{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MSP5ZRFP2TMJG5TAERJFRSBZQ5","short_pith_number":"pith:MSP5ZRFP","canonical_record":{"source":{"id":"2109.06262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T19:01:07Z","cross_cats_sorted":[],"title_canon_sha256":"b698064118d97e5599fd123208238da0d72f56d7269c5b8c4522f8e1256e768f","abstract_canon_sha256":"09fa768ad4b18f2b83d6ae06c5ed1fb49019483f39caac9318151afb374a1530"},"schema_version":"1.0"},"canonical_sha256":"649fdcc4afd4d8937660245258c8398755dfed7869ba9029e1cddcfb01fe78f1","source":{"kind":"arxiv","id":"2109.06262","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06262","created_at":"2026-07-05T03:13:52Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06262v1","created_at":"2026-07-05T03:13:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06262","created_at":"2026-07-05T03:13:52Z"},{"alias_kind":"pith_short_12","alias_value":"MSP5ZRFP2TMJ","created_at":"2026-07-05T03:13:52Z"},{"alias_kind":"pith_short_16","alias_value":"MSP5ZRFP2TMJG5TA","created_at":"2026-07-05T03:13:52Z"},{"alias_kind":"pith_short_8","alias_value":"MSP5ZRFP","created_at":"2026-07-05T03:13:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MSP5ZRFP2TMJG5TAERJFRSBZQ5","target":"record","payload":{"canonical_record":{"source":{"id":"2109.06262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T19:01:07Z","cross_cats_sorted":[],"title_canon_sha256":"b698064118d97e5599fd123208238da0d72f56d7269c5b8c4522f8e1256e768f","abstract_canon_sha256":"09fa768ad4b18f2b83d6ae06c5ed1fb49019483f39caac9318151afb374a1530"},"schema_version":"1.0"},"canonical_sha256":"649fdcc4afd4d8937660245258c8398755dfed7869ba9029e1cddcfb01fe78f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:52.377913Z","signature_b64":"hzm/WOJjd9NsU8NCteOWj8vCeE9u2TanmtFYBGz8lgLPjj2hwh6SENijqWRSz6NJu7P7HyexO5AA2X2t63ICBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"649fdcc4afd4d8937660245258c8398755dfed7869ba9029e1cddcfb01fe78f1","last_reissued_at":"2026-07-05T03:13:52.377381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:52.377381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.06262","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":"2026-07-05T03:13:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1mNso5OYKfA6/w8dJ0pIK3IRPUZzC8mGbRoT37Ng3qdZ8BjJOIE74NB/yCoy6WfVQrJrdK2YSM69ZWO/SCNHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:05:43.608444Z"},"content_sha256":"1efff2eded947dcdff369940ffa997cdebd2a920ad2e4b10a995a74ae95c7822","schema_version":"1.0","event_id":"sha256:1efff2eded947dcdff369940ffa997cdebd2a920ad2e4b10a995a74ae95c7822"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MSP5ZRFP2TMJG5TAERJFRSBZQ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Multiway Multilingual NMT in the Turkic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahsan Wahab, Aigiz Kunafin, Anoop Babu, Behzod Moydinboyev, Duygu Ataman, Francis Tyers, Jamshidbek Mirzakhalov, John Licato, Julia Kreutzer, Mokhiyakhon Uzokova, Orhan Firat, Sardana Ivanova, Shaxnoza Pulatova, Sriram Chellappan","submitted_at":"2021-09-13T19:01:07Z","abstract_excerpt":"Despite the increasing number of large and comprehensive machine translation (MT) systems, evaluation of these methods in various languages has been restrained by the lack of high-quality parallel corpora as well as engagement with the people that speak these languages. In this study, we present an evaluation of state-of-the-art approaches to training and evaluating MT systems in 22 languages from the Turkic language family, most of which being extremely under-explored. First, we adopt the TIL Corpus with a few key improvements to the training and the evaluation sets. Then, we train 26 bilingu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06262","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/2109.06262/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":"2026-07-05T03:13:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2tnfA7iKGRo1XfS+pU8th1RZEMDLNoHR3T5ebyovceYUpxeYQ9xd6/Rmzfe5nqpRJQC+5olTSiz6+MACiE6WBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:05:43.609356Z"},"content_sha256":"018e1912fc549de24ea594e025b71a89a6eb2b3f124d040f9a1904413da4acfc","schema_version":"1.0","event_id":"sha256:018e1912fc549de24ea594e025b71a89a6eb2b3f124d040f9a1904413da4acfc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/bundle.json","state_url":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/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":"2026-08-13T11:05:43Z","links":{"resolver":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5","bundle":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/bundle.json","state":"https://pith.science/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSP5ZRFP2TMJG5TAERJFRSBZQ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MSP5ZRFP2TMJG5TAERJFRSBZQ5","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":"09fa768ad4b18f2b83d6ae06c5ed1fb49019483f39caac9318151afb374a1530","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T19:01:07Z","title_canon_sha256":"b698064118d97e5599fd123208238da0d72f56d7269c5b8c4522f8e1256e768f"},"schema_version":"1.0","source":{"id":"2109.06262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06262","created_at":"2026-07-05T03:13:52Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06262v1","created_at":"2026-07-05T03:13:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06262","created_at":"2026-07-05T03:13:52Z"},{"alias_kind":"pith_short_12","alias_value":"MSP5ZRFP2TMJ","created_at":"2026-07-05T03:13:52Z"},{"alias_kind":"pith_short_16","alias_value":"MSP5ZRFP2TMJG5TA","created_at":"2026-07-05T03:13:52Z"},{"alias_kind":"pith_short_8","alias_value":"MSP5ZRFP","created_at":"2026-07-05T03:13:52Z"}],"graph_snapshots":[{"event_id":"sha256:018e1912fc549de24ea594e025b71a89a6eb2b3f124d040f9a1904413da4acfc","target":"graph","created_at":"2026-07-05T03:13:52Z","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/2109.06262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the increasing number of large and comprehensive machine translation (MT) systems, evaluation of these methods in various languages has been restrained by the lack of high-quality parallel corpora as well as engagement with the people that speak these languages. In this study, we present an evaluation of state-of-the-art approaches to training and evaluating MT systems in 22 languages from the Turkic language family, most of which being extremely under-explored. First, we adopt the TIL Corpus with a few key improvements to the training and the evaluation sets. Then, we train 26 bilingu","authors_text":"Ahsan Wahab, Aigiz Kunafin, Anoop Babu, Behzod Moydinboyev, Duygu Ataman, Francis Tyers, Jamshidbek Mirzakhalov, John Licato, Julia Kreutzer, Mokhiyakhon Uzokova, Orhan Firat, Sardana Ivanova, Shaxnoza Pulatova, Sriram Chellappan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T19:01:07Z","title":"Evaluating Multiway Multilingual NMT in the Turkic Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06262","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":"sha256:1efff2eded947dcdff369940ffa997cdebd2a920ad2e4b10a995a74ae95c7822","target":"record","created_at":"2026-07-05T03:13:52Z","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":"09fa768ad4b18f2b83d6ae06c5ed1fb49019483f39caac9318151afb374a1530","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T19:01:07Z","title_canon_sha256":"b698064118d97e5599fd123208238da0d72f56d7269c5b8c4522f8e1256e768f"},"schema_version":"1.0","source":{"id":"2109.06262","kind":"arxiv","version":1}},"canonical_sha256":"649fdcc4afd4d8937660245258c8398755dfed7869ba9029e1cddcfb01fe78f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"649fdcc4afd4d8937660245258c8398755dfed7869ba9029e1cddcfb01fe78f1","first_computed_at":"2026-07-05T03:13:52.377381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:52.377381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hzm/WOJjd9NsU8NCteOWj8vCeE9u2TanmtFYBGz8lgLPjj2hwh6SENijqWRSz6NJu7P7HyexO5AA2X2t63ICBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:52.377913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.06262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1efff2eded947dcdff369940ffa997cdebd2a920ad2e4b10a995a74ae95c7822","sha256:018e1912fc549de24ea594e025b71a89a6eb2b3f124d040f9a1904413da4acfc"],"state_sha256":"6053a1f757146749395b27b9a783c758f8750d70205af2341282a241c9abb3b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sZziKTfpbgucfQmWxbzSqOeA5LLEI2AOsV9MfQZibQ9LUEnH/PGF0nAGSlQVW8nCqoYfKY+YeECYW/dqEq8nAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T11:05:43.676600Z","bundle_sha256":"1004e2820e9abb0f6e6e20415878a1e0a9b192c709e7a2af2c226b43d0368b80"}}