{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:254CM3ER7ZMDYTP46A6YKZMEUI","short_pith_number":"pith:254CM3ER","canonical_record":{"source":{"id":"1812.08102","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-19T17:27:04Z","cross_cats_sorted":[],"title_canon_sha256":"fa0efede97d460ed467dbc42fd840c78cfa9d95738303307cc40de7a1007e0df","abstract_canon_sha256":"9db8aa5273e562c4c6dafd20a4fda8a96f2d5b3fea941eb44f3f794a1ce2c9b1"},"schema_version":"1.0"},"canonical_sha256":"d778266c91fe583c4dfcf03d856584a223dfb53c13a83a3c5e603f66811d5481","source":{"kind":"arxiv","id":"1812.08102","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.08102","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"arxiv_version","alias_value":"1812.08102v2","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08102","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"pith_short_12","alias_value":"254CM3ER7ZMD","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"254CM3ER7ZMDYTP4","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"254CM3ER","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:254CM3ER7ZMDYTP46A6YKZMEUI","target":"record","payload":{"canonical_record":{"source":{"id":"1812.08102","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-19T17:27:04Z","cross_cats_sorted":[],"title_canon_sha256":"fa0efede97d460ed467dbc42fd840c78cfa9d95738303307cc40de7a1007e0df","abstract_canon_sha256":"9db8aa5273e562c4c6dafd20a4fda8a96f2d5b3fea941eb44f3f794a1ce2c9b1"},"schema_version":"1.0"},"canonical_sha256":"d778266c91fe583c4dfcf03d856584a223dfb53c13a83a3c5e603f66811d5481","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:57.977290Z","signature_b64":"G0ex/MhLHhA26EqIY7/5+yjo9958sC7Dvu0zcFsFOAZ6QRuCetWaH2je4Fqn68uQzWV3izFqJ0wTRZv8baElAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d778266c91fe583c4dfcf03d856584a223dfb53c13a83a3c5e603f66811d5481","last_reissued_at":"2026-05-17T23:56:57.976723Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:57.976723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.08102","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":"2026-05-17T23:56:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xyLT6odOf/tjfM3rPDoCyVEHdUJ1CHZ+b+oxuRsKOf3m6BOnB52mOc3TP017Nz2E2+Nsq1b3yqxdfnVcBp8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:08:33.778450Z"},"content_sha256":"00c0e6fedfa2b6666235e210577c5059842572c7c702c32ebbb66ef7abc821a2","schema_version":"1.0","event_id":"sha256:00c0e6fedfa2b6666235e210577c5059842572c7c702c32ebbb66ef7abc821a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:254CM3ER7ZMDYTP46A6YKZMEUI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Random Forest Classifier in WEKA: Discussion and New Developments for Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Maier, Elli Angelopoulou, Firas Mualla, Mario Amrehn, Stefan Steidl","submitted_at":"2018-12-19T17:27:04Z","abstract_excerpt":"Data analysis and machine learning have become an integrative part of the modern scientific methodology, providing automated techniques to predict further information based on observations. One of these classification and regression techniques is the random forest approach. Those decision tree based predictors are best known for their good computational performance and scalability. However, in case of severely imbalanced training data, as often seen in medical studies' data with large control groups, the training algorithm or the sampling process has to be altered in order to improve the predi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08102","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":""},"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":"2026-05-17T23:56:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"55QH/ehKS3reDoB9shnN9xATn+fDhbco4JTQII2tVNJxwIiaOA6eLIKFGreVatB88tRa1GVtgZ41M/PZ+OX1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:08:33.778800Z"},"content_sha256":"a846ab63f0880c9be3b7aa365ab1c3ffd3483c124ca00d54bc6250fc9e704b5a","schema_version":"1.0","event_id":"sha256:a846ab63f0880c9be3b7aa365ab1c3ffd3483c124ca00d54bc6250fc9e704b5a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/254CM3ER7ZMDYTP46A6YKZMEUI/bundle.json","state_url":"https://pith.science/pith/254CM3ER7ZMDYTP46A6YKZMEUI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/254CM3ER7ZMDYTP46A6YKZMEUI/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":"2026-06-06T09:08:33Z","links":{"resolver":"https://pith.science/pith/254CM3ER7ZMDYTP46A6YKZMEUI","bundle":"https://pith.science/pith/254CM3ER7ZMDYTP46A6YKZMEUI/bundle.json","state":"https://pith.science/pith/254CM3ER7ZMDYTP46A6YKZMEUI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/254CM3ER7ZMDYTP46A6YKZMEUI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:254CM3ER7ZMDYTP46A6YKZMEUI","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":"9db8aa5273e562c4c6dafd20a4fda8a96f2d5b3fea941eb44f3f794a1ce2c9b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-19T17:27:04Z","title_canon_sha256":"fa0efede97d460ed467dbc42fd840c78cfa9d95738303307cc40de7a1007e0df"},"schema_version":"1.0","source":{"id":"1812.08102","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.08102","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"arxiv_version","alias_value":"1812.08102v2","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08102","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"pith_short_12","alias_value":"254CM3ER7ZMD","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"254CM3ER7ZMDYTP4","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"254CM3ER","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:a846ab63f0880c9be3b7aa365ab1c3ffd3483c124ca00d54bc6250fc9e704b5a","target":"graph","created_at":"2026-05-17T23:56:57Z","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"},"paper":{"abstract_excerpt":"Data analysis and machine learning have become an integrative part of the modern scientific methodology, providing automated techniques to predict further information based on observations. One of these classification and regression techniques is the random forest approach. Those decision tree based predictors are best known for their good computational performance and scalability. However, in case of severely imbalanced training data, as often seen in medical studies' data with large control groups, the training algorithm or the sampling process has to be altered in order to improve the predi","authors_text":"Andreas Maier, Elli Angelopoulou, Firas Mualla, Mario Amrehn, Stefan Steidl","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-19T17:27:04Z","title":"The Random Forest Classifier in WEKA: Discussion and New Developments for Imbalanced Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08102","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":"sha256:00c0e6fedfa2b6666235e210577c5059842572c7c702c32ebbb66ef7abc821a2","target":"record","created_at":"2026-05-17T23:56:57Z","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":"9db8aa5273e562c4c6dafd20a4fda8a96f2d5b3fea941eb44f3f794a1ce2c9b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-19T17:27:04Z","title_canon_sha256":"fa0efede97d460ed467dbc42fd840c78cfa9d95738303307cc40de7a1007e0df"},"schema_version":"1.0","source":{"id":"1812.08102","kind":"arxiv","version":2}},"canonical_sha256":"d778266c91fe583c4dfcf03d856584a223dfb53c13a83a3c5e603f66811d5481","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d778266c91fe583c4dfcf03d856584a223dfb53c13a83a3c5e603f66811d5481","first_computed_at":"2026-05-17T23:56:57.976723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:57.976723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G0ex/MhLHhA26EqIY7/5+yjo9958sC7Dvu0zcFsFOAZ6QRuCetWaH2je4Fqn68uQzWV3izFqJ0wTRZv8baElAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:57.977290Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.08102","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00c0e6fedfa2b6666235e210577c5059842572c7c702c32ebbb66ef7abc821a2","sha256:a846ab63f0880c9be3b7aa365ab1c3ffd3483c124ca00d54bc6250fc9e704b5a"],"state_sha256":"7d65bfc6afb2db64f01d25b401d33e896ad226d8ddc7cb4487241c8f04864930"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lzLbIBazUK++0RirXF7ZIMKOBNZP30FrwxUXDVS13DgyL//HmrW+Vl9nt9WyXPMu2ySl1aSiaKsvRYxdzl8AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T09:08:33.780842Z","bundle_sha256":"a52f2e7749a9686799775fc7042f7ce48058f7485b3f880b7b42e9313464b08b"}}