{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W2MYBJ4Y55L6GOAB337AOKKNJV","short_pith_number":"pith:W2MYBJ4Y","canonical_record":{"source":{"id":"2503.12239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-15T19:34:15Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"fca1f246cd2b6bbb8e050b99eb38d31e07836143e55e4d8948aa685cc8b915d8","abstract_canon_sha256":"186b258b2f41d4c4278d45e7c4c6aa698728e338782c4c17c841dbaf8a829833"},"schema_version":"1.0"},"canonical_sha256":"b69980a798ef57e33801defe07294d4d6aa212a97aeee572c2f54693b89c9b9f","source":{"kind":"arxiv","id":"2503.12239","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12239","created_at":"2026-07-05T10:32:42Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12239v1","created_at":"2026-07-05T10:32:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12239","created_at":"2026-07-05T10:32:42Z"},{"alias_kind":"pith_short_12","alias_value":"W2MYBJ4Y55L6","created_at":"2026-07-05T10:32:42Z"},{"alias_kind":"pith_short_16","alias_value":"W2MYBJ4Y55L6GOAB","created_at":"2026-07-05T10:32:42Z"},{"alias_kind":"pith_short_8","alias_value":"W2MYBJ4Y","created_at":"2026-07-05T10:32:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W2MYBJ4Y55L6GOAB337AOKKNJV","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-15T19:34:15Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"fca1f246cd2b6bbb8e050b99eb38d31e07836143e55e4d8948aa685cc8b915d8","abstract_canon_sha256":"186b258b2f41d4c4278d45e7c4c6aa698728e338782c4c17c841dbaf8a829833"},"schema_version":"1.0"},"canonical_sha256":"b69980a798ef57e33801defe07294d4d6aa212a97aeee572c2f54693b89c9b9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:42.981638Z","signature_b64":"gv/gCvoFhsCBKi3bYASU1GX6YNVEXMqHEPp53tNdioYdxeIIvpVxn5JUIfywd0dN5/a7ZC5xRB2wEdGTl2jTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b69980a798ef57e33801defe07294d4d6aa212a97aeee572c2f54693b89c9b9f","last_reissued_at":"2026-07-05T10:32:42.980931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:42.980931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12239","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":"2026-07-05T10:32:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P9jjrE9FqU1M3iMtkVuKyQNYuqI6jOhaBN+6km7vvzGN5PzjIvclQuyTqMwfBiqRPPu5jVowd3DwIOBZ75EoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:30:18.168667Z"},"content_sha256":"f547d7a8de3ad91e992471c4f175b95c86f3363077d35e4185d595eeb4a72afd","schema_version":"1.0","event_id":"sha256:f547d7a8de3ad91e992471c4f175b95c86f3363077d35e4185d595eeb4a72afd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W2MYBJ4Y55L6GOAB337AOKKNJV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Novel Double Pruning method for Imbalanced Data using Information Entropy and Roulette Wheel Selection for Breast Cancer Diagnosis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Belarbi Mostefa, Doreen Sebastian Sarwatt, Huansheng Ning, Sahraoui Dhelim, Soufiane Bacha","submitted_at":"2025-03-15T19:34:15Z","abstract_excerpt":"Accurate illness diagnosis is vital for effective treatment and patient safety. Machine learning models are widely used for cancer diagnosis based on historical medical data. However, data imbalance remains a major challenge, leading to hindering classifier performance and reliability. The SMOTEBoost method addresses this issue by generating synthetic data to balance the dataset, but it may overlook crucial overlapping regions near the decision boundary and can produce noisy samples. This paper proposes RE-SMOTEBoost, an enhanced version of SMOTEBoost, designed to overcome these limitations. F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12239","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/2503.12239/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":"2026-07-05T10:32:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RbKRQUmfyZIoTSEX0zKt9pmAyHTkFKaSClKGdInjRKYGNFRDSLZYUnGu9i/rS5ExNoGbxEqKcsc6yWdxJDasCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:30:18.169348Z"},"content_sha256":"4921992e87fb122faf043d799555e93887b10425c55eec735a20185d1fb6db80","schema_version":"1.0","event_id":"sha256:4921992e87fb122faf043d799555e93887b10425c55eec735a20185d1fb6db80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W2MYBJ4Y55L6GOAB337AOKKNJV/bundle.json","state_url":"https://pith.science/pith/W2MYBJ4Y55L6GOAB337AOKKNJV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W2MYBJ4Y55L6GOAB337AOKKNJV/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":"2026-08-04T17:30:18Z","links":{"resolver":"https://pith.science/pith/W2MYBJ4Y55L6GOAB337AOKKNJV","bundle":"https://pith.science/pith/W2MYBJ4Y55L6GOAB337AOKKNJV/bundle.json","state":"https://pith.science/pith/W2MYBJ4Y55L6GOAB337AOKKNJV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W2MYBJ4Y55L6GOAB337AOKKNJV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W2MYBJ4Y55L6GOAB337AOKKNJV","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":"186b258b2f41d4c4278d45e7c4c6aa698728e338782c4c17c841dbaf8a829833","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-15T19:34:15Z","title_canon_sha256":"fca1f246cd2b6bbb8e050b99eb38d31e07836143e55e4d8948aa685cc8b915d8"},"schema_version":"1.0","source":{"id":"2503.12239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12239","created_at":"2026-07-05T10:32:42Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12239v1","created_at":"2026-07-05T10:32:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12239","created_at":"2026-07-05T10:32:42Z"},{"alias_kind":"pith_short_12","alias_value":"W2MYBJ4Y55L6","created_at":"2026-07-05T10:32:42Z"},{"alias_kind":"pith_short_16","alias_value":"W2MYBJ4Y55L6GOAB","created_at":"2026-07-05T10:32:42Z"},{"alias_kind":"pith_short_8","alias_value":"W2MYBJ4Y","created_at":"2026-07-05T10:32:42Z"}],"graph_snapshots":[{"event_id":"sha256:4921992e87fb122faf043d799555e93887b10425c55eec735a20185d1fb6db80","target":"graph","created_at":"2026-07-05T10:32:42Z","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/2503.12239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate illness diagnosis is vital for effective treatment and patient safety. Machine learning models are widely used for cancer diagnosis based on historical medical data. However, data imbalance remains a major challenge, leading to hindering classifier performance and reliability. The SMOTEBoost method addresses this issue by generating synthetic data to balance the dataset, but it may overlook crucial overlapping regions near the decision boundary and can produce noisy samples. This paper proposes RE-SMOTEBoost, an enhanced version of SMOTEBoost, designed to overcome these limitations. F","authors_text":"Belarbi Mostefa, Doreen Sebastian Sarwatt, Huansheng Ning, Sahraoui Dhelim, Soufiane Bacha","cross_cats":["cs.AI","cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-15T19:34:15Z","title":"A Novel Double Pruning method for Imbalanced Data using Information Entropy and Roulette Wheel Selection for Breast Cancer Diagnosis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12239","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:f547d7a8de3ad91e992471c4f175b95c86f3363077d35e4185d595eeb4a72afd","target":"record","created_at":"2026-07-05T10:32:42Z","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":"186b258b2f41d4c4278d45e7c4c6aa698728e338782c4c17c841dbaf8a829833","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-15T19:34:15Z","title_canon_sha256":"fca1f246cd2b6bbb8e050b99eb38d31e07836143e55e4d8948aa685cc8b915d8"},"schema_version":"1.0","source":{"id":"2503.12239","kind":"arxiv","version":1}},"canonical_sha256":"b69980a798ef57e33801defe07294d4d6aa212a97aeee572c2f54693b89c9b9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b69980a798ef57e33801defe07294d4d6aa212a97aeee572c2f54693b89c9b9f","first_computed_at":"2026-07-05T10:32:42.980931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:42.980931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gv/gCvoFhsCBKi3bYASU1GX6YNVEXMqHEPp53tNdioYdxeIIvpVxn5JUIfywd0dN5/a7ZC5xRB2wEdGTl2jTBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:42.981638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f547d7a8de3ad91e992471c4f175b95c86f3363077d35e4185d595eeb4a72afd","sha256:4921992e87fb122faf043d799555e93887b10425c55eec735a20185d1fb6db80"],"state_sha256":"805541b9e64a5355034ae2c9c2a62894658d9e0f8fb30a989a4e7f7d68a3b7d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UNlXmMHJQ4q3SeVGlkFustizRIYl++fiiVSiP232t33glwhS4ARvFUbFqxptKNGdONv5WD+caJYzleNYkL18Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:30:18.175667Z","bundle_sha256":"6108a10f01bf312c0de80fae3596a14829c0e48ab5a74217233d3739444c074e"}}