{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZAGSIEH54OUTRCSIHWNKOGFZG6","short_pith_number":"pith:ZAGSIEH5","canonical_record":{"source":{"id":"2207.14473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-29T04:29:43Z","cross_cats_sorted":[],"title_canon_sha256":"9dca2a4eb70b4a32cd90238c366313ba26d292a03a3a2073d0daa5d5b8b85ceb","abstract_canon_sha256":"f2a872af39dfcc338ff600e549a485db55f8bb38d01ac8adb8c64c6ec69e2f79"},"schema_version":"1.0"},"canonical_sha256":"c80d2410fde3a9388a483d9aa718b937b46496fd6653a4bde967b2269394cc97","source":{"kind":"arxiv","id":"2207.14473","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.14473","created_at":"2026-07-05T04:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"2207.14473v1","created_at":"2026-07-05T04:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.14473","created_at":"2026-07-05T04:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZAGSIEH54OUT","created_at":"2026-07-05T04:44:34Z"},{"alias_kind":"pith_short_16","alias_value":"ZAGSIEH54OUTRCSI","created_at":"2026-07-05T04:44:34Z"},{"alias_kind":"pith_short_8","alias_value":"ZAGSIEH5","created_at":"2026-07-05T04:44:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZAGSIEH54OUTRCSIHWNKOGFZG6","target":"record","payload":{"canonical_record":{"source":{"id":"2207.14473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-29T04:29:43Z","cross_cats_sorted":[],"title_canon_sha256":"9dca2a4eb70b4a32cd90238c366313ba26d292a03a3a2073d0daa5d5b8b85ceb","abstract_canon_sha256":"f2a872af39dfcc338ff600e549a485db55f8bb38d01ac8adb8c64c6ec69e2f79"},"schema_version":"1.0"},"canonical_sha256":"c80d2410fde3a9388a483d9aa718b937b46496fd6653a4bde967b2269394cc97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:34.744552Z","signature_b64":"/4+bszBopNNgFaSdvDoX0fDTFEb3Rbn4frpUBA3pdZscLFAVxfkTGGrFYqBXGAnHR6YvKtu3Bcqqjfd9Xd/ZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c80d2410fde3a9388a483d9aa718b937b46496fd6653a4bde967b2269394cc97","last_reissued_at":"2026-07-05T04:44:34.744146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:34.744146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.14473","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":"2026-07-05T04:44:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WdsK8yQb1ZbmSFeGqkSKICPgZu0VR8IK0ASVbCUV/LJLgtxIEJxhdEFSWC1yqSaYQHHI0t2HjWD9P3WN+PJNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T19:04:58.411055Z"},"content_sha256":"5fcafd7bdcfb04f38fc028fb96ccd53f7551187cf11116cda0b5bf35d5c85994","schema_version":"1.0","event_id":"sha256:5fcafd7bdcfb04f38fc028fb96ccd53f7551187cf11116cda0b5bf35d5c85994"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZAGSIEH54OUTRCSIHWNKOGFZG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Azerbaijani Neural Machine Translation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chih-Chen Chen, William Chen","submitted_at":"2022-07-29T04:29:43Z","abstract_excerpt":"Little research has been done on Neural Machine Translation (NMT) for Azerbaijani. In this paper, we benchmark the performance of Azerbaijani-English NMT systems on a range of techniques and datasets. We evaluate which segmentation techniques work best on Azerbaijani translation and benchmark the performance of Azerbaijani NMT models across several domains of text. Our results show that while Unigram segmentation improves NMT performance and Azerbaijani translation models scale better with dataset quality than quantity, cross-domain generalization remains a challenge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.14473","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/2207.14473/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":"2026-07-05T04:44:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TWslrf7Ae3qMCdGXdn+R4XqeGR7HNTOPLBB6CNhM+Z8Py6VV2BtjRdAaBKKUC1/0Y9Yu8xTPNzpCDuJZuUZoCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T19:04:58.411908Z"},"content_sha256":"b115f415ae1ed9ce4e05f2b36113ff97ecfcac62314be9673ec0018c1bff6e99","schema_version":"1.0","event_id":"sha256:b115f415ae1ed9ce4e05f2b36113ff97ecfcac62314be9673ec0018c1bff6e99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZAGSIEH54OUTRCSIHWNKOGFZG6/bundle.json","state_url":"https://pith.science/pith/ZAGSIEH54OUTRCSIHWNKOGFZG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZAGSIEH54OUTRCSIHWNKOGFZG6/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":"2026-07-13T19:04:58Z","links":{"resolver":"https://pith.science/pith/ZAGSIEH54OUTRCSIHWNKOGFZG6","bundle":"https://pith.science/pith/ZAGSIEH54OUTRCSIHWNKOGFZG6/bundle.json","state":"https://pith.science/pith/ZAGSIEH54OUTRCSIHWNKOGFZG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZAGSIEH54OUTRCSIHWNKOGFZG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZAGSIEH54OUTRCSIHWNKOGFZG6","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":"f2a872af39dfcc338ff600e549a485db55f8bb38d01ac8adb8c64c6ec69e2f79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-29T04:29:43Z","title_canon_sha256":"9dca2a4eb70b4a32cd90238c366313ba26d292a03a3a2073d0daa5d5b8b85ceb"},"schema_version":"1.0","source":{"id":"2207.14473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.14473","created_at":"2026-07-05T04:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"2207.14473v1","created_at":"2026-07-05T04:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.14473","created_at":"2026-07-05T04:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZAGSIEH54OUT","created_at":"2026-07-05T04:44:34Z"},{"alias_kind":"pith_short_16","alias_value":"ZAGSIEH54OUTRCSI","created_at":"2026-07-05T04:44:34Z"},{"alias_kind":"pith_short_8","alias_value":"ZAGSIEH5","created_at":"2026-07-05T04:44:34Z"}],"graph_snapshots":[{"event_id":"sha256:b115f415ae1ed9ce4e05f2b36113ff97ecfcac62314be9673ec0018c1bff6e99","target":"graph","created_at":"2026-07-05T04:44:34Z","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/2207.14473/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Little research has been done on Neural Machine Translation (NMT) for Azerbaijani. In this paper, we benchmark the performance of Azerbaijani-English NMT systems on a range of techniques and datasets. We evaluate which segmentation techniques work best on Azerbaijani translation and benchmark the performance of Azerbaijani NMT models across several domains of text. Our results show that while Unigram segmentation improves NMT performance and Azerbaijani translation models scale better with dataset quality than quantity, cross-domain generalization remains a challenge","authors_text":"Chih-Chen Chen, William Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-29T04:29:43Z","title":"Benchmarking Azerbaijani Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.14473","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":"sha256:5fcafd7bdcfb04f38fc028fb96ccd53f7551187cf11116cda0b5bf35d5c85994","target":"record","created_at":"2026-07-05T04:44:34Z","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":"f2a872af39dfcc338ff600e549a485db55f8bb38d01ac8adb8c64c6ec69e2f79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-29T04:29:43Z","title_canon_sha256":"9dca2a4eb70b4a32cd90238c366313ba26d292a03a3a2073d0daa5d5b8b85ceb"},"schema_version":"1.0","source":{"id":"2207.14473","kind":"arxiv","version":1}},"canonical_sha256":"c80d2410fde3a9388a483d9aa718b937b46496fd6653a4bde967b2269394cc97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c80d2410fde3a9388a483d9aa718b937b46496fd6653a4bde967b2269394cc97","first_computed_at":"2026-07-05T04:44:34.744146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:44:34.744146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/4+bszBopNNgFaSdvDoX0fDTFEb3Rbn4frpUBA3pdZscLFAVxfkTGGrFYqBXGAnHR6YvKtu3Bcqqjfd9Xd/ZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:44:34.744552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.14473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fcafd7bdcfb04f38fc028fb96ccd53f7551187cf11116cda0b5bf35d5c85994","sha256:b115f415ae1ed9ce4e05f2b36113ff97ecfcac62314be9673ec0018c1bff6e99"],"state_sha256":"e127ff990333e9fd0deb5c78c01d37d8ad3e25b67c5efd108ffae7f0b8414fda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PXBlG0zdMVdC4m3Zb5CHXEdd+X0PBGU11k8ALVSGdZSkadbrVeqYhCMbey3zIIs8jjOXvj7oVMmIKNmpbLTlDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T19:04:58.416044Z","bundle_sha256":"1676583a5e6881d1278cfae7650c0d94b125ce09bc914e6d33f5704e1eed713b"}}