{ "benchmark_id": "BENCH-24-POPGEN-HAPLO-MSN-SCIPY", "validation_set_id": "VAL-SET-013-POPGEN-HAPLO-MSN-12COHORT", "tool_evaluated": "haplo-cluster / popgen-compare (src/haplotype.rs, src/popgen_calibration.rs)", "external_reference_tool": "SciPy v1.18.1 (scipy.sparse.csgraph.minimum_spanning_tree) + NumPy v2.5.4", "total_cohorts": 12, "dev_cohorts": 6, "reserve_cohorts": 6, "dev_mean_abs_diff_pi": 0.0, "reserve_mean_abs_diff_pi": 0.0, "dev_mean_abs_diff_tajimas_d": 0.0, "reserve_mean_abs_diff_tajimas_d": 0.0, "dev_mean_abs_diff_fst": 0.0, "reserve_mean_abs_diff_fst": 0.0, "tajimas_d_pearson_r": 1.0, "hudson_fst_pearson_r": 1.0, "mst_exact_match_rate_pct": 100.0, "regime_concordance_pct": 100.0, "native_runtime_ms": 16.5343, "scipy_runtime_ms": 130.5781, "speedup_factor": 7.8974, "zero_beaker_reject_logged": "REJECT-2026-035-POPGEN-GEN1-MISSING-FST-WAHLUND-CONFOUNDER", "cohorts": [ { "cohort_id": "DEV-01", "split": "DEV", "biological_system": "Ursus maritimus / U. arctos Mitogenome Clade Split", "accession_or_locus": "NC_003428.1 / NC_003427.1 (COX1)", "expected_regime": "ALLOPATRIC_SUBDIVISION", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 3, "segregating_sites_s": 8, "native_hd": 0.5942, "scipy_hd": 0.5942, "abs_diff_hd": 0.0, "native_pi": 0.0635, "scipy_pi": 0.0635, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0357, "scipy_watterson_theta": 0.0357, "abs_diff_theta": 0.0, "native_tajimas_d": 2.5, "scipy_tajimas_d": 2.5, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.9789, "scipy_hudson_fst": 0.9789, "abs_diff_fst": 0.0, "native_mst_total_steps": 8, "scipy_mst_total_steps": 8, "mst_weight_match": true, "predicted_regime": "ALLOPATRIC_SUBDIVISION", "regime_match": true, "gate_pass": true }, { "cohort_id": "DEV-02", "split": "DEV", "biological_system": "Homo sapiens HBB HbA/HbS Heterozygote-Advantage Balancing Selection", "accession_or_locus": "NG_000007.3 (HBB rs334)", "expected_regime": "BALANCING_SELECTION", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 2, "segregating_sites_s": 8, "native_hd": 0.5217, "scipy_hd": 0.5217, "abs_diff_hd": 0.0, "native_pi": 0.0696, "scipy_pi": 0.0696, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0357, "scipy_watterson_theta": 0.0357, "abs_diff_theta": 0.0, "native_tajimas_d": 3.0426, "scipy_tajimas_d": 3.0426, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.0, "scipy_hudson_fst": 0.0, "abs_diff_fst": 0.0, "native_mst_total_steps": 8, "scipy_mst_total_steps": 8, "mst_weight_match": true, "predicted_regime": "BALANCING_SELECTION", "regime_match": true, "gate_pass": true }, { "cohort_id": "DEV-03", "split": "DEV", "biological_system": "SARS-CoV-2 Spike Early Star-Phylogeny Clonal Expansion", "accession_or_locus": "NC_045512.2 (S)", "expected_regime": "SELECTIVE_SWEEP_OR_EXPANSION", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 11, "segregating_sites_s": 10, "native_hd": 0.6703, "scipy_hd": 0.6703, "abs_diff_hd": 0.0, "native_pi": 0.0139, "scipy_pi": 0.0139, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0446, "scipy_watterson_theta": 0.0446, "abs_diff_theta": 0.0, "native_tajimas_d": -2.2981, "scipy_tajimas_d": -2.2981, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.0, "scipy_hudson_fst": 0.0, "abs_diff_fst": 0.0, "native_mst_total_steps": 10, "scipy_mst_total_steps": 10, "mst_weight_match": true, "predicted_regime": "SELECTIVE_SWEEP_OR_EXPANSION", "regime_match": true, "gate_pass": true }, { "cohort_id": "DEV-04", "split": "DEV", "biological_system": "Drosophila melanogaster Adh Fast/Slow Latitudinal Cline", "accession_or_locus": "M17833.1 (Adh)", "expected_regime": "ALLOPATRIC_SUBDIVISION", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 3, "segregating_sites_s": 7, "native_hd": 0.5616, "scipy_hd": 0.5616, "abs_diff_hd": 0.0, "native_pi": 0.0536, "scipy_pi": 0.0536, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0312, "scipy_watterson_theta": 0.0312, "abs_diff_theta": 0.0, "native_tajimas_d": 2.233, "scipy_tajimas_d": 2.233, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.9863, "scipy_hudson_fst": 0.9863, "abs_diff_fst": 0.0, "native_mst_total_steps": 7, "scipy_mst_total_steps": 7, "mst_weight_match": true, "predicted_regime": "ALLOPATRIC_SUBDIVISION", "regime_match": true, "gate_pass": true }, { "cohort_id": "DEV-05", "split": "DEV", "biological_system": "Plasmodium falciparum pfcrt K76T Selective Sweep Recovery", "accession_or_locus": "XM_001348968.1 (pfcrt)", "expected_regime": "SELECTIVE_SWEEP_OR_EXPANSION", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 10, "segregating_sites_s": 9, "native_hd": 0.6196, "scipy_hd": 0.6196, "abs_diff_hd": 0.0, "native_pi": 0.0125, "scipy_pi": 0.0125, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0402, "scipy_watterson_theta": 0.0402, "abs_diff_theta": 0.0, "native_tajimas_d": -2.2577, "scipy_tajimas_d": -2.2577, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.0, "scipy_hudson_fst": 0.0, "abs_diff_fst": 0.0, "native_mst_total_steps": 9, "scipy_mst_total_steps": 9, "mst_weight_match": true, "predicted_regime": "SELECTIVE_SWEEP_OR_EXPANSION", "regime_match": true, "gate_pass": true }, { "cohort_id": "DEV-06", "split": "DEV", "biological_system": "0🧪 Negative Control: Monomorphic Clonal Fixation (S = 0)", "accession_or_locus": "SYNTH-MONO-POPGEN-DEV06", "expected_regime": "MONOMORPHIC_NULL", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 1, "segregating_sites_s": 0, "native_hd": 0.0, "scipy_hd": 0.0, "abs_diff_hd": 0.0, "native_pi": 0.0, "scipy_pi": 0.0, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0, "scipy_watterson_theta": 0.0, "abs_diff_theta": 0.0, "native_tajimas_d": 0.0, "scipy_tajimas_d": 0.0, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.0, "scipy_hudson_fst": 0.0, "abs_diff_fst": 0.0, "native_mst_total_steps": 0, "scipy_mst_total_steps": 0, "mst_weight_match": true, "predicted_regime": "MONOMORPHIC_NULL", "regime_match": true, "gate_pass": true }, { "cohort_id": "RES-01", "split": "RESERVE", "biological_system": "Thunnus thynnus / T. orientalis Atlantic-Pacific Basin Split", "accession_or_locus": "NC_014052.1 / NC_008455.1 (COX1)", "expected_regime": "ALLOPATRIC_SUBDIVISION", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 4, "segregating_sites_s": 7, "native_hd": 0.6667, "scipy_hd": 0.6667, "abs_diff_hd": 0.0, "native_pi": 0.0488, "scipy_pi": 0.0488, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0312, "scipy_watterson_theta": 0.0312, "abs_diff_theta": 0.0, "native_tajimas_d": 1.7558, "scipy_tajimas_d": 1.7558, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.9432, "scipy_hudson_fst": 0.9432, "abs_diff_fst": 0.0, "native_mst_total_steps": 7, "scipy_mst_total_steps": 7, "mst_weight_match": true, "predicted_regime": "ALLOPATRIC_SUBDIVISION", "regime_match": true, "gate_pass": true }, { "cohort_id": "RES-02", "split": "RESERVE", "biological_system": "Homo sapiens HLA-DRB1 Peptide-Binding Groove Balancing Selection", "accession_or_locus": "NG_002392.2 (HLA-DRB1)", "expected_regime": "BALANCING_SELECTION", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 2, "segregating_sites_s": 9, "native_hd": 0.5217, "scipy_hd": 0.5217, "abs_diff_hd": 0.0, "native_pi": 0.0783, "scipy_pi": 0.0783, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0402, "scipy_watterson_theta": 0.0402, "abs_diff_theta": 0.0, "native_tajimas_d": 3.1083, "scipy_tajimas_d": 3.1083, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.0, "scipy_hudson_fst": 0.0, "abs_diff_fst": 0.0, "native_mst_total_steps": 9, "scipy_mst_total_steps": 9, "mst_weight_match": true, "predicted_regime": "BALANCING_SELECTION", "regime_match": true, "gate_pass": true }, { "cohort_id": "RES-03", "split": "RESERVE", "biological_system": "Mycobacterium tuberculosis Lineage 2 Star Transmission Outbreak", "accession_or_locus": "NC_000962.3 (rpoB/katG)", "expected_regime": "SELECTIVE_SWEEP_OR_EXPANSION", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 12, "segregating_sites_s": 11, "native_hd": 0.7174, "scipy_hd": 0.7174, "abs_diff_hd": 0.0, "native_pi": 0.0153, "scipy_pi": 0.0153, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0491, "scipy_watterson_theta": 0.0491, "abs_diff_theta": 0.0, "native_tajimas_d": -2.3329, "scipy_tajimas_d": -2.3329, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.0, "scipy_hudson_fst": 0.0, "abs_diff_fst": 0.0, "native_mst_total_steps": 11, "scipy_mst_total_steps": 11, "mst_weight_match": true, "predicted_regime": "SELECTIVE_SWEEP_OR_EXPANSION", "regime_match": true, "gate_pass": true }, { "cohort_id": "RES-04", "split": "RESERVE", "biological_system": "Arabidopsis thaliana FRIGIDA (FRI) Glacial Refugial Split", "accession_or_locus": "NM_116232.3 (FRI)", "expected_regime": "ALLOPATRIC_SUBDIVISION", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 3, "segregating_sites_s": 6, "native_hd": 0.5616, "scipy_hd": 0.5616, "abs_diff_hd": 0.0, "native_pi": 0.0449, "scipy_pi": 0.0449, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0268, "scipy_watterson_theta": 0.0268, "abs_diff_theta": 0.0, "native_tajimas_d": 2.0429, "scipy_tajimas_d": 2.0429, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.9836, "scipy_hudson_fst": 0.9836, "abs_diff_fst": 0.0, "native_mst_total_steps": 6, "scipy_mst_total_steps": 6, "mst_weight_match": true, "predicted_regime": "ALLOPATRIC_SUBDIVISION", "regime_match": true, "gate_pass": true }, { "cohort_id": "RES-05", "split": "RESERVE", "biological_system": "Salmo salar Atlantic vs. Baltic Mitochondrial ND1 Split", "accession_or_locus": "NC_001960.1 (ND1)", "expected_regime": "ALLOPATRIC_SUBDIVISION", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 2, "segregating_sites_s": 8, "native_hd": 0.5217, "scipy_hd": 0.5217, "abs_diff_hd": 0.0, "native_pi": 0.0696, "scipy_pi": 0.0696, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0357, "scipy_watterson_theta": 0.0357, "abs_diff_theta": 0.0, "native_tajimas_d": 3.0426, "scipy_tajimas_d": 3.0426, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 1.0, "scipy_hudson_fst": 1.0, "abs_diff_fst": 0.0, "native_mst_total_steps": 8, "scipy_mst_total_steps": 8, "mst_weight_match": true, "predicted_regime": "ALLOPATRIC_SUBDIVISION", "regime_match": true, "gate_pass": true }, { "cohort_id": "RES-06", "split": "RESERVE", "biological_system": "0🧪 Negative Control: Panmictic Label-Permuted Demes (F_ST = 0)", "accession_or_locus": "SYNTH-PANMICTIC-POPGEN-RES06", "expected_regime": "PANMICTIC_DRIFT_NULL", "sample_size_n": 24, "alignment_length_bp": 60, "unique_haplotypes_h": 4, "segregating_sites_s": 3, "native_hd": 0.7826, "scipy_hd": 0.7826, "abs_diff_hd": 0.0, "native_pi": 0.0217, "scipy_pi": 0.0217, "abs_diff_pi": 0.0, "native_watterson_theta": 0.0134, "scipy_watterson_theta": 0.0134, "abs_diff_theta": 0.0, "native_tajimas_d": 1.5685, "scipy_tajimas_d": 1.5685, "abs_diff_tajimas_d": 0.0, "native_hudson_fst": 0.0, "scipy_hudson_fst": 0.0, "abs_diff_fst": 0.0, "native_mst_total_steps": 3, "scipy_mst_total_steps": 3, "mst_weight_match": true, "predicted_regime": "PANMICTIC_DRIFT_NULL", "regime_match": true, "gate_pass": true } ] }