{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2QMFJ7HIHRX2VYDJJ56MZBAOT2","short_pith_number":"pith:2QMFJ7HI","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"},"canonical_sha256":"d41854fce83c6faae0694f7ccc840e9eb8e6ddb6ad720fe7a77164b044757ced","source":{"kind":"arxiv","id":"1909.01522","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01522","created_at":"2026-07-05T00:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01522v2","created_at":"2026-07-05T00:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01522","created_at":"2026-07-05T00:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"2QMFJ7HIHRX2","created_at":"2026-07-05T00:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"2QMFJ7HIHRX2VYDJ","created_at":"2026-07-05T00:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"2QMFJ7HI","created_at":"2026-07-05T00:04:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2QMFJ7HIHRX2VYDJJ56MZBAOT2","target":"record","payload":{"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"},"canonical_sha256":"d41854fce83c6faae0694f7ccc840e9eb8e6ddb6ad720fe7a77164b044757ced","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"},"source_kind":"arxiv","source_id":"1909.01522","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":"2026-07-05T00:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+SmR3W5B/azzNHC5gVOMoa5qDxxskF5x24TOpuWfKfVG+xt7LG3O6tqC5vzIXM1Qkq16s6VqPAXvJHM+nBlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:30:32.522303Z"},"content_sha256":"2d094995d4391b3e9b4db8058128584b1e562ecc1108ddc25fa7551efc895abd","schema_version":"1.0","event_id":"sha256:2d094995d4391b3e9b4db8058128584b1e562ecc1108ddc25fa7551efc895abd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2QMFJ7HIHRX2VYDJJ56MZBAOT2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mVQNLj0BYWsfd6koo0wOfF/ZWQjrtrhUW0LSXgGCdJlIlRTo0P3/vLatqeef7+HG7RmVWSh++jglmJX+dnjiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:30:32.522680Z"},"content_sha256":"ca4fbc1c71b08b91a49d8f7bea1c3ba481f4e57f1a71a5fe29ef96b770c8e9d8","schema_version":"1.0","event_id":"sha256:ca4fbc1c71b08b91a49d8f7bea1c3ba481f4e57f1a71a5fe29ef96b770c8e9d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/bundle.json","state_url":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/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":"2026-08-21T11:30:32Z","links":{"resolver":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2","bundle":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/bundle.json","state":"https://pith.science/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2QMFJ7HIHRX2VYDJJ56MZBAOT2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2QMFJ7HIHRX2VYDJJ56MZBAOT2","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":"8555a657371148bcf7abef39bbc35d1a74dc773c4cfb504a0f5ebfe216a66704","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T02:20:54Z","title_canon_sha256":"4fca33185e492eeabd6d340d76b500be48de988b1d80c14f5d088092d593bc55"},"schema_version":"1.0","source":{"id":"1909.01522","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01522","created_at":"2026-07-05T00:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01522v2","created_at":"2026-07-05T00:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01522","created_at":"2026-07-05T00:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"2QMFJ7HIHRX2","created_at":"2026-07-05T00:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"2QMFJ7HIHRX2VYDJ","created_at":"2026-07-05T00:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"2QMFJ7HI","created_at":"2026-07-05T00:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:ca4fbc1c71b08b91a49d8f7bea1c3ba481f4e57f1a71a5fe29ef96b770c8e9d8","target":"graph","created_at":"2026-07-05T00:04:44Z","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/1909.01522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Katharina Kann, Kyunghyun Cho, Samuel R. Bowman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T02:20:54Z","title":"Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01522","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":"sha256:2d094995d4391b3e9b4db8058128584b1e562ecc1108ddc25fa7551efc895abd","target":"record","created_at":"2026-07-05T00:04:44Z","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":"8555a657371148bcf7abef39bbc35d1a74dc773c4cfb504a0f5ebfe216a66704","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T02:20:54Z","title_canon_sha256":"4fca33185e492eeabd6d340d76b500be48de988b1d80c14f5d088092d593bc55"},"schema_version":"1.0","source":{"id":"1909.01522","kind":"arxiv","version":2}},"canonical_sha256":"d41854fce83c6faae0694f7ccc840e9eb8e6ddb6ad720fe7a77164b044757ced","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d41854fce83c6faae0694f7ccc840e9eb8e6ddb6ad720fe7a77164b044757ced","first_computed_at":"2026-07-05T00:04:44.535631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:04:44.535631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rTRZ14nCJaE6/QG5c9U3ru2bPeqzFVx0+/OeqHXn2lJg11KSShvunvFnQ6JYUjAQT7JbjqTa4YaXhJzl1FEUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:04:44.536090Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.01522","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d094995d4391b3e9b4db8058128584b1e562ecc1108ddc25fa7551efc895abd","sha256:ca4fbc1c71b08b91a49d8f7bea1c3ba481f4e57f1a71a5fe29ef96b770c8e9d8"],"state_sha256":"92ff9dbcd82059db1b554678af51f2a59b232c085cce9ed4e0f2b3a53ccb1262"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0AiWbF64/fMhZNynSs6ovTi4FH73uZYWW4AtH/QjAH1cQt2WIg0VPNn7xE3R9V4DViaMTMVwaSnUYrg+8EDQAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T11:30:32.525009Z","bundle_sha256":"4700f3337f1cbb8378ef0452abe5753ff4be0af978cd2765b9be5785ca22e012"}}