{
  "documents": [
    {
      "doc_id": "k8s-workloads-cron-jobs",
      "filename": "k8s-workloads-cron-jobs.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/workloads/controllers/cron-jobs.md",
      "doc_type": "tech_md",
      "bytes": 14124,
      "extracted_chars": 13934,
      "stresses": "YAML blocks, field tables, deep nesting",
      "markers": [
        {
          "kind": "identifier",
          "needle": "RFC3339",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "passage",
          "needle": "concurrency policy only applies to the Jobs",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "are suspended during their scheduled time count",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "database from the Go standard library is",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "Job object approximately once per execution time",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "circumstances where two Jobs might be created",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-workloads-daemonset",
      "filename": "k8s-workloads-daemonset.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/workloads/controllers/daemonset.md",
      "doc_type": "tech_md",
      "bytes": 14881,
      "extracted_chars": 14881,
      "stresses": "YAML blocks, field tables, deep nesting",
      "markers": [
        {
          "kind": "code_token",
          "needle": "RestartPolicy",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "matchLabels",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "matchExpressions",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "hostPort",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "endpoints",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "updateStrategy",
          "note": "configuration key or symbol in code formatting"
        }
      ]
    },
    {
      "doc_id": "k8s-workloads-deployment",
      "filename": "k8s-workloads-deployment.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/workloads/controllers/deployment.md",
      "doc_type": "tech_md",
      "bytes": 59640,
      "extracted_chars": 59632,
      "stresses": "YAML blocks, field tables, deep nesting",
      "markers": [
        {
          "kind": "code_token",
          "needle": "operator",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "terminationGracePeriodSeconds",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "ReplicaSetCreateError",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "table_cell",
          "needle": "512Mi",
          "note": "quantity with a unit, typically a setting"
        },
        {
          "kind": "body_text",
          "needle": "Ctrl-C",
          "note": "rare compound proper noun"
        },
        {
          "kind": "passage",
          "needle": "rolls out changes to your application or",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-workloads-replicaset",
      "filename": "k8s-workloads-replicaset.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/workloads/controllers/replicaset.md",
      "doc_type": "tech_md",
      "bytes": 19303,
      "extracted_chars": 19303,
      "stresses": "YAML blocks, field tables, deep nesting",
      "markers": [
        {
          "kind": "code_token",
          "needle": "Background",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "PodDeletionCost",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "body_text",
          "needle": "Non-Template",
          "note": "rare compound proper noun"
        },
        {
          "kind": "passage",
          "needle": "create to meet the number of replicas",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "Pods as needed to reach the desired",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "specifies what resource the current object is",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-workloads-replicationcontroller",
      "filename": "k8s-workloads-replicationcontroller.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/workloads/controllers/replicationcontroller.md",
      "doc_type": "tech_md",
      "bytes": 18779,
      "extracted_chars": 18779,
      "stresses": "YAML blocks, field tables, deep nesting",
      "markers": [
        {
          "kind": "passage",
          "needle": "ReplicationController config runs three copies of the",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "the ReplicationController to be replaced without affecting",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "is designed to facilitate rolling updates to",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "updates the set of pods regardless of",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "rolling update controller would take application readiness",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "ReplicationControllers would need to create pods with",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-config-configmap",
      "filename": "k8s-config-configmap.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/configuration/configmap.md",
      "doc_type": "tech_md",
      "bytes": 12932,
      "extracted_chars": 12932,
      "stresses": "configuration keys and defaults",
      "markers": [
        {
          "kind": "code_token",
          "needle": "DATABASE_HOST",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "localhost",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "configMapAndSecretChangeDetectionStrategy",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "configMapRef",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "env.valueFrom",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "body_text",
          "needle": "Twelve-Factor",
          "note": "rare compound proper noun"
        }
      ]
    },
    {
      "doc_id": "k8s-config-manage-resources-containers",
      "filename": "k8s-config-manage-resources-containers.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/configuration/manage-resources-containers.md",
      "doc_type": "tech_md",
      "bytes": 33492,
      "extracted_chars": 33488,
      "stresses": "configuration keys and defaults",
      "markers": [
        {
          "kind": "table_cell",
          "needle": "0.001",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "0.005",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "0.0005",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "1.120",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "10.240",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "10.244",
          "note": "high-precision decimal"
        }
      ]
    },
    {
      "doc_id": "k8s-config-organize-cluster-access-kubeconfig",
      "filename": "k8s-config-organize-cluster-access-kubeconfig.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/configuration/organize-cluster-access-kubeconfig.md",
      "doc_type": "tech_md",
      "bytes": 6900,
      "extracted_chars": 6900,
      "stresses": "configuration keys and defaults",
      "markers": [
        {
          "kind": "passage",
          "needle": "kubeconfig file could result in malicious code",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "cluster information attributes exist from the merged",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-config-secret",
      "filename": "k8s-config-secret.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/configuration/secret.md",
      "doc_type": "tech_md",
      "bytes": 32981,
      "extracted_chars": 32981,
      "stresses": "configuration keys and defaults",
      "markers": [
        {
          "kind": "identifier",
          "needle": "RFC3339",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "code_token",
          "needle": "dotfile-test-container",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "automountServiceAccountToken",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "serviceAccountName",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "ssh-privatekey",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "known_hosts",
          "note": "configuration key or symbol in code formatting"
        }
      ]
    },
    {
      "doc_id": "cncf-kubeweekly",
      "filename": "cncf-kubeweekly.md",
      "source_url": "https://raw.githubusercontent.com/cncf/foundation/main/KubeWeekly.md",
      "doc_type": "policy_md",
      "bytes": 2079,
      "extracted_chars": 2079,
      "stresses": "charters and policies, the shape of a company policy page",
      "markers": [
        {
          "kind": "passage",
          "needle": "events shared in KubeWeekly are the CNCF",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "cncf-readme",
      "filename": "cncf-readme.md",
      "source_url": "https://raw.githubusercontent.com/cncf/foundation/main/README.md",
      "doc_type": "policy_md",
      "bytes": 2088,
      "extracted_chars": 2079,
      "stresses": "charters and policies, the shape of a company policy page",
      "markers": [
        {
          "kind": "passage",
          "needle": "information on all programs offered publicly by",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "project maintainer can update this list by",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "cncf-charter",
      "filename": "cncf-charter.md",
      "source_url": "https://raw.githubusercontent.com/cncf/foundation/main/charter.md",
      "doc_type": "policy_md",
      "bytes": 35623,
      "extracted_chars": 35553,
      "stresses": "charters and policies, the shape of a company policy page",
      "markers": [
        {
          "kind": "passage",
          "needle": "mission is to make cloud native computing",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "technologies empower organizations to build and run",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "enable loosely coupled systems that are resilient",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "Native Computing Foundation seeks to drive adoption",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "state-of-the-art patterns to make these innovations accessible",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "community by making the technology accessible and",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "cncf-cncf-membership-guide",
      "filename": "cncf-cncf-membership-guide.md",
      "source_url": "https://raw.githubusercontent.com/cncf/foundation/main/cncf-membership-guide.md",
      "doc_type": "policy_md",
      "bytes": 9742,
      "extracted_chars": 9742,
      "stresses": "charters and policies, the shape of a company policy page",
      "markers": [
        {
          "kind": "passage",
          "needle": "this CNCF Membership Engagement Guide to help",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "new member or want to improve your",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "team to manage your CNCF engagement ensures",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "measurable goals allows you to focus your",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "organization's visibility within the CNCF community can",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "your team's cloud native skills demonstrates your",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "gh-security-about-anonymized-urls",
      "filename": "gh-security-about-anonymized-urls.md",
      "source_url": "https://raw.githubusercontent.com/github/docs/main/content/authentication/keeping-your-account-and-data-secure/about-anonymized-urls.md",
      "doc_type": "process_md",
      "bytes": 5265,
      "extracted_chars": 5265,
      "stresses": "security procedure documentation",
      "markers": [
        {
          "kind": "passage",
          "needle": "an anonymous URL proxy for each file",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "get anonymized URLs with the same format",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "request to Camo to add your content",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "gh-security-about-authentication-to-github",
      "filename": "gh-security-about-authentication-to-github.md",
      "source_url": "https://raw.githubusercontent.com/github/docs/main/content/authentication/keeping-your-account-and-data-secure/about-authentication-to-github.md",
      "doc_type": "process_md",
      "bytes": 17634,
      "extracted_chars": 17634,
      "stresses": "security procedure documentation",
      "markers": [
        {
          "kind": "code_token",
          "needle": "github_pat_",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "passage",
          "needle": "also use two-factor authentication and SAML single",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "leave the check up period by successfully",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "can access resources owned by an organization",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "of authenticating is determined based on whether",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "outlines the available authentication methods based on",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "gh-security-about-githubs-ip-addresses",
      "filename": "gh-security-about-githubs-ip-addresses.md",
      "source_url": "https://raw.githubusercontent.com/github/docs/main/content/authentication/keeping-your-account-and-data-secure/about-githubs-ip-addresses.md",
      "doc_type": "process_md",
      "bytes": 2639,
      "extracted_chars": 2639,
      "stresses": "security procedure documentation",
      "markers": [
        {
          "kind": "passage",
          "needle": "changes to our IP addresses from time",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "gh-security-managing-your-personal-access-tokens",
      "filename": "gh-security-managing-your-personal-access-tokens.md",
      "source_url": "https://raw.githubusercontent.com/github/docs/main/content/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens.md",
      "doc_type": "process_md",
      "bytes": 30393,
      "extracted_chars": 30385,
      "stresses": "security procedure documentation",
      "markers": [
        {
          "kind": "code_token",
          "needle": "admin:org",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "internal",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "GITHUB_TOKEN",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "metadata:read",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "codespaces_user_secrets",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "copilot_messages",
          "note": "configuration key or symbol in code formatting"
        }
      ]
    },
    {
      "doc_id": "k8s-security-api-server-bypass-risks",
      "filename": "k8s-security-api-server-bypass-risks.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/security/api-server-bypass-risks.md",
      "doc_type": "policy_md",
      "bytes": 8772,
      "extracted_chars": 8772,
      "stresses": "security policy and standards prose",
      "markers": [
        {
          "kind": "passage",
          "needle": "API can be configured to authenticate requests",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "anonymous access doesn't make this assertion with",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "the etcd API is typically managed by",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "rights by accessing cluster secrets or modifying",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "only used for health checking can also",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "this socket can launch new containers or",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-security-application-security-checklist",
      "filename": "k8s-security-application-security-checklist.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/security/application-security-checklist.md",
      "doc_type": "policy_md",
      "bytes": 6567,
      "extracted_chars": 6567,
      "stresses": "security policy and standards prose",
      "markers": [
        {
          "kind": "code_token",
          "needle": "automountServiceAccountToken",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "runAsUser",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "runAsGroup",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "system:unauthenticated",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "runtimeClassName",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "body_text",
          "needle": "Security-Context",
          "note": "rare compound proper noun"
        }
      ]
    },
    {
      "doc_id": "k8s-security-cloud-native-security",
      "filename": "k8s-security-cloud-native-security.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/security/cloud-native-security.md",
      "doc_type": "policy_md",
      "bytes": 11701,
      "extracted_chars": 11697,
      "stresses": "security policy and standards prose",
      "markers": [
        {
          "kind": "passage",
          "needle": "security of the supply chain for container",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "different trust contexts run on separate sets",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "your cluster provides an appropriate level of",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "which helps ensure the fidelity of logs",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-security-controlling-access",
      "filename": "k8s-security-controlling-access.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/security/controlling-access.md",
      "doc_type": "policy_md",
      "bytes": 8373,
      "extracted_chars": 8371,
      "stresses": "security policy and standards prose",
      "markers": [
        {
          "kind": "code_token",
          "needle": "projectFish",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "passage",
          "needle": "provides an overview of controlling access to",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "modules are software modules that can modify",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-security-linux-kernel-security-constraints",
      "filename": "k8s-security-linux-kernel-security-constraints.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/security/linux-kernel-security-constraints.md",
      "doc_type": "policy_md",
      "bytes": 14833,
      "extracted_chars": 14833,
      "stresses": "security policy and standards prose",
      "markers": [
        {
          "kind": "identifier",
          "needle": "CVE-2019-5736",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "code_token",
          "needle": "allowPrivilegeEscalation",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "Unconfined",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "unconfined_t",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "CAP_SYS_ADMIN",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "CAP_NET_ADMIN",
          "note": "configuration key or symbol in code formatting"
        }
      ]
    },
    {
      "doc_id": "k8s-storage-dynamic-provisioning",
      "filename": "k8s-storage-dynamic-provisioning.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/storage/dynamic-provisioning.md",
      "doc_type": "tech_md",
      "bytes": 5125,
      "extracted_chars": 5125,
      "stresses": "parameter tables and provisioning options",
      "markers": [
        {
          "kind": "body_text",
          "needle": "Multi-Zone",
          "note": "rare compound proper noun"
        },
        {
          "kind": "body_text",
          "needle": "Single-Zone",
          "note": "rare compound proper noun"
        },
        {
          "kind": "passage",
          "needle": "provisioning allows storage volumes to be created",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "passed to that provisioner when dynamic provisioning",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-storage-ephemeral-storage",
      "filename": "k8s-storage-ephemeral-storage.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/storage/ephemeral-storage.md",
      "doc_type": "tech_md",
      "bytes": 12793,
      "extracted_chars": 12793,
      "stresses": "parameter tables and provisioning options",
      "markers": [
        {
          "kind": "code_token",
          "needle": "UserNamespacesSupport",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "table_cell",
          "needle": "123Mi",
          "note": "quantity with a unit, typically a setting"
        },
        {
          "kind": "table_cell",
          "needle": "400Mi",
          "note": "quantity with a unit, typically a setting"
        },
        {
          "kind": "passage",
          "needle": "sets the resource quota for ephemeral-storage in",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "to specify limits for the ephemeral-storage resource",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "filesystem does not hold any image layers",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-storage-ephemeral-volumes",
      "filename": "k8s-storage-ephemeral-volumes.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/storage/ephemeral-volumes.md",
      "doc_type": "tech_md",
      "bytes": 11617,
      "extracted_chars": 11617,
      "stresses": "parameter tables and provisioning options",
      "markers": [
        {
          "kind": "code_token",
          "needle": "volumeLifecycleModes",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "WaitForFirstConsumer",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "my-app-scratch-volume",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "passage",
          "needle": "be exposed to users through the use",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "k8s-storage-persistent-volumes",
      "filename": "k8s-storage-persistent-volumes.md",
      "source_url": "https://raw.githubusercontent.com/kubernetes/website/main/content/en/docs/concepts/storage/persistent-volumes.md",
      "doc_type": "tech_md",
      "bytes": 51240,
      "extracted_chars": 51238,
      "stresses": "parameter tables and provisioning options",
      "markers": [
        {
          "kind": "table_cell",
          "needle": "192.168",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "10.100",
          "note": "high-precision decimal"
        },
        {
          "kind": "identifier",
          "needle": "192.168.10",
          "note": "version string"
        },
        {
          "kind": "identifier",
          "needle": "172.17.0",
          "note": "version string"
        },
        {
          "kind": "code_token",
          "needle": "RequiresFSResize",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "awsElasticBlockStore",
          "note": "configuration key or symbol in code formatting"
        }
      ]
    },
    {
      "doc_id": "gh-repo-managing-github-actions-settings-for-a-repository",
      "filename": "gh-repo-managing-github-actions-settings-for-a-repository.md",
      "source_url": "https://raw.githubusercontent.com/github/docs/main/content/repositories/managing-your-repositorys-settings-and-features/enabling-features-for-your-repository/managing-github-actions-settings-for-a-repository.md",
      "doc_type": "process_md",
      "bytes": 15784,
      "extracted_chars": 15784,
      "stresses": "product procedure with settings references",
      "markers": [
        {
          "kind": "code_token",
          "needle": "contents",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "code_token",
          "needle": "packages",
          "note": "configuration key or symbol in code formatting"
        },
        {
          "kind": "passage",
          "needle": "setting overrides the configuration set at the",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "configure cache retention and size settings for",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "The number of days to retain caches",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "gh-repo-managing-security-and-analysis-settings-for-your-repository",
      "filename": "gh-repo-managing-security-and-analysis-settings-for-your-repository.md",
      "source_url": "https://raw.githubusercontent.com/github/docs/main/content/repositories/managing-your-repositorys-settings-and-features/enabling-features-for-your-repository/managing-security-and-analysis-settings-for-your-repository.md",
      "doc_type": "process_md",
      "bytes": 7455,
      "extracted_chars": 7455,
      "stresses": "product procedure with settings references",
      "markers": [
        {
          "kind": "passage",
          "needle": "give additional teams and people access to",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "rfc-8259",
      "filename": "rfc-8259.txt",
      "source_url": "https://www.rfc-editor.org/rfc/rfc8259.txt",
      "doc_type": "spec_text",
      "bytes": 28360,
      "extracted_chars": 28360,
      "stresses": "numbered sections, ASCII diagrams, no markup",
      "markers": [
        {
          "kind": "table_cell",
          "needle": "3.141592653589793238462643383279",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "37.7668",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "122.3959",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "37.371991",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "122.026020",
          "note": "high-precision decimal"
        },
        {
          "kind": "identifier",
          "needle": "RFC 7841",
          "note": "specification or advisory identifier"
        }
      ]
    },
    {
      "doc_id": "rfc-7519",
      "filename": "rfc-7519.txt",
      "source_url": "https://www.rfc-editor.org/rfc/rfc7519.txt",
      "doc_type": "spec_text",
      "bytes": 63039,
      "extracted_chars": 63039,
      "stresses": "numbered sections, ASCII diagrams, no markup",
      "markers": [
        {
          "kind": "identifier",
          "needle": "RFC 5741",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 7518",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC7518",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 7516",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC7516",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 7515",
          "note": "specification or advisory identifier"
        }
      ]
    },
    {
      "doc_id": "rfc-6455",
      "filename": "rfc-6455.txt",
      "source_url": "https://www.rfc-editor.org/rfc/rfc6455.txt",
      "doc_type": "spec_text",
      "bytes": 162067,
      "extracted_chars": 162067,
      "stresses": "numbered sections, ASCII diagrams, no markup",
      "markers": [
        {
          "kind": "identifier",
          "needle": "RFC 5741",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 1928",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 2119",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 2818",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 3629",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 3864",
          "note": "specification or advisory identifier"
        }
      ]
    },
    {
      "doc_id": "rfc-7232",
      "filename": "rfc-7232.txt",
      "source_url": "https://www.rfc-editor.org/rfc/rfc7232.txt",
      "doc_type": "spec_text",
      "bytes": 56696,
      "extracted_chars": 56696,
      "stresses": "numbered sections, ASCII diagrams, no markup",
      "markers": [
        {
          "kind": "identifier",
          "needle": "RFC 5741",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 2119",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 5234",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 7230",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 7231",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 7233",
          "note": "specification or advisory identifier"
        }
      ]
    },
    {
      "doc_id": "rfc-6265",
      "filename": "rfc-6265.txt",
      "source_url": "https://www.rfc-editor.org/rfc/rfc6265.txt",
      "doc_type": "spec_text",
      "bytes": 79724,
      "extracted_chars": 79724,
      "stresses": "numbered sections, ASCII diagrams, no markup",
      "markers": [
        {
          "kind": "table_cell",
          "needle": "1455770.1455782",
          "note": "high-precision decimal"
        },
        {
          "kind": "identifier",
          "needle": "RFC 5741",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 1034",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 1123",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 2119",
          "note": "specification or advisory identifier"
        },
        {
          "kind": "identifier",
          "needle": "RFC 2616",
          "note": "specification or advisory identifier"
        }
      ]
    },
    {
      "doc_id": "irs-fw9",
      "filename": "irs-fw9.pdf",
      "source_url": "https://www.irs.gov/pub/irs-pdf/fw9.pdf",
      "doc_type": "scanned_pdf",
      "bytes": 140815,
      "extracted_chars": 53586,
      "stresses": "form layout, boxed fields",
      "markers": [
        {
          "kind": "table_cell",
          "needle": "1.1441",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "1.897",
          "note": "high-precision decimal"
        },
        {
          "kind": "passage",
          "needle": "related to the purpose of Form W-",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "appropriate box for federal tax classification of",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "this is generally your social security number",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "Give the Requester for guidelines on whose",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "irs-fw4",
      "filename": "irs-fw4.pdf",
      "source_url": "https://www.irs.gov/pub/irs-pdf/fw4.pdf",
      "doc_type": "scanned_pdf",
      "bytes": 208845,
      "extracted_chars": 35550,
      "stresses": "worksheet layout",
      "markers": [
        {
          "kind": "table_cell",
          "needle": "0.075",
          "note": "high-precision decimal"
        },
        {
          "kind": "table_cell",
          "needle": "0.005",
          "note": "high-precision decimal"
        },
        {
          "kind": "passage",
          "needle": "amount of withholding depends on income earned",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "additional tax you want withheld each pay",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "are to the Internal Revenue Code unless",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "latest information about developments related to Form",
          "note": "distinctive phrase from running prose"
        }
      ]
    },
    {
      "doc_id": "irs-f1040",
      "filename": "irs-f1040.pdf",
      "source_url": "https://www.irs.gov/pub/irs-pdf/f1040.pdf",
      "doc_type": "scanned_pdf",
      "bytes": 220237,
      "extracted_chars": 20668,
      "stresses": "dense form grid",
      "markers": [
        {
          "kind": "table_cell",
          "needle": "301.9100",
          "note": "high-precision decimal"
        },
        {
          "kind": "passage",
          "needle": "Household employee wages not reported on Form",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "Medicaid waiver payments not reported on Form",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "elect to use the lump-sum election method",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "are married filing separately and lived apart",
          "note": "distinctive phrase from running prose"
        },
        {
          "kind": "passage",
          "needle": "tax credit or credit for other dependents",
          "note": "distinctive phrase from running prose"
        }
      ]
    }
  ],
  "skipped": [
    {
      "doc_id": "cncf-cncf-marketing-committee-chair",
      "reason": "cncf-cncf-marketing-committee-chair: no unambiguous probe markers found; the document would contribute nothing checkable and is left out rather than scored on guesswork"
    },
    {
      "doc_id": "gh-security-creating-a-strong-password",
      "reason": "gh-security-creating-a-strong-password: no unambiguous probe markers found; the document would contribute nothing checkable and is left out rather than scored on guesswork"
    }
  ],
  "shape": "Many small documents rather than a few large ones, which is what an internal knowledge base actually contains. An earlier corpus built from SEC filings was dominated by four documents that produced more chunks than forty others combined, and measured how each platform copes with outliers instead of with the ordinary workload.",
  "note": "Probe markers are strings verified to occur exactly once in their document, so a later search for them is unambiguous. Documents yielding no unambiguous marker are skipped rather than scored on guesswork."
}