{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WAOPKW7K34ITW3OMDZI5VGHVMC","short_pith_number":"pith:WAOPKW7K","canonical_record":{"source":{"id":"2309.02237","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T13:42:43Z","cross_cats_sorted":[],"title_canon_sha256":"d6cb1cc43548aef6125527e28cb4109bb1bb4fda136c547c02aa0c119686e459","abstract_canon_sha256":"4507b91d70971bc99e7a9f92d20b1b558c22eb3a98d33cee4a727a2eccddd854"},"schema_version":"1.0"},"canonical_sha256":"b01cf55beadf113b6dcc1e51da98f5608f9ba55f4fb67414cd6388c912c2d70a","source":{"kind":"arxiv","id":"2309.02237","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02237","created_at":"2026-07-05T06:47:57Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02237v1","created_at":"2026-07-05T06:47:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02237","created_at":"2026-07-05T06:47:57Z"},{"alias_kind":"pith_short_12","alias_value":"WAOPKW7K34IT","created_at":"2026-07-05T06:47:57Z"},{"alias_kind":"pith_short_16","alias_value":"WAOPKW7K34ITW3OM","created_at":"2026-07-05T06:47:57Z"},{"alias_kind":"pith_short_8","alias_value":"WAOPKW7K","created_at":"2026-07-05T06:47:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WAOPKW7K34ITW3OMDZI5VGHVMC","target":"record","payload":{"canonical_record":{"source":{"id":"2309.02237","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T13:42:43Z","cross_cats_sorted":[],"title_canon_sha256":"d6cb1cc43548aef6125527e28cb4109bb1bb4fda136c547c02aa0c119686e459","abstract_canon_sha256":"4507b91d70971bc99e7a9f92d20b1b558c22eb3a98d33cee4a727a2eccddd854"},"schema_version":"1.0"},"canonical_sha256":"b01cf55beadf113b6dcc1e51da98f5608f9ba55f4fb67414cd6388c912c2d70a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:57.858694Z","signature_b64":"9whK/EUWG7qX+ma9s65a7FiC6TKkGxStnkwFyArVTzlgjYV25GA+4G4wpfYK1OA3lorfqzt1Mhh9Em0TJXcFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b01cf55beadf113b6dcc1e51da98f5608f9ba55f4fb67414cd6388c912c2d70a","last_reissued_at":"2026-07-05T06:47:57.858216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:57.858216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.02237","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":"2026-07-05T06:47:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gvuh5kyKEzpaaYExml6ZaFOpaGLgUsicFNVHQaW6eN/6kzQ7u0tA8Omg4nuh2I5R6c4EY9eoAm+7oUbvp9ySCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:17:31.725628Z"},"content_sha256":"df82ba7fa357a5d90f343b378c1042d1ed6f287fa080462add07f1fb6f2e5c01","schema_version":"1.0","event_id":"sha256:df82ba7fa357a5d90f343b378c1042d1ed6f287fa080462add07f1fb6f2e5c01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WAOPKW7K34ITW3OMDZI5VGHVMC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Size in Natural Language Processing within Healthcare Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Angus Roberts, Daniel Stahl, Diana Shamsutdinova, Felix Zimmer, Jaya Chaturvedi, Robert Stewart, Sumithra Velupillai","submitted_at":"2023-09-05T13:42:43Z","abstract_excerpt":"Sample size calculation is an essential step in most data-based disciplines. Large enough samples ensure representativeness of the population and determine the precision of estimates. This is true for most quantitative studies, including those that employ machine learning methods, such as natural language processing, where free-text is used to generate predictions and classify instances of text. Within the healthcare domain, the lack of sufficient corpora of previously collected data can be a limiting factor when determining sample sizes for new studies. This paper tries to address the issue b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02237","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/2309.02237/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":"2026-07-05T06:47:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hpNUv5bsD4bsl34uqghQpr9EnU5UWRdF2gTN6mSKvaxdp20mDrotgpeOFeCiqV8Am4xKiBHVekPKxV3pIWD2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:17:31.726248Z"},"content_sha256":"a206e3433fa97f461c468c559345e05da8a2bfdd51eebc6a24d10a458abc8f92","schema_version":"1.0","event_id":"sha256:a206e3433fa97f461c468c559345e05da8a2bfdd51eebc6a24d10a458abc8f92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAOPKW7K34ITW3OMDZI5VGHVMC/bundle.json","state_url":"https://pith.science/pith/WAOPKW7K34ITW3OMDZI5VGHVMC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAOPKW7K34ITW3OMDZI5VGHVMC/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":"2026-08-19T12:17:31Z","links":{"resolver":"https://pith.science/pith/WAOPKW7K34ITW3OMDZI5VGHVMC","bundle":"https://pith.science/pith/WAOPKW7K34ITW3OMDZI5VGHVMC/bundle.json","state":"https://pith.science/pith/WAOPKW7K34ITW3OMDZI5VGHVMC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAOPKW7K34ITW3OMDZI5VGHVMC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WAOPKW7K34ITW3OMDZI5VGHVMC","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":"4507b91d70971bc99e7a9f92d20b1b558c22eb3a98d33cee4a727a2eccddd854","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T13:42:43Z","title_canon_sha256":"d6cb1cc43548aef6125527e28cb4109bb1bb4fda136c547c02aa0c119686e459"},"schema_version":"1.0","source":{"id":"2309.02237","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02237","created_at":"2026-07-05T06:47:57Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02237v1","created_at":"2026-07-05T06:47:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02237","created_at":"2026-07-05T06:47:57Z"},{"alias_kind":"pith_short_12","alias_value":"WAOPKW7K34IT","created_at":"2026-07-05T06:47:57Z"},{"alias_kind":"pith_short_16","alias_value":"WAOPKW7K34ITW3OM","created_at":"2026-07-05T06:47:57Z"},{"alias_kind":"pith_short_8","alias_value":"WAOPKW7K","created_at":"2026-07-05T06:47:57Z"}],"graph_snapshots":[{"event_id":"sha256:a206e3433fa97f461c468c559345e05da8a2bfdd51eebc6a24d10a458abc8f92","target":"graph","created_at":"2026-07-05T06:47:57Z","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/2309.02237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample size calculation is an essential step in most data-based disciplines. Large enough samples ensure representativeness of the population and determine the precision of estimates. This is true for most quantitative studies, including those that employ machine learning methods, such as natural language processing, where free-text is used to generate predictions and classify instances of text. Within the healthcare domain, the lack of sufficient corpora of previously collected data can be a limiting factor when determining sample sizes for new studies. This paper tries to address the issue b","authors_text":"Angus Roberts, Daniel Stahl, Diana Shamsutdinova, Felix Zimmer, Jaya Chaturvedi, Robert Stewart, Sumithra Velupillai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T13:42:43Z","title":"Sample Size in Natural Language Processing within Healthcare Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02237","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:df82ba7fa357a5d90f343b378c1042d1ed6f287fa080462add07f1fb6f2e5c01","target":"record","created_at":"2026-07-05T06:47:57Z","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":"4507b91d70971bc99e7a9f92d20b1b558c22eb3a98d33cee4a727a2eccddd854","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T13:42:43Z","title_canon_sha256":"d6cb1cc43548aef6125527e28cb4109bb1bb4fda136c547c02aa0c119686e459"},"schema_version":"1.0","source":{"id":"2309.02237","kind":"arxiv","version":1}},"canonical_sha256":"b01cf55beadf113b6dcc1e51da98f5608f9ba55f4fb67414cd6388c912c2d70a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b01cf55beadf113b6dcc1e51da98f5608f9ba55f4fb67414cd6388c912c2d70a","first_computed_at":"2026-07-05T06:47:57.858216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:57.858216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9whK/EUWG7qX+ma9s65a7FiC6TKkGxStnkwFyArVTzlgjYV25GA+4G4wpfYK1OA3lorfqzt1Mhh9Em0TJXcFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:57.858694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.02237","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df82ba7fa357a5d90f343b378c1042d1ed6f287fa080462add07f1fb6f2e5c01","sha256:a206e3433fa97f461c468c559345e05da8a2bfdd51eebc6a24d10a458abc8f92"],"state_sha256":"34eca38cd4478499f93ad143fd6c41219b52be36e43859964e4428f054127499"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OA7H7oIL6V8kciTrW6zxnzR/fhZHbIhS3OceeoEJ37uRnN2dlaoapX29qf+74ZacwFWUxVB5/zmyKXMvNkdfCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T12:17:31.731034Z","bundle_sha256":"5b9337cc3af6adc975fa168a13ce373aa97edd16ccd3674e51b889c6b5e354c7"}}