{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V4JYP6P3ZLOEMVVMYJD2MRAO2G","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":"b3f1fcde3a0b31facd163f53ba19c9fcab181c47ab2ad08e8d0535659a20e6a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T17:04:38Z","title_canon_sha256":"2212b3ae0ace66b3d2c8caaf19e975f39939ca57c8191dac69b1b2fbd71e990a"},"schema_version":"1.0","source":{"id":"2211.07534","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.07534","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"arxiv_version","alias_value":"2211.07534v1","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07534","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"pith_short_12","alias_value":"V4JYP6P3ZLOE","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"pith_short_16","alias_value":"V4JYP6P3ZLOEMVVM","created_at":"2026-07-05T05:15:54Z"},{"alias_kind":"pith_short_8","alias_value":"V4JYP6P3","created_at":"2026-07-05T05:15:54Z"}],"graph_snapshots":[{"event_id":"sha256:0f49bfb0b8e18256fc53bb27c8b21ffbe3f51ff3016a628e652b6d78e49882c0","target":"graph","created_at":"2026-07-05T05:15:54Z","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/2211.07534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The central bottleneck for low-resource NLP is typically regarded to be the quantity of accessible data, overlooking the contribution of data quality. This is particularly seen in the development and evaluation of low-resource systems via down sampling of high-resource language data. In this work we investigate the validity of this approach, and we specifically focus on two well-known NLP tasks for our empirical investigations: POS-tagging and machine translation. We show that down sampling from a high-resource language results in datasets with different properties than the low-resource datase","authors_text":"David Grangier, Maartje ter Hoeve, Natalie Schluter","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T17:04:38Z","title":"High-Resource Methodological Bias in Low-Resource Investigations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07534","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:ace572afccd747a93073ff010797f0618a8ca331909fda475675f7fb1da525b1","target":"record","created_at":"2026-07-05T05:15:54Z","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":"b3f1fcde3a0b31facd163f53ba19c9fcab181c47ab2ad08e8d0535659a20e6a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T17:04:38Z","title_canon_sha256":"2212b3ae0ace66b3d2c8caaf19e975f39939ca57c8191dac69b1b2fbd71e990a"},"schema_version":"1.0","source":{"id":"2211.07534","kind":"arxiv","version":1}},"canonical_sha256":"af1387f9fbcadc4656acc247a6440ed1ab50ab150561a16c09b6133aaf7aa3b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af1387f9fbcadc4656acc247a6440ed1ab50ab150561a16c09b6133aaf7aa3b0","first_computed_at":"2026-07-05T05:15:54.731602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:54.731602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C/bwPuPmjcRI+lZjh6zSh3ez2yGVhuyk/YV/DPPQcME2/zkTribjsZp7YZjOBr8fcYtO2kxGhEmAFJ77y3/tAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:54.732425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.07534","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ace572afccd747a93073ff010797f0618a8ca331909fda475675f7fb1da525b1","sha256:0f49bfb0b8e18256fc53bb27c8b21ffbe3f51ff3016a628e652b6d78e49882c0"],"state_sha256":"10e8f86b1b980c16701a66d522a628857ab18dbb741d1d0364dc5ae59e2b6a0f"}