{
  "format": "agent-article-v0",
  "article_id": "EA-171",
  "canonical_url": "/tools/ea-171-arize-phoenix",
  "page_type": "reference",
  "claim_ids": [],
  "evidence_ids": [
    "EA-171-R11-RESEARCH",
    "EA-171-R11-WEB-READBACK"
  ],
  "unknown_ids": [
    "EA-171-UNKNOWN-01",
    "EA-171-UNKNOWN-CURRENTNESS"
  ],
  "operational_object_ids": [],
  "provider": [],
  "models": [],
  "plans": [],
  "surfaces": [],
  "regions": [],
  "current_status": "UNKNOWN",
  "observation_status": "SPEC_ONLY",
  "freshness": "UNKNOWN",
  "last_verified": null,
  "supersedes": [],
  "superseded_by": [],
  "provenance": [
    "COMM-049-EA0171",
    "WEBBODY-EA0171-R8-06FCB6C3"
  ],
  "article_sources": [
    {
      "id": "EA-171-R11-RESEARCH",
      "evidence_class": "RESEARCH",
      "title": "EA-171 監査済みresearch / canonical revision binding",
      "supports": [
        "Phoenix documentation describes OpenTelemetry/OpenInference-based instrumentation and OTLP ingestion for AI application tracing. Documentation and repository availability establish capabilities, not complete instrumentation, secure deployment, evaluator validity, or enterprise SLO."
      ],
      "limit": "canonical監査・revision bindingの存在を示す。外部ソースcurrentnessが本文またはcontrol-planeで確定していない場合は、currentnessをUNKNOWNのまま保持する。",
      "origin_class": "AUDITED_CANONICAL_RESEARCH_PACKET",
      "source_or_experiment_ids": [
        "COMM-049-EA0171"
      ],
      "supporting_locators": [
        "COMM-049-EA0171",
        "EA-171-V21-LEGACY-MIGRATION-20261003-R1",
        "content/staging/EA-171.md"
      ],
      "scope": "監査済みEA本文・canonical revision・既存Source Graph relationの範囲。欠損currentnessは推測で閉じない。",
      "provenance_status": "AUDIT_PASS_CANONICAL_BINDING"
    },
    {
      "id": "EA-171-R11-WEB-READBACK",
      "evidence_class": "IMPL",
      "title": "EA-171 Web body identity / canonical readback",
      "supports": [
        "canonical staging bodyのSHA-256一致とR9 canonical ledger readbackをProduction projectionの入力として検証する。"
      ],
      "limit": "body identity/readbackは本文claim自体の真偽や外部ソースの最新性を追加保証しない。",
      "checked_at": null,
      "origin_class": "IMPLEMENTATION_READBACK",
      "source_or_experiment_ids": [
        "WEBBODY-EA0171-R8-06FCB6C3"
      ],
      "supporting_locators": [
        "WEBBODY-EA0171-R8-06FCB6C3",
        "content/staging/EA-171.md",
        "EA-171-V21-LEGACY-MIGRATION-20261003-R1"
      ],
      "scope": "R9/R10 canonical readback後のProduction生成時body identity。",
      "provenance_status": "CANONICAL_READBACK_BODY_HASH_MATCH"
    }
  ],
  "research_sections": [
    {
      "heading": "PUBLIC_CLAIM",
      "text": "Arize Phoenix is documented as an open-source AI observability and evaluation platform built on OpenTelemetry and OpenInference. Its documented surface includes traces for model calls, retrieval, tool use and custom logic, together with evaluation, versioned datasets and experiments. Phoenix OSS and the managed Arize AX workflow are separate operational and contractual boundaries."
    },
    {
      "heading": "ESTABLISHED",
      "text": "Phoenix documentation describes OpenTelemetry/OpenInference-based instrumentation and OTLP ingestion for AI application tracing. Documentation and repository availability establish capabilities, not complete instrumentation, secure deployment, evaluator validity, or enterprise SLO."
    },
    {
      "heading": "INFERENCE",
      "text": "Phoenix can be used as a locally controlled observability/evaluation layer, but an OSS label, OpenTelemetry support, integration listing, or visible trace is not proof of complete visibility, privacy-safe capture, correct evaluation, production readiness, or parity with Arize AX."
    },
    {
      "heading": "AVAILABILITY_GATES",
      "text": "Pin and verify the Phoenix release/commit and package versions, Phoenix OSS versus Arize AX boundary, ELv2 obligations, OTLP collector/exporter/backend, supported framework/provider/language, auto/manual instrumentation, sampling and redaction, authentication/RBAC/tenant controls, storage/backup/retention/region, dataset/evaluator versions, deployment/upgrade path, cost and SLO."
    },
    {
      "heading": "IMPLEMENTATION_STATE",
      "text": "Evidence-only desk research. No Phoenix server, UI, SDK, OTLP exporter, evaluation, dataset, or Arize AX tenant was exercised by the source packet."
    },
    {
      "heading": "UNKNOWN",
      "text": "Current component releases; exact ELv2 scope for the intended use; instrumentation matrix; OpenTelemetry/OpenInference parity; trace loss and overhead; evaluator behavior; self-host security defaults; managed feature, region, retention and SLO behavior; public incident completeness."
    },
    {
      "heading": "SECURITY_PRIVACY_AUDIT_OPERABILITY",
      "text": "Traces can contain prompts, outputs, retrievals, tool calls and identities. Redaction and access controls must be applied before export; collector, backend, UI and backups require protection. Self-hosting transfers compute, storage, backup, upgrade, patching and incident-response obligations to the deployer."
    },
    {
      "heading": "STOP_CONDITION",
      "text": "Do not treat Phoenix's OSS label, OpenTelemetry foundation, integration list, or UI trace as proof of complete observability, safe privacy, correct evaluation, or Arize AX equivalence."
    }
  ],
  "human_url": "/tools/ea-171-arize-phoenix",
  "markdown_url": "/agent/article.md?path=%2Ftools%2Fea-171-arize-phoenix",
  "json_url": "/agent/article.json?path=%2Ftools%2Fea-171-arize-phoenix"
}