{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:R5DKYX264OPW7N6ZE7YSLDOVPJ","short_pith_number":"pith:R5DKYX26","canonical_record":{"source":{"id":"2206.00564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-01T15:21:16Z","cross_cats_sorted":[],"title_canon_sha256":"0c25dde7aa54d0e02c68fc474646f4fafb625200c61c7cac23447a9506ca0978","abstract_canon_sha256":"0da221c23627c1724311825a9a41a437beb3fcb207b17e9cb2dd24f9d9b493ae"},"schema_version":"1.0"},"canonical_sha256":"8f46ac5f5ee39f6fb7d927f1258dd57a6c86b0647dccdc56a5c8cd2ff382149a","source":{"kind":"arxiv","id":"2206.00564","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00564","created_at":"2026-07-05T06:46:20Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00564v1","created_at":"2026-07-05T06:46:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00564","created_at":"2026-07-05T06:46:20Z"},{"alias_kind":"pith_short_12","alias_value":"R5DKYX264OPW","created_at":"2026-07-05T06:46:20Z"},{"alias_kind":"pith_short_16","alias_value":"R5DKYX264OPW7N6Z","created_at":"2026-07-05T06:46:20Z"},{"alias_kind":"pith_short_8","alias_value":"R5DKYX26","created_at":"2026-07-05T06:46:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:R5DKYX264OPW7N6ZE7YSLDOVPJ","target":"record","payload":{"canonical_record":{"source":{"id":"2206.00564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-01T15:21:16Z","cross_cats_sorted":[],"title_canon_sha256":"0c25dde7aa54d0e02c68fc474646f4fafb625200c61c7cac23447a9506ca0978","abstract_canon_sha256":"0da221c23627c1724311825a9a41a437beb3fcb207b17e9cb2dd24f9d9b493ae"},"schema_version":"1.0"},"canonical_sha256":"8f46ac5f5ee39f6fb7d927f1258dd57a6c86b0647dccdc56a5c8cd2ff382149a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:20.327229Z","signature_b64":"GxVCXA3BLO3IXsFoWAbgK+RHnnaw76MM0cgLaSdWv7UQdO7vCQxSAI8neFOlFePDXSjtx7c9qLkawytR9zz9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f46ac5f5ee39f6fb7d927f1258dd57a6c86b0647dccdc56a5c8cd2ff382149a","last_reissued_at":"2026-07-05T06:46:20.326699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:20.326699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.00564","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":"2026-07-05T06:46:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LLOFYFOqSDxJLjfHeFkUi9yaDSb1/c5Y8bxzb6+djH6KE1b53y+G7ChNtYyM/vs0dAwKWPJa/3ThylBhqHulCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:16:43.111835Z"},"content_sha256":"1b6c9be01ca39ead9e3177c60d758a52ed0c6c4e9bc8a6a7f66aea79fb72d990","schema_version":"1.0","event_id":"sha256:1b6c9be01ca39ead9e3177c60d758a52ed0c6c4e9bc8a6a7f66aea79fb72d990"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:R5DKYX264OPW7N6ZE7YSLDOVPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Diversity in Back Translation for Low-Resource Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Birch, Kenneth Heafield, Laurie Burchell","submitted_at":"2022-06-01T15:21:16Z","abstract_excerpt":"Back translation is one of the most widely used methods for improving the performance of neural machine translation systems. Recent research has sought to enhance the effectiveness of this method by increasing the 'diversity' of the generated translations. We argue that the definitions and metrics used to quantify 'diversity' in previous work have been insufficient. This work puts forward a more nuanced framework for understanding diversity in training data, splitting it into lexical diversity and syntactic diversity. We present novel metrics for measuring these different aspects of diversity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00564","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/2206.00564/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":"2026-07-05T06:46:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUV/uUnpX765dP2+HQIwMDdSBdeMz1GgRyaIGq8nB3g1zRUNFwapV5UpuMK6O7hflpLFvtGcZDq+wF8XGVytDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:16:43.112215Z"},"content_sha256":"92d8aeac2cce28e16f79726236af918da065c5d6153cffd06ac2fa75ee039767","schema_version":"1.0","event_id":"sha256:92d8aeac2cce28e16f79726236af918da065c5d6153cffd06ac2fa75ee039767"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5DKYX264OPW7N6ZE7YSLDOVPJ/bundle.json","state_url":"https://pith.science/pith/R5DKYX264OPW7N6ZE7YSLDOVPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5DKYX264OPW7N6ZE7YSLDOVPJ/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":"2026-08-01T07:16:43Z","links":{"resolver":"https://pith.science/pith/R5DKYX264OPW7N6ZE7YSLDOVPJ","bundle":"https://pith.science/pith/R5DKYX264OPW7N6ZE7YSLDOVPJ/bundle.json","state":"https://pith.science/pith/R5DKYX264OPW7N6ZE7YSLDOVPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5DKYX264OPW7N6ZE7YSLDOVPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:R5DKYX264OPW7N6ZE7YSLDOVPJ","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":"0da221c23627c1724311825a9a41a437beb3fcb207b17e9cb2dd24f9d9b493ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-01T15:21:16Z","title_canon_sha256":"0c25dde7aa54d0e02c68fc474646f4fafb625200c61c7cac23447a9506ca0978"},"schema_version":"1.0","source":{"id":"2206.00564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00564","created_at":"2026-07-05T06:46:20Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00564v1","created_at":"2026-07-05T06:46:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00564","created_at":"2026-07-05T06:46:20Z"},{"alias_kind":"pith_short_12","alias_value":"R5DKYX264OPW","created_at":"2026-07-05T06:46:20Z"},{"alias_kind":"pith_short_16","alias_value":"R5DKYX264OPW7N6Z","created_at":"2026-07-05T06:46:20Z"},{"alias_kind":"pith_short_8","alias_value":"R5DKYX26","created_at":"2026-07-05T06:46:20Z"}],"graph_snapshots":[{"event_id":"sha256:92d8aeac2cce28e16f79726236af918da065c5d6153cffd06ac2fa75ee039767","target":"graph","created_at":"2026-07-05T06:46:20Z","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/2206.00564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Back translation is one of the most widely used methods for improving the performance of neural machine translation systems. Recent research has sought to enhance the effectiveness of this method by increasing the 'diversity' of the generated translations. We argue that the definitions and metrics used to quantify 'diversity' in previous work have been insufficient. This work puts forward a more nuanced framework for understanding diversity in training data, splitting it into lexical diversity and syntactic diversity. We present novel metrics for measuring these different aspects of diversity ","authors_text":"Alexandra Birch, Kenneth Heafield, Laurie Burchell","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-01T15:21:16Z","title":"Exploring Diversity in Back Translation for Low-Resource Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00564","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":"sha256:1b6c9be01ca39ead9e3177c60d758a52ed0c6c4e9bc8a6a7f66aea79fb72d990","target":"record","created_at":"2026-07-05T06:46:20Z","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":"0da221c23627c1724311825a9a41a437beb3fcb207b17e9cb2dd24f9d9b493ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-01T15:21:16Z","title_canon_sha256":"0c25dde7aa54d0e02c68fc474646f4fafb625200c61c7cac23447a9506ca0978"},"schema_version":"1.0","source":{"id":"2206.00564","kind":"arxiv","version":1}},"canonical_sha256":"8f46ac5f5ee39f6fb7d927f1258dd57a6c86b0647dccdc56a5c8cd2ff382149a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f46ac5f5ee39f6fb7d927f1258dd57a6c86b0647dccdc56a5c8cd2ff382149a","first_computed_at":"2026-07-05T06:46:20.326699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:20.326699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GxVCXA3BLO3IXsFoWAbgK+RHnnaw76MM0cgLaSdWv7UQdO7vCQxSAI8neFOlFePDXSjtx7c9qLkawytR9zz9DA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:20.327229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b6c9be01ca39ead9e3177c60d758a52ed0c6c4e9bc8a6a7f66aea79fb72d990","sha256:92d8aeac2cce28e16f79726236af918da065c5d6153cffd06ac2fa75ee039767"],"state_sha256":"f9e921e20bc43e46a02ef4bff0c64eb24bc6248b9665308a42e78a11ccad995e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4mrEM6Wc11pKOz0rL/1ga/1Zm3cTf5/Mc+4gFqDbQzLUxtRIdXBlVqg7RyFw3co5YOP6Oov6qDEFJD2SPXH8Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:16:43.115026Z","bundle_sha256":"d38c5d700d04d880a8b1c2ff364880d9aec159189fb325d6a3e73582bcdfa287"}}