{
  "schema": "grex-public-experiment-summary/v1",
  "slug": "social-discovery",
  "updated": "2026-11-04",
  "experimentDate": "2026-08-30",
  "status": "Calibration only · comparison held",
  "scope": "Sanitized aggregate transcription of retained source records, not a raw-data release or independent reproduction. Private operational identifiers, source bodies and traces are excluded.",
  "question": "Could Grex find useful public conversations and draft evidence-supported replies more effectively than Hermes using the same underlying model?",
  "hypothesis": {
    "statement": "Grex’s task boundaries, evidence checks and separate reviewer would improve recommendation precision and reply usability over an unaided Hermes session at acceptable review effort.",
    "provenance": "Paraphrase of the original hypothesis recorded before scored runs in the August 29 experiment charter. Unlike the other retrospective summaries, this study did register directional and numerical pass conditions. Calibration did not test those conditions."
  },
  "sample": "Calibration observations from August 29–30, including three repeated search slots and the first reviewed brief. They are not seven scored pairs or independent discovery samples.",
  "method": "The charter proposed a controlled track with the same frozen candidate corpus for both arms and a separate field track using each arm’s native tools. Actual retained calibration exercised Grex’s live search, filtering, drafting and separate review path.",
  "comparison": {
    "columns": [
      "Measure",
      "Planned comparison",
      "Observed calibration"
    ],
    "rows": [
      [
        "Matched scored runs",
        "7 pairs",
        "No completed paired result recorded"
      ],
      [
        "Repeated search slots",
        "Independent scored recommendations",
        "53 candidates in each of 3 slots"
      ],
      [
        "Candidates sent to drafting per slot",
        "Up to 5 final recommendations",
        "8 candidates; all 8 refused"
      ],
      [
        "First reviewed internal brief",
        "Worth-reading assessment",
        "Rejected as not worth reading"
      ],
      [
        "Public replies",
        "Separate publication decision",
        "No posting path in the tested workflow"
      ]
    ]
  },
  "findings": [
    {
      "title": "Repeated search was not fresh progress",
      "body": "Three recorded slots each rediscovered the same 53 candidates. Eight reached drafting each time and all eight were refused as promotional or otherwise unsuitable. The workflow spent effort repeating a decision instead of learning from it."
    },
    {
      "title": "A refusal became a suggested reply",
      "body": "A later internal brief carried the drafter’s refusal as if it were a reply. This was a delivery defect: text existed, but it did not satisfy the intended engagement task."
    },
    {
      "title": "Independent review contradicted the relevance score",
      "body": "The first live reviewer verdict found the post resolvable and its evidence link present, yet judged it not worth reading. Mechanical source validity and keyword relevance did not establish usefulness."
    },
    {
      "title": "The comparison question remained unanswered",
      "body": "The formal results table was never filled with seven scored pairs in the records reviewed. Calibration exposed useful defects, but it did not establish better precision, lower review effort or improved audience response versus Hermes."
    }
  ],
  "limitations": [
    "Historical architecture and calibration only, not a current Grex social-integration capability.",
    "The observed slots reused candidates and involved operational adjustments. They are not independent trials or a controlled quality estimate.",
    "The intended controlled and field tracks differed in source and tool treatment; neither supplies a completed comparative result here.",
    "Registered precision, reply-usability and review-time thresholds were not evaluated by these calibration observations.",
    "No customer demand, revenue, engagement uplift or complete cost-per-useful-recommendation result was established."
  ],
  "decision": "Retain calibration findings while leaving the formal comparison unresolved. A working search-to-review pipeline and a single rejection are not evidence that Grex outperforms Hermes.",
  "next": "Any resumed comparison would need a fresh bounded plan, distinguish controlled-corpus work from live discovery, and keep failed or unhelpful outputs visible. No restart is implied by this historical record.",
  "controls": [
    "The proposed formal comparison required the same resolved MiniMax model, alternating order and blind scoring. Those are planned controls, not evidence that a scored comparison ran.",
    "Calibration was explicitly excluded from the registered pass/fail calculation.",
    "The live reviewer used the same model as drafting in a separate process and context, after deterministic source checks.",
    "The tested workflow had no tool to post replies externally. Internal brief publication was not social-platform publication.",
    "The registered bar required at least 70% recommendation precision and a 20-percentage-point lead over Hermes, zero unsupported material claims, at least half the replies usable with light editing, and review under 15 minutes. These thresholds were not scored."
  ]
}