{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6VBIUW6ODMZIAY5UJ3TQ2XG2HI","short_pith_number":"pith:6VBIUW6O","canonical_record":{"source":{"id":"2105.15071","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-31T16:01:18Z","cross_cats_sorted":[],"title_canon_sha256":"e0592c40d9628c5d22c413fb88e2d2aed013feecf55bf25cfb74cd325bd024c4","abstract_canon_sha256":"30c55e6d5fdc53b00ecae0b3d1db85d941f25ea4e1ee6ab5c9c30f54c2eed014"},"schema_version":"1.0"},"canonical_sha256":"f5428a5bce1b328063b44ee70d5cda3a292aa7235153018b7968f94996b77e11","source":{"kind":"arxiv","id":"2105.15071","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.15071","created_at":"2026-07-05T02:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2105.15071v2","created_at":"2026-07-05T02:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.15071","created_at":"2026-07-05T02:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"6VBIUW6ODMZI","created_at":"2026-07-05T02:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"6VBIUW6ODMZIAY5U","created_at":"2026-07-05T02:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"6VBIUW6O","created_at":"2026-07-05T02:45:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6VBIUW6ODMZIAY5UJ3TQ2XG2HI","target":"record","payload":{"canonical_record":{"source":{"id":"2105.15071","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-31T16:01:18Z","cross_cats_sorted":[],"title_canon_sha256":"e0592c40d9628c5d22c413fb88e2d2aed013feecf55bf25cfb74cd325bd024c4","abstract_canon_sha256":"30c55e6d5fdc53b00ecae0b3d1db85d941f25ea4e1ee6ab5c9c30f54c2eed014"},"schema_version":"1.0"},"canonical_sha256":"f5428a5bce1b328063b44ee70d5cda3a292aa7235153018b7968f94996b77e11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:38.855764Z","signature_b64":"kH+xNNZA6THAQxKtprLSgkp/U+p5aSGPNhD5L2lihwDN/NFbKYxXDvVBsxuf68uPUodSMiCq92Tmro6+NjymBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5428a5bce1b328063b44ee70d5cda3a292aa7235153018b7968f94996b77e11","last_reissued_at":"2026-07-05T02:45:38.855247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:38.855247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.15071","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OFBQRDM6G2+SM38TwhVzS/ydK/cryEiwYCTamvDvevfJs7FMdYcsRwUoJBUAlaYfhXY728UJGpMkWWan71ILCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:31:06.272769Z"},"content_sha256":"81ddb3aa5f4fc0a45e48aae8c89dab303ba67e8ee4a560ba4d957834e57cdc2c","schema_version":"1.0","event_id":"sha256:81ddb3aa5f4fc0a45e48aae8c89dab303ba67e8ee4a560ba4d957834e57cdc2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6VBIUW6ODMZIAY5UJ3TQ2XG2HI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adithya Renduchintala, Ahmed El-Kishky, Francisco Guzm\\'an, Mona Diab, Naman Goyal, Pascale Fung, Philipp Koehn, Vishrav Chaudhary, Wei-Jen Ko","submitted_at":"2021-05-31T16:01:18Z","abstract_excerpt":"The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are linguistically related or similar to high-resource languages; these related languages may share many lexical or syntactic structures. In this work, we exploit this linguistic overlap to facilitate translating to and from a low-resource language with only monolingual data, in addition to any parallel data in the related high-resource language. Our method, NMT-Adapt, combines denoising autoencoding, back-translation and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.15071","kind":"arxiv","version":2},"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/2105.15071/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":"2026-07-05T02:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8qH8ndgWNQQQxrIPa9tCTxdZ7FhNHY0U7ikcJhBbxuhqen9uKICiUn48VW+sjo7oPFQTUxO5kc4BuM6wMsF1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:31:06.273269Z"},"content_sha256":"1d4f7c05cfcf288311d780098b3b13a11d67b17716ca44147fac6ffa5e8e4b3f","schema_version":"1.0","event_id":"sha256:1d4f7c05cfcf288311d780098b3b13a11d67b17716ca44147fac6ffa5e8e4b3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6VBIUW6ODMZIAY5UJ3TQ2XG2HI/bundle.json","state_url":"https://pith.science/pith/6VBIUW6ODMZIAY5UJ3TQ2XG2HI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6VBIUW6ODMZIAY5UJ3TQ2XG2HI/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":"2026-08-23T12:31:06Z","links":{"resolver":"https://pith.science/pith/6VBIUW6ODMZIAY5UJ3TQ2XG2HI","bundle":"https://pith.science/pith/6VBIUW6ODMZIAY5UJ3TQ2XG2HI/bundle.json","state":"https://pith.science/pith/6VBIUW6ODMZIAY5UJ3TQ2XG2HI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6VBIUW6ODMZIAY5UJ3TQ2XG2HI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6VBIUW6ODMZIAY5UJ3TQ2XG2HI","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":"30c55e6d5fdc53b00ecae0b3d1db85d941f25ea4e1ee6ab5c9c30f54c2eed014","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-31T16:01:18Z","title_canon_sha256":"e0592c40d9628c5d22c413fb88e2d2aed013feecf55bf25cfb74cd325bd024c4"},"schema_version":"1.0","source":{"id":"2105.15071","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.15071","created_at":"2026-07-05T02:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2105.15071v2","created_at":"2026-07-05T02:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.15071","created_at":"2026-07-05T02:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"6VBIUW6ODMZI","created_at":"2026-07-05T02:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"6VBIUW6ODMZIAY5U","created_at":"2026-07-05T02:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"6VBIUW6O","created_at":"2026-07-05T02:45:38Z"}],"graph_snapshots":[{"event_id":"sha256:1d4f7c05cfcf288311d780098b3b13a11d67b17716ca44147fac6ffa5e8e4b3f","target":"graph","created_at":"2026-07-05T02:45:38Z","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/2105.15071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are linguistically related or similar to high-resource languages; these related languages may share many lexical or syntactic structures. In this work, we exploit this linguistic overlap to facilitate translating to and from a low-resource language with only monolingual data, in addition to any parallel data in the related high-resource language. Our method, NMT-Adapt, combines denoising autoencoding, back-translation and a","authors_text":"Adithya Renduchintala, Ahmed El-Kishky, Francisco Guzm\\'an, Mona Diab, Naman Goyal, Pascale Fung, Philipp Koehn, Vishrav Chaudhary, Wei-Jen Ko","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-31T16:01:18Z","title":"Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.15071","kind":"arxiv","version":2},"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":"sha256:81ddb3aa5f4fc0a45e48aae8c89dab303ba67e8ee4a560ba4d957834e57cdc2c","target":"record","created_at":"2026-07-05T02:45:38Z","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":"30c55e6d5fdc53b00ecae0b3d1db85d941f25ea4e1ee6ab5c9c30f54c2eed014","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-31T16:01:18Z","title_canon_sha256":"e0592c40d9628c5d22c413fb88e2d2aed013feecf55bf25cfb74cd325bd024c4"},"schema_version":"1.0","source":{"id":"2105.15071","kind":"arxiv","version":2}},"canonical_sha256":"f5428a5bce1b328063b44ee70d5cda3a292aa7235153018b7968f94996b77e11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5428a5bce1b328063b44ee70d5cda3a292aa7235153018b7968f94996b77e11","first_computed_at":"2026-07-05T02:45:38.855247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:38.855247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kH+xNNZA6THAQxKtprLSgkp/U+p5aSGPNhD5L2lihwDN/NFbKYxXDvVBsxuf68uPUodSMiCq92Tmro6+NjymBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:38.855764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.15071","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81ddb3aa5f4fc0a45e48aae8c89dab303ba67e8ee4a560ba4d957834e57cdc2c","sha256:1d4f7c05cfcf288311d780098b3b13a11d67b17716ca44147fac6ffa5e8e4b3f"],"state_sha256":"9cfa1ba4ed38ea4e07e298bab6f4ce44cf67a23d343738ad1bf77fb21ffad931"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ja5HphuUBJMoB7ABcCYmkJn1AMVMWgkV2+tbfKwCb9FgLIxzIaq7qlvIZwCWIR8Ej/b0GrwU1bvR4ldFQWhdAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T12:31:06.278679Z","bundle_sha256":"60b6549a60a78bc157679c6281e682d73e39c2e5a872caf2d57c42c451b26d36"}}