources, each of them with different quality, issues, and unique filtering/preprocessi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14838","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/2311.14838/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":"2026-07-05T07:16:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PG6hZbrre+qrNv7ei6QwCiD0HNlgzifCUjdVxCjeNx87Jw3vuFr3YZh7JdBVpzaBoYYsTyANLouyhTXBbkJ3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:55:10.590822Z"},"content_sha256":"a5674b821794eb196d3c75aa5970d4fcf5862adc036326a6337d7302fd972097","schema_version":"1.0","event_id":"sha256:a5674b821794eb196d3c75aa5970d4fcf5862adc036326a6337d7302fd972097"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MOR365S2LMLXWSYYMQEF4QAYDZ/bundle.json","state_url":"https://pith.science/pith/MOR365S2LMLXWSYYMQEF4QAYDZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MOR365S2LMLXWSYYMQEF4QAYDZ/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":"2026-07-07T08:55:10Z","links":{"resolver":"https://pith.science/pith/MOR365S2LMLXWSYYMQEF4QAYDZ","bundle":"https://pith.science/pith/MOR365S2LMLXWSYYMQEF4QAYDZ/bundle.json","state":"https://pith.science/pith/MOR365S2LMLXWSYYMQEF4QAYDZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MOR365S2LMLXWSYYMQEF4QAYDZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MOR365S2LMLXWSYYMQEF4QAYDZ","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":"003af91364195c790afc052bee7f4f97fc3d28784c15d57d9e77fbf7dda9dd82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-24T20:24:00Z","title_canon_sha256":"7ec557754660c4109f41af9bfdd8df84d15aa00bbcc9dcbd6b33e9a30cb881d2"},"schema_version":"1.0","source":{"id":"2311.14838","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14838","created_at":"2026-07-05T07:16:53Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14838v1","created_at":"2026-07-05T07:16:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14838","created_at":"2026-07-05T07:16:53Z"},{"alias_kind":"pith_short_12","alias_value":"MOR365S2LMLX","created_at":"2026-07-05T07:16:53Z"},{"alias_kind":"pith_short_16","alias_value":"MOR365S2LMLXWSYY","created_at":"2026-07-05T07:16:53Z"},{"alias_kind":"pith_short_8","alias_value":"MOR365S2","created_at":"2026-07-05T07:16:53Z"}],"graph_snapshots":[{"event_id":"sha256:a5674b821794eb196d3c75aa5970d4fcf5862adc036326a6337d7302fd972097","target":"graph","created_at":"2026-07-05T07:16:53Z","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/2311.14838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing high quality machine translation systems is a labour intensive, challenging and confusing process for newcomers to the field. We present a pair of tools OpusCleaner and OpusTrainer that aim to simplify the process, reduce the amount of work and lower the entry barrier for newcomers.\n  OpusCleaner is a data downloading, cleaning, and proprocessing toolkit. It is designed to allow researchers to quickly download, visualise and preprocess bilingual (or monolingual) data that comes from many different sources, each of them with different quality, issues, and unique filtering/preprocessi","authors_text":"Barry Haddow, Gema Ram\\'irez-S\\'anchez, Graeme Nail, Jaume Zaragoza-Bernabeu, Jelmer van der Linde, Jind\\v{r}ich Helcl, Lukas Weymann, Mikko Aulamo, Nikolay Bogoychev, Tudor Nicolae Mateiu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-24T20:24:00Z","title":"OpusCleaner and OpusTrainer, open source toolkits for training Machine Translation and Large language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14838","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":"sha256:3d99b496ec6c0d88096111ef3a7ac39a7ccedfaf10941fe2996ddf74328ba007","target":"record","created_at":"2026-07-05T07:16:53Z","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":"003af91364195c790afc052bee7f4f97fc3d28784c15d57d9e77fbf7dda9dd82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-24T20:24:00Z","title_canon_sha256":"7ec557754660c4109f41af9bfdd8df84d15aa00bbcc9dcbd6b33e9a30cb881d2"},"schema_version":"1.0","source":{"id":"2311.14838","kind":"arxiv","version":1}},"canonical_sha256":"63a3bf765a5b177b4b1864085e40181e58e25b3a18e94595af8f62046a4eb044","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63a3bf765a5b177b4b1864085e40181e58e25b3a18e94595af8f62046a4eb044","first_computed_at":"2026-07-05T07:16:53.449293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:53.449293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ni/kFGnUZgs5VP9ug/6mBRiT1nruRwQ60sDaA134q5bHbjLspanlYUKvvXCeQbsI5odhnX77TEaEKp4KkcY5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:53.449710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.14838","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d99b496ec6c0d88096111ef3a7ac39a7ccedfaf10941fe2996ddf74328ba007","sha256:a5674b821794eb196d3c75aa5970d4fcf5862adc036326a6337d7302fd972097"],"state_sha256":"a2709b912ae8424bfd12feafac2c4a0ab89b98c95269aea9dfbc4cb820c59d48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GsgmNiHO8s1hKvgC0Q7idRsGo7EfDaX3EEEa+inralpW60smaJga0+WRFXHIzsgPN3jO3Gwgk/edATb84KCkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:55:10.593187Z","bundle_sha256":"637cee2de54298db726bafdc25bcf76c0280b13dae1f88a98f089e1d267d855f"}}