{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y5QNB5SHVQJWNENHC6YKL2SGCN","short_pith_number":"pith:Y5QNB5SH","schema_version":"1.0","canonical_sha256":"c760d0f647ac136691a717b0a5ea46137e7befc6394f92c135c8f27fc1e02a79","source":{"kind":"arxiv","id":"2606.24944","version":1},"attestation_state":"computed","paper":{"title":"A Leakage-Aware Comparative Benchmark of Machine Learning, Deep Learning, and Transformer Models for Reliable Leukemia Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Nisreen Albzour","submitted_at":"2026-06-23T04:53:49Z","abstract_excerpt":"Automated classification of acute lymphoblastic leukemia (ALL) from peripheral blood smear images has often reported near-perfect performance on the C-NMC 2019 dataset. We show that such results can be inflated by patient-level data leakage caused by random image-level partitioning, where cells from the same subject may appear in both training and test folds. We establish a leakage-aware benchmark under a strict subject-disjoint protocol, comparing LightGBM, RBF-SVM, EfficientNet-B0, EfficientNet-B1, and ViT-Tiny. Models are developed using three subject-disjoint folds from 73 subjects and eva"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.24944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2026-06-23T04:53:49Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"17199fc489fabf5d2decc67a29ca171582f845f1b6ab62c36ba8aa05bd2b5863","abstract_canon_sha256":"79eac6ae6e635c5f103beb1a03d3d1a92aa1e1b868acdc9c99005ffd231791ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:17:46.568951Z","signature_b64":"GdGHn4YuGPhyhZle9+LWbZNPbQhQrA6Rw+Vb9wKbu2q7hWElFxBbwLrUny7eqOWX4CCbNQRamZqbQhQU69ErAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c760d0f647ac136691a717b0a5ea46137e7befc6394f92c135c8f27fc1e02a79","last_reissued_at":"2026-06-25T00:17:46.568605Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:17:46.568605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Leakage-Aware Comparative Benchmark of Machine Learning, Deep Learning, and Transformer Models for Reliable Leukemia Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Nisreen Albzour","submitted_at":"2026-06-23T04:53:49Z","abstract_excerpt":"Automated classification of acute lymphoblastic leukemia (ALL) from peripheral blood smear images has often reported near-perfect performance on the C-NMC 2019 dataset. We show that such results can be inflated by patient-level data leakage caused by random image-level partitioning, where cells from the same subject may appear in both training and test folds. We establish a leakage-aware benchmark under a strict subject-disjoint protocol, comparing LightGBM, RBF-SVM, EfficientNet-B0, EfficientNet-B1, and ViT-Tiny. Models are developed using three subject-disjoint folds from 73 subjects and eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24944","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/2606.24944/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.24944","created_at":"2026-06-25T00:17:46.568667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24944v1","created_at":"2026-06-25T00:17:46.568667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24944","created_at":"2026-06-25T00:17:46.568667+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5QNB5SHVQJW","created_at":"2026-06-25T00:17:46.568667+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5QNB5SHVQJWNENH","created_at":"2026-06-25T00:17:46.568667+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5QNB5SH","created_at":"2026-06-25T00:17:46.568667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5QNB5SHVQJWNENHC6YKL2SGCN","json":"https://pith.science/pith/Y5QNB5SHVQJWNENHC6YKL2SGCN.json","graph_json":"https://pith.science/api/pith-number/Y5QNB5SHVQJWNENHC6YKL2SGCN/graph.json","events_json":"https://pith.science/api/pith-number/Y5QNB5SHVQJWNENHC6YKL2SGCN/events.json","paper":"https://pith.science/paper/Y5QNB5SH"},"agent_actions":{"view_html":"https://pith.science/pith/Y5QNB5SHVQJWNENHC6YKL2SGCN","download_json":"https://pith.science/pith/Y5QNB5SHVQJWNENHC6YKL2SGCN.json","view_paper":"https://pith.science/paper/Y5QNB5SH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24944&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5QNB5SHVQJWNENHC6YKL2SGCN/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5QNB5SHVQJWNENHC6YKL2SGCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5QNB5SHVQJWNENHC6YKL2SGCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5QNB5SHVQJWNENHC6YKL2SGCN/action/storage_attestation","attest_author":"https://pith.science/pith/Y5QNB5SHVQJWNENHC6YKL2SGCN/action/author_attestation","sign_citation":"https://pith.science/pith/Y5QNB5SHVQJWNENHC6YKL2SGCN/action/citation_signature","submit_replication":"https://pith.science/pith/Y5QNB5SHVQJWNENHC6YKL2SGCN/action/replication_record"}},"created_at":"2026-06-25T00:17:46.568667+00:00","updated_at":"2026-06-25T00:17:46.568667+00:00"}