{
  "title": "Harness Path — The Litreview Runtime",
  "story": [
    {
      "type": "markdown",
      "id": "0d1c33fbf6d39b02",
      "text": "# 📖 Harness Path — The Litreview Runtime"
    },
    {
      "type": "markdown",
      "id": "9c41d8b43c233ea2",
      "text": "*15 · the Programme lit-review runtime — novelty against an adversary* — an entry in the origin fleet catalogued in [[The Harness Paths]] (group: Adjacent embodiments). The catalogue is the operator's work WITH the harness, not part of the system you adopt; none of its code lives in the harness repo. This is the map entry, so you can see what a filled config looks like at this weight."
    },
    {
      "type": "markdown",
      "id": "5146026a91c8fea6",
      "text": "*(private instance of the author — inside the research corpus; the V6\npipeline's descendant, turned on related work. Its epigraph is the whole\ndesign: \"a literature review that only finds agreement has not been run\nagainst an adversary.\")*"
    },
    {
      "type": "markdown",
      "id": "0dc7b557578048f0",
      "text": "The objective is a **defensible novelty claim**, and the operative object is\nthe **residue** — what remains of a claim after covering art is subtracted.\nRun 03 seats eleven: **5 sweep ⊥ 5 refute ⊥ 1 judge**. The sweep bench\nsearches prior art by modality; the refute bench hunts covering art\nper-residue and is *instructed to default to coverage*; the judge rules\n**SURVIVES / NARROWED / COVERED**. The hold-apart is context isolation by\nconstruction — a refuter receives the residue and the sweep digest but\n**never the prover's argument** (D3: separation must be structural; a run\nseparated by prompt alone is invalid). D2 forbids the domain's oldest\noverclaim: absence of evidence is reported as `not_found_in_corpus(n,\nrange)`, never as *novel*. And the honest limit is declared in the manifest\nrather than hidden (D4b): all seats run the same weights, so **an\nall-SURVIVES result is treated as a failed enforcement of the adversarial\ndiscipline** — the run is trusted not by its result but by whether the\nadversary ever knocked anything down. It did: run 02 returned 0 VALIDATED /\n5 MIRAGE; run 03 (76 sweep items, 48 covering candidates) returned **1\nCOVERED / 4 NARROWED / 0 SURVIVES**, retiring one claimed novelty outright\nand shrinking the other four to their defensible cores; run 04 added the\nnormative strand and per-paper placement. Verdicts are candidates only —\nadoption and the terminal gate are the First Person's, and the manifests\nare generated artifacts: fix the data, regenerate, never hand-edit."
    },
    {
      "type": "markdown",
      "id": "e0f546acb468d942",
      "text": "> **At a glance** —\n> **objective:** residues surviving refutation — the defensible core of a novelty claim, honestly shrunk · **gate:** the refute bench + judge; verdict lexicon SURVIVES / NARROWED / COVERED, confidence never entering tier-A artifacts (GR-2) · **hard constraint:** D2 — absence is `not_found_in_corpus(…)`, never *novel*\n> **the Gap:** context isolation as the hold-apart — refuters never see the prover's argument (D3, structural); the draw is not hashed, and the manifest says so · **lenses:** five search modalities ⊥ five per-residue refuters, judge as the only barrier · **canary:** inverted and declared — same weights on all seats (D4b), so an adversary that never lands a hit indicts the run, not the claims\n> **weight:** full, non-numeric · private, inside the corpus · **the lesson it carries:** in research the mirage is agreement — the valuable verdict is the one that kills your claim, and a review that returns all-clear has failed, not succeeded."
    },
    {
      "type": "markdown",
      "id": "ff3e0b91ebf56440",
      "text": "## Navigation\n\n← [[Welcome Visitors]] · [[The Harness Paths]] · [[Adopting The Harness]] · [[Workflows And Runtimes]]"
    },
    {
      "type": "markdown",
      "id": "29691ca6f128f907",
      "text": "---\n*the wiki is a projection; `~/dual-agent-harness` (git) is the source of truth · (⚔️⊥⿻⊥🧙)😊 = neg ⊕ bnot → succ*"
    }
  ],
  "journal": [
    {
      "type": "create",
      "item": {
        "title": "Harness Path — The Litreview Runtime",
        "story": [
          {
            "type": "markdown",
            "id": "0d1c33fbf6d39b02",
            "text": "# 📖 Harness Path — The Litreview Runtime"
          },
          {
            "type": "markdown",
            "id": "9c41d8b43c233ea2",
            "text": "*15 · the Programme lit-review runtime — novelty against an adversary* — an entry in the origin fleet catalogued in [[The Harness Paths]] (group: Adjacent embodiments). The catalogue is the operator's work WITH the harness, not part of the system you adopt; none of its code lives in the harness repo. This is the map entry, so you can see what a filled config looks like at this weight."
          },
          {
            "type": "markdown",
            "id": "5146026a91c8fea6",
            "text": "*(private instance of the author — inside the research corpus; the V6\npipeline's descendant, turned on related work. Its epigraph is the whole\ndesign: \"a literature review that only finds agreement has not been run\nagainst an adversary.\")*"
          },
          {
            "type": "markdown",
            "id": "0dc7b557578048f0",
            "text": "The objective is a **defensible novelty claim**, and the operative object is\nthe **residue** — what remains of a claim after covering art is subtracted.\nRun 03 seats eleven: **5 sweep ⊥ 5 refute ⊥ 1 judge**. The sweep bench\nsearches prior art by modality; the refute bench hunts covering art\nper-residue and is *instructed to default to coverage*; the judge rules\n**SURVIVES / NARROWED / COVERED**. The hold-apart is context isolation by\nconstruction — a refuter receives the residue and the sweep digest but\n**never the prover's argument** (D3: separation must be structural; a run\nseparated by prompt alone is invalid). D2 forbids the domain's oldest\noverclaim: absence of evidence is reported as `not_found_in_corpus(n,\nrange)`, never as *novel*. And the honest limit is declared in the manifest\nrather than hidden (D4b): all seats run the same weights, so **an\nall-SURVIVES result is treated as a failed enforcement of the adversarial\ndiscipline** — the run is trusted not by its result but by whether the\nadversary ever knocked anything down. It did: run 02 returned 0 VALIDATED /\n5 MIRAGE; run 03 (76 sweep items, 48 covering candidates) returned **1\nCOVERED / 4 NARROWED / 0 SURVIVES**, retiring one claimed novelty outright\nand shrinking the other four to their defensible cores; run 04 added the\nnormative strand and per-paper placement. Verdicts are candidates only —\nadoption and the terminal gate are the First Person's, and the manifests\nare generated artifacts: fix the data, regenerate, never hand-edit."
          },
          {
            "type": "markdown",
            "id": "e0f546acb468d942",
            "text": "> **At a glance** —\n> **objective:** residues surviving refutation — the defensible core of a novelty claim, honestly shrunk · **gate:** the refute bench + judge; verdict lexicon SURVIVES / NARROWED / COVERED, confidence never entering tier-A artifacts (GR-2) · **hard constraint:** D2 — absence is `not_found_in_corpus(…)`, never *novel*\n> **the Gap:** context isolation as the hold-apart — refuters never see the prover's argument (D3, structural); the draw is not hashed, and the manifest says so · **lenses:** five search modalities ⊥ five per-residue refuters, judge as the only barrier · **canary:** inverted and declared — same weights on all seats (D4b), so an adversary that never lands a hit indicts the run, not the claims\n> **weight:** full, non-numeric · private, inside the corpus · **the lesson it carries:** in research the mirage is agreement — the valuable verdict is the one that kills your claim, and a review that returns all-clear has failed, not succeeded."
          },
          {
            "type": "markdown",
            "id": "ff3e0b91ebf56440",
            "text": "## Navigation\n\n← [[Welcome Visitors]] · [[The Harness Paths]] · [[Adopting The Harness]] · [[Workflows And Runtimes]]"
          },
          {
            "type": "markdown",
            "id": "29691ca6f128f907",
            "text": "---\n*the wiki is a projection; `~/dual-agent-harness` (git) is the source of truth · (⚔️⊥⿻⊥🧙)😊 = neg ⊕ bnot → succ*"
          }
        ]
      },
      "date": 1787093563953
    }
  ]
}