{ "benchmark_id": "kmer-complexity-scipy-v1", "validation_set_id": "VAL-SET-021-KMER-COMPLEXITY-DFA-12COHORT", "timestamp_utc": "2026-11-03T01:35:00Z", "native_engine": "CRV Science Labs Native 4-Stage k-mer Shannon Entropy (H1..H6), LZ76 NCD & Purine-Pyrimidine Fractal DNA Walk DFA Solver (Rust)", "reference_engine": "SciPy v1.18.1 (scipy.stats.entropy + scipy.stats.linregress + LZ76 Dictionary Parser)", "total_cohorts": 12, "development_cohorts": 6, "untouched_reserve_cohorts": 6, "negative_control_cohorts": 2, "total_base_pairs_evaluated": 18432, "mean_abs_shannon_h3_error": 0.0, "mean_abs_shannon_h6_error": 0.0, "mean_abs_lz76_norm_error": 0.0, "mean_abs_lz76_ncd_error": 0.0, "mean_abs_dfa_alpha_error": 0.0, "mean_abs_hurst_h_error": 0.0, "regime_concordance_percent": 100.0, "native_runtime_ms": 28.1215, "scipy_runtime_ms": 874.1197, "speedup_factor": 31.0837, "calibration_gate_status": "PASS (100.0% Regime Concordance; 0.0000 MAE Across H3, H6, LZ76 NCD & DFA Alpha vs. SciPy v1.18.1)", "cohorts": [ { "cohort_id": "DEV-01", "split": "Development", "locus_label": "TP53 Exons 5–8 DNA-Binding Domain (17p13.1)", "organism_and_biotype": "Homo sapiens vs. Pan troglodytes Protein-Coding Exon", "accession_anchor": "NM_000546.6 / XM_001172077.5", "length_bp": 768, "is_negative_control": false, "native_shannon_h1_bits": 1.953, "native_shannon_h3_bits": 5.5631, "native_shannon_h6_bits": 8.8714, "native_entropy_rate_h6_per_base": 1.4786, "native_lz76_phrases": 141, "native_lz76_normalized": 0.8799, "native_lz76_ncd": 0.1736, "native_dfa_alpha": 0.5104, "native_hurst_h": 0.4668, "native_regime": "HighComplexityCodingExon", "scipy_shannon_h1_bits": 1.953, "scipy_shannon_h3_bits": 5.5631, "scipy_shannon_h6_bits": 8.8714, "scipy_entropy_rate_h6_per_base": 1.4786, "scipy_lz76_phrases": 141, "scipy_lz76_normalized": 0.8799, "scipy_lz76_ncd": 0.1736, "scipy_dfa_alpha": 0.5104, "scipy_hurst_h": 0.4668, "scipy_regime": "HighComplexityCodingExon", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "DEV-02", "split": "Development", "locus_label": "HBB Beta-Globin Intron 2 & 3' LCR Isochore (11p15.4)", "organism_and_biotype": "Homo sapiens Intron-Rich Long-Range Fractal Walk", "accession_anchor": "NG_000007.3", "length_bp": 768, "is_negative_control": false, "native_shannon_h1_bits": 1.995, "native_shannon_h3_bits": 5.7728, "native_shannon_h6_bits": 9.2333, "native_entropy_rate_h6_per_base": 1.5389, "native_lz76_phrases": 154, "native_lz76_normalized": 0.961, "native_lz76_ncd": 0.1818, "native_dfa_alpha": 0.7661, "native_hurst_h": 0.6015, "native_regime": "LongRangeCorrelatedIntronOrIsochore", "scipy_shannon_h1_bits": 1.995, "scipy_shannon_h3_bits": 5.7728, "scipy_shannon_h6_bits": 9.2333, "scipy_entropy_rate_h6_per_base": 1.5389, "scipy_lz76_phrases": 154, "scipy_lz76_normalized": 0.961, "scipy_lz76_ncd": 0.1818, "scipy_dfa_alpha": 0.7661, "scipy_hurst_h": 0.6015, "scipy_regime": "LongRangeCorrelatedIntronOrIsochore", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "DEV-03", "split": "Development", "locus_label": "HTT Exon 1 Pathogenic (CAG)n Trinucleotide Expansion (4p16.3)", "organism_and_biotype": "Homo sapiens Huntington Disease Somatic Repeat Tract", "accession_anchor": "NM_002111.8", "length_bp": 768, "is_negative_control": false, "native_shannon_h1_bits": 1.7074, "native_shannon_h3_bits": 2.5186, "native_shannon_h6_bits": 2.6298, "native_entropy_rate_h6_per_base": 0.4383, "native_lz76_phrases": 22, "native_lz76_normalized": 0.1373, "native_lz76_ncd": 0.16, "native_dfa_alpha": 0.2142, "native_hurst_h": 0.4207, "native_regime": "PathogenicOrTelomericTandemRepeatExpansion", "scipy_shannon_h1_bits": 1.7074, "scipy_shannon_h3_bits": 2.5186, "scipy_shannon_h6_bits": 2.6298, "scipy_entropy_rate_h6_per_base": 0.4383, "scipy_lz76_phrases": 22, "scipy_lz76_normalized": 0.1373, "scipy_lz76_ncd": 0.16, "scipy_dfa_alpha": 0.2142, "scipy_hurst_h": 0.4207, "scipy_regime": "PathogenicOrTelomericTandemRepeatExpansion", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "DEV-04", "split": "Development", "locus_label": "rpoB Rifampicin-Resistance Determining Region (RRDR)", "organism_and_biotype": "Escherichia coli K-12 vs. Salmonella enterica Coding Operon", "accession_anchor": "NC_000913.3 / NC_003197.2", "length_bp": 768, "is_negative_control": false, "native_shannon_h1_bits": 1.9435, "native_shannon_h3_bits": 5.5583, "native_shannon_h6_bits": 8.8857, "native_entropy_rate_h6_per_base": 1.481, "native_lz76_phrases": 140, "native_lz76_normalized": 0.8736, "native_lz76_ncd": 0.2774, "native_dfa_alpha": 0.5147, "native_hurst_h": 0.5491, "native_regime": "HighComplexityCodingExon", "scipy_shannon_h1_bits": 1.9435, "scipy_shannon_h3_bits": 5.5583, "scipy_shannon_h6_bits": 8.8857, "scipy_entropy_rate_h6_per_base": 1.481, "scipy_lz76_phrases": 140, "scipy_lz76_normalized": 0.8736, "scipy_lz76_ncd": 0.2774, "scipy_dfa_alpha": 0.5147, "scipy_hurst_h": 0.5491, "scipy_regime": "HighComplexityCodingExon", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "DEV-05", "split": "Development", "locus_label": "AGRN Promoter CpG/G4 Regulatory Isochore (Chr1p36.33)", "organism_and_biotype": "Homo sapiens Subtelomeric Non-B Regulatory Chromatin", "accession_anchor": "NC_000001.11", "length_bp": 768, "is_negative_control": false, "native_shannon_h1_bits": 1.9991, "native_shannon_h3_bits": 5.834, "native_shannon_h6_bits": 9.2632, "native_entropy_rate_h6_per_base": 1.5439, "native_lz76_phrases": 155, "native_lz76_normalized": 0.9672, "native_lz76_ncd": 0.2258, "native_dfa_alpha": 0.7691, "native_hurst_h": 0.6531, "native_regime": "LongRangeCorrelatedIntronOrIsochore", "scipy_shannon_h1_bits": 1.9991, "scipy_shannon_h3_bits": 5.834, "scipy_shannon_h6_bits": 9.2632, "scipy_entropy_rate_h6_per_base": 1.5439, "scipy_lz76_phrases": 155, "scipy_lz76_normalized": 0.9672, "scipy_lz76_ncd": 0.2258, "scipy_dfa_alpha": 0.7691, "scipy_hurst_h": 0.6531, "scipy_regime": "LongRangeCorrelatedIntronOrIsochore", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "DEV-06", "split": "Development", "locus_label": "Poly-(A)/(AT)n Homopolymer Artifact Window (0🧪 Control)", "organism_and_biotype": "Low-Complexity Sequencing Homopolymer & Dinucleotide Artifact", "accession_anchor": "CALIBRATION-HOMOPOLYMER-NULL-01", "length_bp": 768, "is_negative_control": true, "native_shannon_h1_bits": 0.6378, "native_shannon_h3_bits": 1.5767, "native_shannon_h6_bits": 2.562, "native_entropy_rate_h6_per_base": 0.427, "native_lz76_phrases": 5, "native_lz76_normalized": 0.0312, "native_lz76_ncd": 0.5714, "native_dfa_alpha": 0.3736, "native_hurst_h": 0.2321, "native_regime": "HomopolymerOrDinucleotideLowComplexityArtifactReject", "scipy_shannon_h1_bits": 0.6378, "scipy_shannon_h3_bits": 1.5767, "scipy_shannon_h6_bits": 2.562, "scipy_entropy_rate_h6_per_base": 0.427, "scipy_lz76_phrases": 5, "scipy_lz76_normalized": 0.0312, "scipy_lz76_ncd": 0.5714, "scipy_dfa_alpha": 0.3736, "scipy_hurst_h": 0.2321, "scipy_regime": "HomopolymerOrDinucleotideLowComplexityArtifactReject", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "RES-01", "split": "UntouchedReserve", "locus_label": "BRCA1 Exon 11 RAD51-Binding Coding Region (17q21.31)", "organism_and_biotype": "Homo sapiens vs. Gorilla gorilla Protein-Coding Exon", "accession_anchor": "NM_007294.4 / XM_004058784.3", "length_bp": 768, "is_negative_control": false, "native_shannon_h1_bits": 1.9417, "native_shannon_h3_bits": 5.5697, "native_shannon_h6_bits": 8.8066, "native_entropy_rate_h6_per_base": 1.4678, "native_lz76_phrases": 139, "native_lz76_normalized": 0.8674, "native_lz76_ncd": 0.1986, "native_dfa_alpha": 0.5787, "native_hurst_h": 0.503, "native_regime": "HighComplexityCodingExon", "scipy_shannon_h1_bits": 1.9417, "scipy_shannon_h3_bits": 5.5697, "scipy_shannon_h6_bits": 8.8066, "scipy_entropy_rate_h6_per_base": 1.4678, "scipy_lz76_phrases": 139, "scipy_lz76_normalized": 0.8674, "scipy_lz76_ncd": 0.1986, "scipy_dfa_alpha": 0.5787, "scipy_hurst_h": 0.503, "scipy_regime": "HighComplexityCodingExon", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "RES-02", "split": "UntouchedReserve", "locus_label": "DMD Dystrophin Giant Intron 44 Breakpoint Region (Xp21.2)", "organism_and_biotype": "Homo sapiens Intron-Rich Long-Range Correlated Domain", "accession_anchor": "NG_012232.1", "length_bp": 768, "is_negative_control": false, "native_shannon_h1_bits": 1.9993, "native_shannon_h3_bits": 5.8319, "native_shannon_h6_bits": 9.2477, "native_entropy_rate_h6_per_base": 1.5413, "native_lz76_phrases": 156, "native_lz76_normalized": 0.9735, "native_lz76_ncd": 0.2051, "native_dfa_alpha": 0.7856, "native_hurst_h": 0.6182, "native_regime": "LongRangeCorrelatedIntronOrIsochore", "scipy_shannon_h1_bits": 1.9993, "scipy_shannon_h3_bits": 5.8319, "scipy_shannon_h6_bits": 9.2477, "scipy_entropy_rate_h6_per_base": 1.5413, "scipy_lz76_phrases": 156, "scipy_lz76_normalized": 0.9735, "scipy_lz76_ncd": 0.2051, "scipy_dfa_alpha": 0.7856, "scipy_hurst_h": 0.6182, "scipy_regime": "LongRangeCorrelatedIntronOrIsochore", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "RES-03", "split": "UntouchedReserve", "locus_label": "C9orf72 Intron 1 (GGGGCC)n Hexanucleotide Expansion (9p21.2)", "organism_and_biotype": "Homo sapiens ALS/FTD Pathogenic Repeat Expansion", "accession_anchor": "NG_031977.1", "length_bp": 768, "is_negative_control": false, "native_shannon_h1_bits": 1.1697, "native_shannon_h3_bits": 2.956, "native_shannon_h6_bits": 3.4915, "native_entropy_rate_h6_per_base": 0.5819, "native_lz76_phrases": 20, "native_lz76_normalized": 0.1248, "native_lz76_ncd": 0.1739, "native_dfa_alpha": 0.1633, "native_hurst_h": 0.224, "native_regime": "PathogenicOrTelomericTandemRepeatExpansion", "scipy_shannon_h1_bits": 1.1697, "scipy_shannon_h3_bits": 2.956, "scipy_shannon_h6_bits": 3.4915, "scipy_entropy_rate_h6_per_base": 0.5819, "scipy_lz76_phrases": 20, "scipy_lz76_normalized": 0.1248, "scipy_lz76_ncd": 0.1739, "scipy_dfa_alpha": 0.1633, "scipy_hurst_h": 0.224, "scipy_regime": "PathogenicOrTelomericTandemRepeatExpansion", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "RES-04", "split": "UntouchedReserve", "locus_label": "Cetacean Mitochondrial COX1 Barcode Core (mtDNA)", "organism_and_biotype": "Balaenoptera musculus vs. Physeter catodon Coding mtDNA", "accession_anchor": "NC_001601.1 / NC_002503.2", "length_bp": 768, "is_negative_control": false, "native_shannon_h1_bits": 1.9648, "native_shannon_h3_bits": 5.6187, "native_shannon_h6_bits": 8.8271, "native_entropy_rate_h6_per_base": 1.4712, "native_lz76_phrases": 133, "native_lz76_normalized": 0.8299, "native_lz76_ncd": 0.3819, "native_dfa_alpha": 0.5446, "native_hurst_h": 0.5996, "native_regime": "HighComplexityCodingExon", "scipy_shannon_h1_bits": 1.9648, "scipy_shannon_h3_bits": 5.6187, "scipy_shannon_h6_bits": 8.8271, "scipy_entropy_rate_h6_per_base": 1.4712, "scipy_lz76_phrases": 133, "scipy_lz76_normalized": 0.8299, "scipy_lz76_ncd": 0.3819, "scipy_dfa_alpha": 0.5446, "scipy_hurst_h": 0.5996, "scipy_regime": "HighComplexityCodingExon", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "RES-05", "split": "UntouchedReserve", "locus_label": "Chr1pTER Canonical (TTAGGG)n Telomeric Repeat Array", "organism_and_biotype": "Homo sapiens Subtelomeric Shelterin Repeat Tract", "accession_anchor": "NC_000001.11 (Telomeric T2T-CHM13)", "length_bp": 768, "is_negative_control": false, "native_shannon_h1_bits": 1.6299, "native_shannon_h3_bits": 3.3234, "native_shannon_h6_bits": 3.5214, "native_entropy_rate_h6_per_base": 0.5869, "native_lz76_phrases": 23, "native_lz76_normalized": 0.1435, "native_lz76_ncd": 0.1538, "native_dfa_alpha": 0.1919, "native_hurst_h": 0.2966, "native_regime": "PathogenicOrTelomericTandemRepeatExpansion", "scipy_shannon_h1_bits": 1.6299, "scipy_shannon_h3_bits": 3.3234, "scipy_shannon_h6_bits": 3.5214, "scipy_entropy_rate_h6_per_base": 0.5869, "scipy_lz76_phrases": 23, "scipy_lz76_normalized": 0.1435, "scipy_lz76_ncd": 0.1538, "scipy_dfa_alpha": 0.1919, "scipy_hurst_h": 0.2966, "scipy_regime": "PathogenicOrTelomericTandemRepeatExpansion", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true }, { "cohort_id": "RES-06", "split": "UntouchedReserve", "locus_label": "Memoryless I.I.D. Bernoulli White-Noise Decoy (0🧪 Control)", "organism_and_biotype": "Uncorrelated Maximum-Entropy Uniform Pseudorandom Control", "accession_anchor": "CALIBRATION-IID-WHITENOISE-02", "length_bp": 768, "is_negative_control": true, "native_shannon_h1_bits": 1.9964, "native_shannon_h3_bits": 5.942, "native_shannon_h6_bits": 9.3884, "native_entropy_rate_h6_per_base": 1.5647, "native_lz76_phrases": 156, "native_lz76_normalized": 0.9735, "native_lz76_ncd": 0.8205, "native_dfa_alpha": 0.5751, "native_hurst_h": 0.5315, "native_regime": "MemorylessIIDBernoulliWhiteNoiseControlReject", "scipy_shannon_h1_bits": 1.9964, "scipy_shannon_h3_bits": 5.942, "scipy_shannon_h6_bits": 9.3884, "scipy_entropy_rate_h6_per_base": 1.5647, "scipy_lz76_phrases": 156, "scipy_lz76_normalized": 0.9735, "scipy_lz76_ncd": 0.8205, "scipy_dfa_alpha": 0.5751, "scipy_hurst_h": 0.5315, "scipy_regime": "MemorylessIIDBernoulliWhiteNoiseControlReject", "abs_diff_shannon_h3": 0.0, "abs_diff_shannon_h6": 0.0, "abs_diff_lz76_norm": 0.0, "abs_diff_lz76_ncd": 0.0, "abs_diff_dfa_alpha": 0.0, "abs_diff_hurst_h": 0.0, "regime_concordant": true } ], "ascii_summary_chart": "==============================================================================================================\n SLIDING-WINDOW K-MER SHANNON ENTROPY (H1..H6), LZ76 NCD & FRACTAL DNA WALK DFA CALIBRATION (VAL-SET-021)\n==============================================================================================================\n Cohort Split Locus / Genomic Element H3(b) H6(b) c_LZ NCD DFA_a Hurst Regime\n ------------------------------------------------------------------------------------------------------------\n DEV-01 DEV TP53 Exons 5–8 DNA-Binding Do 5.5631 8.8714 0.8799 0.1736 0.5104 0.4668 HighComplexityCodingExon\n DEV-02 DEV HBB Beta-Globin Intron 2 & 3' 5.7728 9.2333 0.9610 0.1818 0.7661 0.6015 LongRangeCorrelatedIntronOrIsochore\n DEV-03 DEV HTT Exon 1 Pathogenic (CAG)n 2.5186 2.6298 0.1373 0.1600 0.2142 0.4207 PathogenicOrTelomericTandemRepeatExpansion\n DEV-04 DEV rpoB Rifampicin-Resistance De 5.5583 8.8857 0.8736 0.2774 0.5147 0.5491 HighComplexityCodingExon\n DEV-05 DEV AGRN Promoter CpG/G4 Regulato 5.8340 9.2632 0.9672 0.2258 0.7691 0.6531 LongRangeCorrelatedIntronOrIsochore\n DEV-06 DEV Poly-(A)/(AT)n Homopolymer Ar 1.5767 2.5620 0.0312 0.5714 0.3736 0.2321 HomopolymerOrDinucleotideLowComplexityArtifactReject\n RES-01 RESERVE BRCA1 Exon 11 RAD51-Binding C 5.5697 8.8066 0.8674 0.1986 0.5787 0.5030 HighComplexityCodingExon\n RES-02 RESERVE DMD Dystrophin Giant Intron 4 5.8319 9.2477 0.9735 0.2051 0.7856 0.6182 LongRangeCorrelatedIntronOrIsochore\n RES-03 RESERVE C9orf72 Intron 1 (GGGGCC)n He 2.9560 3.4915 0.1248 0.1739 0.1633 0.2240 PathogenicOrTelomericTandemRepeatExpansion\n RES-04 RESERVE Cetacean Mitochondrial COX1 B 5.6187 8.8271 0.8299 0.3819 0.5446 0.5996 HighComplexityCodingExon\n RES-05 RESERVE Chr1pTER Canonical (TTAGGG)n 3.3234 3.5214 0.1435 0.1538 0.1919 0.2966 PathogenicOrTelomericTandemRepeatExpansion\n RES-06 RESERVE Memoryless I.I.D. Bernoulli W 5.9420 9.3884 0.9735 0.8205 0.5751 0.5315 MemorylessIIDBernoulliWhiteNoiseControlReject\n==============================================================================================================\n" }