{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2QMFJ7HIHRX2VYDJJ56MZBAOT2","short_pith_number":"pith:2QMFJ7HI","schema_version":"1.0","canonical_sha256":"d41854fce83c6faae0694f7ccc840e9eb8e6ddb6ad720fe7a77164b044757ced","source":{"kind":"arxiv","id":"1909.01522","version":2},"attestation_state":"computed","paper":{"title":"Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katharina Kann, Kyunghyun Cho, Samuel R. Bowman","submitted_at":"2019-09-04T02:20:54Z","abstract_excerpt":"Development sets are impractical to obtain for real low-resource languages, since using all available data for training is often more effective. However, development sets are widely used in research papers that purport to deal with low-resource natural language processing (NLP). Here, we aim to answer the following questions: Does using a development set for early stopping in the low-resource setting influence results as compared to a more realistic alternative, where the number of training epochs is tuned on development languages? And does it lead to overestimation or underestimation of perfo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1909.01522","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T02:20:54Z","cross_cats_sorted":[],"title_canon_sha256":"4fca33185e492eeabd6d340d76b500be48de988b1d80c14f5d088092d593bc55","abstract_canon_sha256":"8555a657371148bcf7abef39bbc35d1a74dc773c4cfb504a0f5ebfe216a66704"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:44.536090Z","signature_b64":"rTRZ14nCJaE6/QG5c9U3ru2bPeqzFVx0+/OeqHXn2lJg11KSShvunvFnQ6JYUjAQT7JbjqTa4YaXhJzl1FEUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d41854fce83c6faae0694f7ccc840e9eb8e6ddb6ad720fe7a77164b044757ced","last_reissued_at":"2026-07-05T00:04:44.535631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:44.535631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katharina Kann, Kyunghyun Cho, Samuel R. Bowman","submitted_at":"2019-09-04T02:20:54Z","abstract_excerpt":"Development sets are impractical to obtain for real low-resource languages, since using all available data for training is often more effective. However, development sets are widely used in research papers that purport to deal with low-resource natural language processing (NLP). Here, we aim to answer the following questions: Does using a development set for early stopping in the low-resource setting influence results as compared to a more realistic alternative, where the number of training epochs is tuned on development languages? And does it lead to overestimation or underestimation of perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01522","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/1909.01522/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1909.01522","created_at":"2026-07-05T00:04:44.535701+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.01522v2","created_at":"2026-07-05T00:04:44.535701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01522","created_at":"2026-07-05T00:04:44.535701+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QMFJ7HIHRX2","created_at":"2026-07-05T00:04:44.535701+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QMFJ7HIHRX2VYDJ","created_at":"2026-07-05T00:04:44.535701+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QMFJ7HI","created_at":"2026-07-05T00:04:44.535701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2","json":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2.json","graph_json":"https://pith.science/api/pith-number/2QMFJ7HIHRX2VYDJJ56MZBAOT2/graph.json","events_json":"https://pith.science/api/pith-number/2QMFJ7HIHRX2VYDJJ56MZBAOT2/events.json","paper":"https://pith.science/paper/2QMFJ7HI"},"agent_actions":{"view_html":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2","download_json":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2.json","view_paper":"https://pith.science/paper/2QMFJ7HI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.01522&json=true","fetch_graph":"https://pith.science/api/pith-number/2QMFJ7HIHRX2VYDJJ56MZBAOT2/graph.json","fetch_events":"https://pith.science/api/pith-number/2QMFJ7HIHRX2VYDJJ56MZBAOT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/action/storage_attestation","attest_author":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/action/author_attestation","sign_citation":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/action/citation_signature","submit_replication":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/action/replication_record"}},"created_at":"2026-07-05T00:04:44.535701+00:00","updated_at":"2026-07-05T00:04:44.535701+00:00"}