{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AGBY5UOVJWHM6T5RNGDDMRCVIY","short_pith_number":"pith:AGBY5UOV","canonical_record":{"source":{"id":"2103.15147","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-28T15:00:59Z","cross_cats_sorted":[],"title_canon_sha256":"e28870a34f9bd2e67ef4d62269885a250dcb8d3df14f9a34ba5e7541258b3c4e","abstract_canon_sha256":"b382677ae27cd00d4311483608d49aa25310805b50f3d83084e05664f3957ed5"},"schema_version":"1.0"},"canonical_sha256":"01838ed1d54d8ecf4fb16986364455461afc2637a45d9b3ce83654b9a75d0e4a","source":{"kind":"arxiv","id":"2103.15147","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.15147","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"arxiv_version","alias_value":"2103.15147v3","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15147","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"pith_short_12","alias_value":"AGBY5UOVJWHM","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"pith_short_16","alias_value":"AGBY5UOVJWHM6T5R","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"pith_short_8","alias_value":"AGBY5UOV","created_at":"2026-07-05T02:40:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AGBY5UOVJWHM6T5RNGDDMRCVIY","target":"record","payload":{"canonical_record":{"source":{"id":"2103.15147","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-28T15:00:59Z","cross_cats_sorted":[],"title_canon_sha256":"e28870a34f9bd2e67ef4d62269885a250dcb8d3df14f9a34ba5e7541258b3c4e","abstract_canon_sha256":"b382677ae27cd00d4311483608d49aa25310805b50f3d83084e05664f3957ed5"},"schema_version":"1.0"},"canonical_sha256":"01838ed1d54d8ecf4fb16986364455461afc2637a45d9b3ce83654b9a75d0e4a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:33.559687Z","signature_b64":"xjsM+gfSecoNE5CYS4OnFs6W0Xz8qPwUg6P9/lb8a2/poLy0nSH+WlEdBhyK+bZSZG5AvxHTlH9Q8nFcgx8XCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01838ed1d54d8ecf4fb16986364455461afc2637a45d9b3ce83654b9a75d0e4a","last_reissued_at":"2026-07-05T02:40:33.559177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:33.559177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.15147","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:40:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g3XrvGPgPCRv7wXSmr1wloiNZ8gBCP8HzBb5k9SR4zVLpQnSOjQyWpBFWQhIe2rbP4CcQSQF7QtydVhH8E04AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:25:33.404517Z"},"content_sha256":"a4bd58d31b8c4532ce62af52a3a9650cde68ca0f61b5aad42bd313836dcf11c4","schema_version":"1.0","event_id":"sha256:a4bd58d31b8c4532ce62af52a3a9650cde68ca0f61b5aad42bd313836dcf11c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AGBY5UOVJWHM6T5RNGDDMRCVIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Symbolic regression outperforms other models for small data sets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Casper Wilstrup, Jaan Kasak","submitted_at":"2021-03-28T15:00:59Z","abstract_excerpt":"Machine learning is often applied in health science to obtain predictions and new understandings of complex phenomena and relationships, but an availability of sufficient data for model training is a widespread problem. Traditional machine learning techniques, such as random forests and gradient boosting, tend to overfit when working with data sets of only a few hundred observations. This study demonstrates that for small training sets of 250 observations, symbolic regression generalises better to out-of-sample data than traditional machine learning frameworks, as measured by the coefficient o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15147","kind":"arxiv","version":3},"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/2103.15147/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":"2026-07-05T02:40:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQ+tpXN1G344vWQ4j0m34BtG6/Ts46mVQ8ul0L55TPW1ipCOwVtRU00cQU06W43Yqnnr3+Dsr9v2Jujc3MAACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:25:33.405235Z"},"content_sha256":"13df377497ef23ee9ce6f22e20bc7379d91cd6b9b23adc95a5ec47fd9a038bb5","schema_version":"1.0","event_id":"sha256:13df377497ef23ee9ce6f22e20bc7379d91cd6b9b23adc95a5ec47fd9a038bb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AGBY5UOVJWHM6T5RNGDDMRCVIY/bundle.json","state_url":"https://pith.science/pith/AGBY5UOVJWHM6T5RNGDDMRCVIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AGBY5UOVJWHM6T5RNGDDMRCVIY/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":"2026-08-19T17:25:33Z","links":{"resolver":"https://pith.science/pith/AGBY5UOVJWHM6T5RNGDDMRCVIY","bundle":"https://pith.science/pith/AGBY5UOVJWHM6T5RNGDDMRCVIY/bundle.json","state":"https://pith.science/pith/AGBY5UOVJWHM6T5RNGDDMRCVIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AGBY5UOVJWHM6T5RNGDDMRCVIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AGBY5UOVJWHM6T5RNGDDMRCVIY","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":"b382677ae27cd00d4311483608d49aa25310805b50f3d83084e05664f3957ed5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-28T15:00:59Z","title_canon_sha256":"e28870a34f9bd2e67ef4d62269885a250dcb8d3df14f9a34ba5e7541258b3c4e"},"schema_version":"1.0","source":{"id":"2103.15147","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.15147","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"arxiv_version","alias_value":"2103.15147v3","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15147","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"pith_short_12","alias_value":"AGBY5UOVJWHM","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"pith_short_16","alias_value":"AGBY5UOVJWHM6T5R","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"pith_short_8","alias_value":"AGBY5UOV","created_at":"2026-07-05T02:40:33Z"}],"graph_snapshots":[{"event_id":"sha256:13df377497ef23ee9ce6f22e20bc7379d91cd6b9b23adc95a5ec47fd9a038bb5","target":"graph","created_at":"2026-07-05T02:40:33Z","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/2103.15147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning is often applied in health science to obtain predictions and new understandings of complex phenomena and relationships, but an availability of sufficient data for model training is a widespread problem. Traditional machine learning techniques, such as random forests and gradient boosting, tend to overfit when working with data sets of only a few hundred observations. This study demonstrates that for small training sets of 250 observations, symbolic regression generalises better to out-of-sample data than traditional machine learning frameworks, as measured by the coefficient o","authors_text":"Casper Wilstrup, Jaan Kasak","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-28T15:00:59Z","title":"Symbolic regression outperforms other models for small data sets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15147","kind":"arxiv","version":3},"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:a4bd58d31b8c4532ce62af52a3a9650cde68ca0f61b5aad42bd313836dcf11c4","target":"record","created_at":"2026-07-05T02:40:33Z","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":"b382677ae27cd00d4311483608d49aa25310805b50f3d83084e05664f3957ed5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-28T15:00:59Z","title_canon_sha256":"e28870a34f9bd2e67ef4d62269885a250dcb8d3df14f9a34ba5e7541258b3c4e"},"schema_version":"1.0","source":{"id":"2103.15147","kind":"arxiv","version":3}},"canonical_sha256":"01838ed1d54d8ecf4fb16986364455461afc2637a45d9b3ce83654b9a75d0e4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01838ed1d54d8ecf4fb16986364455461afc2637a45d9b3ce83654b9a75d0e4a","first_computed_at":"2026-07-05T02:40:33.559177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:33.559177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xjsM+gfSecoNE5CYS4OnFs6W0Xz8qPwUg6P9/lb8a2/poLy0nSH+WlEdBhyK+bZSZG5AvxHTlH9Q8nFcgx8XCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:33.559687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.15147","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4bd58d31b8c4532ce62af52a3a9650cde68ca0f61b5aad42bd313836dcf11c4","sha256:13df377497ef23ee9ce6f22e20bc7379d91cd6b9b23adc95a5ec47fd9a038bb5"],"state_sha256":"e5b06560d7176fe54c93be29cfc5c0edb933c8886846b83971cf9d5e8a68b8e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ekQpmiJZPGGzy8PRjA/O89Sf+1thgq9JPApx0/zIYFs2Xin0r8Ry86fX19mE4eu+ssK5Jv1kyHw8P+TZEl14DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:25:33.412018Z","bundle_sha256":"431b9517b2e1459658c74f81371ec223fe8a510c143ae6094ed151d093eb2b36"}}