{
  "meta": {
    "name": "bioflow flow_docs 评估集",
    "version": 1,
    "total": 50,
    "criteria": [
      "每条含 1-2 个黄金断言（golds，真实语料关键词）",
      "stage_keyword / source_required 驱动检索口径断言（答案需含对应 stage/来源的引用块）",
      "hit 判定 = 检索条目命中（主条 source == source_required 且 stage/主题匹配，或仅 source 匹配的兜底）",
      "quote 判定 = top5 条目正文拼接后包含全部 golds",
      "bypass = 原文逐字黄金词（检索必全中），属检索底线自查而非代表检索质量"
    ],
    "scoring": {
      "hit": "检索命中（口径断言）",
      "quote": "引用原文包含黄金断言",
      "pass": "hit 且 quote"
    }
  },
  "categories": {
    "gf_stage_io": "基因家族阶段输入输出",
    "rnaseq_stage_io": "RNA-seq 阶段输入输出",
    "wgs_stage_io": "WGS 阶段输入输出",
    "pop_gwas_io": "群体遗传/GWAS 阶段输入输出",
    "params": "默认参数与阈值",
    "preconditions": "前置条件与依赖链",
    "software": "软件对照（附加入库源的差异化价值）",
    "delivery": "质控/交付与整体咨询"
  },
  "items": [
    {
      "id": 1,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "identify 阶段需要什么输入？",
      "stage_keyword": "identify",
      "source_required": "corpus",
      "golds": [
        "Pfam HMM",
        "全蛋白"
      ]
    },
    {
      "id": 2,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "genome_prepare 输出哪些标准文件？",
      "stage_keyword": "genome_prepare",
      "source_required": "corpus",
      "golds": [
        ".gff3",
        ".cds.fasta"
      ]
    },
    {
      "id": 3,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "identify_refine 之后应该跑哪个阶段？",
      "stage_keyword": "identify_refine",
      "source_required": "corpus",
      "golds": [
        "phylogeny",
        "权威成员"
      ]
    },
    {
      "id": 4,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "phylogeny 阶段的主要输出文件是什么？",
      "stage_keyword": "phylogeny",
      "source_required": "corpus",
      "golds": [
        "MAFFT",
        ".tree.nwk"
      ]
    },
    {
      "id": 5,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "motif 分析用什么软件，输出什么？",
      "stage_keyword": "motif",
      "source_required": "corpus",
      "golds": [
        "MEME",
        "motif 表"
      ]
    },
    {
      "id": 6,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "domain 结构域注释的输入和输出文件？",
      "stage_keyword": "domain",
      "source_required": "corpus",
      "golds": [
        "Pfam",
        "domtblout"
      ]
    },
    {
      "id": 7,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "structure 阶段需要哪些输入文件？",
      "stage_keyword": "structure",
      "source_required": "corpus",
      "golds": [
        "GFF3/GTF",
        "系统树"
      ]
    },
    {
      "id": 8,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "promoter 分析的上游默认长度是多少，用什么工具？",
      "stage_keyword": "promoter",
      "source_required": "corpus",
      "golds": [
        "2000 bp",
        "PlantCARE"
      ]
    },
    {
      "id": 9,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "tfbs 阶段的输入和默认过滤阈值？",
      "stage_keyword": "tfbs",
      "source_required": "corpus",
      "golds": [
        "PlantTFDB",
        "q=0.05"
      ]
    },
    {
      "id": 10,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "synteny 共线性分析的输入文件？",
      "stage_keyword": "synteny",
      "source_required": "corpus",
      "golds": [
        "GFF3",
        "共线性区块"
      ]
    },
    {
      "id": 11,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "kaks 分析需要什么输入，输出什么？",
      "stage_keyword": "kaks",
      "source_required": "corpus",
      "golds": [
        "CDS FASTA",
        "kaks_results.csv"
      ]
    },
    {
      "id": 12,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "ppi 蛋白互作网络用什么数据库？",
      "stage_keyword": "ppi",
      "source_required": "corpus",
      "golds": [
        "STRING",
        "ppi_network.tsv"
      ]
    },
    {
      "id": 13,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "pep 阶段预测哪些蛋白性质？",
      "stage_keyword": "pep",
      "source_required": "corpus",
      "golds": [
        "ProtParam",
        "DeepTMHMM"
      ]
    },
    {
      "id": 14,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "expression 阶段两种模式分别怎么用？",
      "stage_keyword": "expression",
      "source_required": "corpus",
      "golds": [
        "TPM",
        "rnaseq_auto"
      ]
    },
    {
      "id": 15,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "gene_family_report 报告的输入来源是什么？",
      "stage_keyword": "gene_family_report",
      "source_required": "corpus",
      "golds": [
        "Manifest",
        "文件哈希"
      ]
    },
    {
      "id": 16,
      "category": "software",
      "type": "hit",
      "query": "ortholog 阶段用哪种比对方法建立目标与参考物种的映射？",
      "stage_keyword": "ortholog",
      "source_required": "stage_contract",
      "golds": [
        "BLASTP",
        "ppiReferenceStorageKey"
      ]
    },
    {
      "id": 17,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "结构域的基因结构可视化阶段对输入树文件有什么要求？",
      "stage_keyword": "structure",
      "source_required": "stage_contract",
      "golds": [
        "final_members.id",
        "系统发育树文件"
      ]
    },
    {
      "id": 18,
      "category": "gf_stage_io",
      "type": "hit",
      "query": "annotation 阶段建立什么映射关系？",
      "stage_keyword": "annotation",
      "source_required": "corpus",
      "golds": [
        "gene2go",
        "InterProScan"
      ]
    },
    {
      "id": 19,
      "category": "software",
      "type": "hit",
      "query": "identify 默认的 HMMER e-value 和覆盖度阈值是多少？",
      "stage_keyword": "identify",
      "source_required": "skill",
      "golds": [
        "1e-5",
        "0.3"
      ]
    },
    {
      "id": 20,
      "category": "software",
      "type": "hit",
      "query": "kaks 技能说明里的参数与依赖软件？",
      "stage_keyword": "kaks",
      "source_required": "skill",
      "golds": [
        "Ka/Ks",
        "yn00"
      ]
    },
    {
      "id": 21,
      "category": "rnaseq_stage_io",
      "type": "hit",
      "query": "rnaseq_qc 用什么工具清洗数据，输出什么？",
      "stage_keyword": "rnaseq_qc",
      "source_required": "corpus",
      "golds": [
        "fastp",
        "clean R1/R2"
      ]
    },
    {
      "id": 22,
      "category": "rnaseq_stage_io",
      "type": "hit",
      "query": "rnaseq_align 用什么比对软件，输入是什么？",
      "stage_keyword": "rnaseq_align",
      "source_required": "corpus",
      "golds": [
        "HISAT2",
        "链特异性"
      ]
    },
    {
      "id": 23,
      "category": "rnaseq_stage_io",
      "type": "hit",
      "query": "rnaseq_quant 定量阶段输出哪些矩阵文件？",
      "stage_keyword": "rnaseq_quant",
      "source_required": "corpus",
      "golds": [
        "featureCounts",
        "count_matrix"
      ]
    },
    {
      "id": 24,
      "category": "params",
      "type": "hit",
      "query": "DESeq2 差异表达分析的默认阈值是什么？",
      "stage_keyword": "rnaseq_de",
      "source_required": "corpus",
      "golds": [
        "log2FoldChange",
        "padj < 0.05"
      ]
    },
    {
      "id": 25,
      "category": "software",
      "type": "hit",
      "query": "KEGG 富集和 GO 富集分别用什么 R 包？",
      "stage_keyword": "rnaseq_enrich",
      "source_required": "corpus",
      "golds": [
        "clusterProfiler",
        "gene2ko"
      ]
    },
    {
      "id": 26,
      "category": "rnaseq_stage_io",
      "type": "hit",
      "query": "rnaseq_wgcna 的默认参数有哪些？",
      "stage_keyword": "rnaseq_wgcna",
      "source_required": "corpus",
      "golds": [
        "min_module_size=30",
        "soft-threshold"
      ]
    },
    {
      "id": 27,
      "category": "software",
      "type": "hit",
      "query": "fgsea 阶段需要什么全量输入文件？",
      "stage_keyword": "rnaseq_fgsea",
      "source_required": "stage_contract",
      "golds": [
        "DE_results.txt",
        "gene2ko"
      ]
    },
    {
      "id": 28,
      "category": "preconditions",
      "type": "hit",
      "query": "rnaseq_candidate_family 阶段的性质和它下游衔接什么？",
      "stage_keyword": "rnaseq_candidate_family",
      "source_required": "corpus",
      "golds": [
        "优先级",
        "identify"
      ]
    },
    {
      "id": 29,
      "category": "rnaseq_stage_io",
      "type": "hit",
      "query": "RNA-seq 样本配置文件怎么组织？",
      "stage_keyword": "rnaseq",
      "source_required": "corpus",
      "golds": [
        "samples.yaml",
        "group_role"
      ]
    },
    {
      "id": 30,
      "category": "delivery",
      "type": "hit",
      "query": "RNA-seq 报告阶段的要求是什么？",
      "stage_keyword": "rnaseq_report",
      "source_required": "corpus",
      "golds": [
        "报告",
        "Manifest"
      ]
    },
    {
      "id": 31,
      "category": "params",
      "type": "hit",
      "query": "wgs_qc 的 fastp 默认参数是什么？",
      "stage_keyword": "wgs_qc",
      "source_required": "corpus",
      "golds": [
        "length_required=50",
        "qualified_quality_phred=5"
      ]
    },
    {
      "id": 32,
      "category": "wgs_stage_io",
      "type": "hit",
      "query": "wgs_index 会生成哪些索引文件？",
      "stage_keyword": "wgs_index",
      "source_required": "corpus",
      "golds": [
        ".fai",
        ".dict"
      ]
    },
    {
      "id": 33,
      "category": "wgs_stage_io",
      "type": "hit",
      "query": "wgs_align 用什么比对软件？",
      "stage_keyword": "wgs",
      "source_required": "corpus",
      "golds": [
        "BWA-MEM2",
        "BAM"
      ]
    },
    {
      "id": 34,
      "category": "wgs_stage_io",
      "type": "hit",
      "query": "wgs_markdup 对重复 reads 做什么处理？",
      "stage_keyword": "wgs_markdup",
      "source_required": "corpus",
      "golds": [
        "remove_duplicates=true",
        "重复比例"
      ]
    },
    {
      "id": 35,
      "category": "wgs_stage_io",
      "type": "hit",
      "query": "wgs_haplotype_calling 用什么工具和模式生成 gVCF？",
      "stage_keyword": "wgs_haplotype_calling",
      "source_required": "corpus",
      "golds": [
        "HaplotypeCaller",
        "ERC=GVCF"
      ]
    },
    {
      "id": 36,
      "category": "preconditions",
      "type": "hit",
      "query": "gVCF 合并阶段的质控要求是什么？",
      "stage_keyword": "wgs_gvcf_combine",
      "source_required": "corpus",
      "golds": [
        "wgs_samples.yaml",
        "完全一致"
      ]
    },
    {
      "id": 37,
      "category": "wgs_stage_io",
      "type": "hit",
      "query": "wgs_joint_genotyping 的默认参数有哪些？",
      "stage_keyword": "wgs_joint_genotyping",
      "source_required": "corpus",
      "golds": [
        "GenotypeGVCFs",
        "替代等位基因数 6"
      ]
    },
    {
      "id": 38,
      "category": "software",
      "type": "hit",
      "query": "变异硬过滤的 SNP 默认阈值是什么？",
      "stage_keyword": "wgs_variant_filter",
      "source_required": "corpus",
      "golds": [
        "QD<2",
        "MQ<40"
      ]
    },
    {
      "id": 39,
      "category": "params",
      "type": "hit",
      "query": "wgs_impute 的 Beagle 默认参数是什么？",
      "stage_keyword": "wgs_impute",
      "source_required": "corpus",
      "golds": [
        "imp_states 1600",
        "window 40"
      ]
    },
    {
      "id": 40,
      "category": "software",
      "type": "hit",
      "query": "变异分离阶段允许用 bcftools 吗？",
      "stage_keyword": "wgs_variant_select",
      "source_required": "corpus",
      "golds": [
        "SelectVariants",
        "静默回退"
      ]
    },
    {
      "id": 41,
      "category": "pop_gwas_io",
      "type": "hit",
      "query": "群体遗传分析有哪五个阶段？",
      "stage_keyword": "pop",
      "source_required": "corpus",
      "golds": [
        "pop_pca",
        "pop_ld_decay"
      ]
    },
    {
      "id": 42,
      "category": "params",
      "type": "hit",
      "query": "pop_snp_density 的窗口大小是什么？",
      "stage_keyword": "pop_snp_density",
      "source_required": "corpus",
      "golds": [
        "1 Mb",
        "500 kb"
      ]
    },
    {
      "id": 43,
      "category": "preconditions",
      "type": "hit",
      "query": "gwas_mlm 的前置阶段有哪些？",
      "stage_keyword": "gwas_mlm",
      "source_required": "corpus",
      "golds": [
        "gwas_kinship",
        "gwas_cov"
      ]
    },
    {
      "id": 44,
      "category": "software",
      "type": "hit",
      "query": "EMMAX 分析的输出文件表头是什么？",
      "stage_keyword": "gwas_emmax",
      "source_required": "corpus",
      "golds": [
        "emmax_pvalues",
        "SNPID"
      ]
    },
    {
      "id": 45,
      "category": "preconditions",
      "type": "hit",
      "query": "GWAS 三条模型路线各是什么定位？",
      "stage_keyword": "gwas",
      "source_required": "corpus",
      "golds": [
        "MLM/CMLM",
        "EMMAX"
      ]
    },
    {
      "id": 46,
      "category": "preconditions",
      "type": "hit",
      "query": "WGS 最终 VCF 可以衔接哪些下游分析？",
      "stage_keyword": "",
      "source_required": "corpus",
      "golds": [
        "pop_pca",
        "gwas_fmt"
      ]
    },
    {
      "id": 47,
      "category": "software",
      "type": "hit",
      "query": "kinship 亲缘矩阵用什么软件计算，依赖哪个上游？",
      "stage_keyword": "gwas_kinship",
      "source_required": "stage_contract",
      "golds": [
        "TASSEL",
        "gwas_fmt"
      ]
    },
    {
      "id": 48,
      "category": "software",
      "type": "hit",
      "query": "MAFFT 和 IQ-TREE 用在哪个基因家族阶段？",
      "stage_keyword": "phylogeny",
      "source_required": "corpus",
      "golds": [
        "MAFFT",
        "IQ-TREE"
      ]
    },
    {
      "id": 49,
      "category": "delivery",
      "type": "hit",
      "query": "项目最终交付目录应该怎么组织？",
      "stage_keyword": "",
      "source_required": "corpus",
      "golds": [
        "00_input_and_design",
        "99_manifests_and_reproducibility"
      ]
    },
    {
      "id": 50,
      "category": "delivery",
      "type": "hit",
      "query": "报告中建议固定包含哪些内容？",
      "stage_keyword": "",
      "source_required": "corpus",
      "golds": [
        "SHA256",
        "软件和数据库"
      ]
    }
  ]
}