{
  "schema": "s2s-bench-v1",
  "kind": "data-kit-index",
  "exhibit": "the-open-call",
  "exhibit_title": "A kid, an elder, and a tired parent walk into the cove",
  "exhibit_url": "https://research.strata2signal.com/the-open-call/index.html",
  "round": "opencall-r2",
  "scored_utc": "2026-08-14T15:31:03.865182+00:00",
  "licence": "CC BY 4.0",
  "attribution": "strata→signal research, research.strata2signal.com",
  "contact": "hello@strata2signal.com",
  "withheld": {
    "sealed_bundles": "each carries an unpublished persona block — a living game's character interiors. seal-manifest.json publishes their full sha256s, so a holder of the bytes can prove they hold these bytes; a stranger cannot reproduce the round from this kit, and the page says so.",
    "judge_letter_map": "the sheets were read blind against shuffled letters from a recorded seed; publishing the map would retire the sealed sheets for any future re-judging.",
    "sealed_reply_records": "results/samples/* — one record per arm per act, holding each reply's spoken line, extraction tier and both clocks. Sealed records are what a future round re-judges and a published record is a retired one, so they stay back; every line they hold prints verbatim on the exhibit page and in its folds. ONE EXCEPTION: the post-publication addendum arm's six records publish as addendum-samples.json — at six records the page already prints every line verbatim, so withholding them would withhold nothing readable.",
    "addendum_judge_letter_map": "the addendum round was blinded the same way and its letter map is withheld for the same reason. Its letters are a fresh shuffle over a different reply list and correspond to nothing in the sealed round's sheets.",
    "harness_ledgers": "LEDGER-*.json and the judge RUN-*.json files — the round's per-leg token counts, in files that also carry internal filesystem paths. The COUNTS are not withheld: the metered arms' are joined into bill.json and the addendum round's judge seats into addendum-bill.json, both with every dollar re-derived from them. It is the files that stay back, never the figures they carry."
  },
  "scrub_declaration": "7 published files carry path-scrub substitutions (scores.json, report.md, known-world-issues.md, seats.json, addendum-scores.json, addendum-runtime-pins.json, addendum-probe.json). Every substitution is listed per file below with its reason. `\"scrub\": null` on a COPIED file means its bytes are identical to the round's own artifact; on a DERIVED file it means nothing was removed — a derived file has no single round artifact to be identical to, and its `source` field says which it is. Nothing measured was changed.",
  "annotation_declaration": "2 published files carry a bracketed correction inserted beside a wrong claim in them (report.md, known-world-issues.md). The original line is left standing in every case; each correction is a count a reader can redo from the same bytes, and each is listed per file below with its reason.",
  "decoding_parameters": "not pinned and not recorded: each transport's defaults were used. Temperature, top-p and sampling seed are not reproducible from this kit, and this is a limit of the round rather than an omission from the kit.",
  "not_a_standard": "Our own round, our own world, our own judges. Not first independent numbers, and not a benchmark.",
  "contamination_caveat": "Published 2026-08. Models with a later training cutoff may have seen this set. We author fresh sets each cycle; this one is not a standard, it is our kit, yours to reuse.",
  "files": [
    {
      "file": "scores.json",
      "role": "the scoring artifact entire: every arm, every act, every one of the 738 scoring cells with its seat, its two dimension scores, its canon verdict and the judge's own note — plus all 102 recused cells kept with their verdicts, the anchor calibration, the agreement matrix, the tie bands, and the canon tallies. Every figure in the SEALED round is a projection of this file; the addendum's thirty cells are a projection of addendum-scores.json beside it",
      "media_type": "application/json",
      "bytes": 1124224,
      "sha256": "722e04db3ae473e2fdffb9129eb1d7bd2089a59e3548317d1dad25eabec350ab",
      "source": "a copy of the round's own artifact",
      "scrub": [
        {
          "scrub": "concurrency-flag",
          "why": "a daemon environment flag restated as the fact it carries; the measurement is unchanged and the configuration detail is not this exhibit's to publish"
        }
      ],
      "annotations": null
    },
    {
      "file": "seal-manifest.json",
      "role": "the seal: for every frozen bundle, the FULL sha256 of the bundle, its event log and its boot log, the full wire sha256 the arms answered, the byte counts, and the verbatim user line each arm was handed",
      "media_type": "application/json",
      "bytes": 9275,
      "sha256": "05cdb3d5deb6a3f82e0c188b3be45688fb15fd7635d6ea3277589847f61a78b5",
      "source": "a copy of the round's own artifact",
      "scrub": null,
      "annotations": null
    },
    {
      "file": "report.md",
      "role": "the complete internal report, built by machine from the round's own artifacts — the per-arm and per-ask tables, the anchor calibration, the agreement matrix, the canon findings including the convergent-invented-span cell table with every judge's deciding words, the mirror table, the fabrication classes, every SPLIT in full, the bill and the curated highlights",
      "media_type": "text/markdown",
      "bytes": 57480,
      "sha256": "50fce08f56fa027f8cb2cedc46b496be539e03728862efdd60bf0a3f1472a340",
      "source": "a copy of the round's own artifact",
      "scrub": [
        {
          "scrub": "read-styled-line",
          "why": "a line telling an internal reader which local command renders the file; it names a filesystem path and nothing else"
        },
        {
          "scrub": "concurrency-flag",
          "why": "a daemon environment flag restated as the fact it carries; the measurement is unchanged and the configuration detail is not this exhibit's to publish"
        }
      ],
      "annotations": [
        {
          "annotation": "scoring-cell-arithmetic",
          "why": "the report's summary line subtracted the recused cells and not the calibration anchors, so it reads 766 where every table under it reads 738. The kit prints the correction beside the line rather than letting the file the page cites disagree with the page"
        }
      ]
    },
    {
      "file": "known-world-issues.md",
      "role": "the fence: the known-world-issues list that rode every judge sheet — as published, 39 table rows naming 64 distinct issue ids — so a reader can check the rows a judge was allowed to reach for, and check that everything off the fence stayed the model's own",
      "media_type": "text/markdown",
      "bytes": 11615,
      "sha256": "dfb49b79a8ed758ab3e2ffe127d8ed8f165fb384450ba75ce9019467a9a5001a",
      "source": "a copy of the round's own artifact",
      "scrub": [
        {
          "scrub": "source-pin-path",
          "why": "the pinned source document keeps its filename and its sha256 — which is what pins it — and loses the private path it sat at"
        },
        {
          "scrub": "operator-name",
          "why": "a human operator is a role this hub names, never a person; the page uses the same word, and the possessive and attributive forms publish as 'the operator's' so the sentence still reads"
        }
      ],
      "annotations": [
        {
          "annotation": "fence-row-count",
          "why": "the fence's headline row count is inherited from a source document that is not published and does not match the rows in this file; the published counts are printed beside it so the number governing what scores clean is one a reader can check"
        }
      ]
    },
    {
      "file": "counting-rules.json",
      "role": "every rule that governs a figure, in one file: the counting rules, the cell arithmetic spelled out, the curation rule as registered AND as implemented, the registered extraction tiers, the mirror column's rule from both of its sources, the fence counted, the tie band with its chaining warning, the forbidden-claims list verbatim — and a note saying why the pre-registration is extracted rather than published whole",
      "media_type": "application/json",
      "bytes": 13175,
      "sha256": "4c394f718e7b8c6069703e6cd26feb4ba17c62ae574f25aeeff387f8c8feaae6",
      "source": "derived — built from the round's artifacts by tools/opencall_kit.py",
      "scrub": null,
      "annotations": null
    },
    {
      "file": "seats.json",
      "role": "the seven judge seats, NAMED: each seat's mean on the shared calibration reply and its offset from the panel, its canon strictness with its own denominator, the pairwise agreement matrix, and the local-seat axis",
      "media_type": "application/json",
      "bytes": 23392,
      "sha256": "4c14d999cdee42ac0edefd8eea4738b6969c82ab9218dff2acbc50c4ddaec6d4",
      "source": "derived — built from the round's artifacts by tools/opencall_kit.py",
      "scrub": [
        {
          "scrub": "concurrency-flag",
          "why": "a daemon environment flag restated as the fact it carries; the measurement is unchanged and the configuration detail is not this exhibit's to publish"
        }
      ],
      "annotations": null
    },
    {
      "file": "bill.json",
      "role": "the bill reconciled: three metered lines, each receipt with the token counts it was billed on, its cited per-token rate and that multiplication performed, the registered caps, the four cost states, the nine discarded cold-start warmups that were billed and never scored, and the difference between the round's carriage artifact and the joined total, named",
      "media_type": "application/json",
      "bytes": 16307,
      "sha256": "dd5acbdaf2b5c60fdbe6ce519429207bcb1943002e3c0e3b2ad628ebba980767",
      "source": "derived — built from the round's artifacts by tools/opencall_kit.py",
      "scrub": null,
      "annotations": null
    },
    {
      "file": "addendum-scores.json",
      "role": "the addendum's scoring artifact: the twenty-first arm (qwen3.8:27b, run after the round was sealed) over 30 cells and 5 families, with every cell's seat, dimension scores, canon verdict and judge note, its own anchor calibration — the bridge that makes it readable beside a round it cannot share blinding letters with — and its floor-gate check. A SEPARATE round: nothing in it re-scores the sealed twenty",
      "media_type": "application/json",
      "bytes": 81943,
      "sha256": "c68a603bd6b8c90d14a97610681f5fbc174123184718361c4ec8550f99d6678e",
      "source": "a copy of the round's own artifact",
      "scrub": [
        {
          "scrub": "concurrency-flag",
          "why": "a daemon environment flag restated as the fact it carries; the measurement is unchanged and the configuration detail is not this exhibit's to publish"
        }
      ],
      "annotations": null
    },
    {
      "file": "addendum-samples.json",
      "role": "the addendum arm's six judged records, whole: each reply's spoken line, its client-wall clock and the endpoint's own counters, the sha256 of the reply, and the wire_sha256 it answered — which is the sealed round's own, byte for byte, so a reader can prove the late arm sat the same exam. Published where the sealed round's records are withheld, and the README says why",
      "media_type": "application/json",
      "bytes": 8445,
      "sha256": "eedf665f7f317f73b10c3d169de0300ec640261d3965713e95a3b76d7db98830",
      "source": "derived — built from the round's artifacts by tools/opencall_kit.py",
      "scrub": null,
      "annotations": null
    },
    {
      "file": "addendum-runtime-pins.json",
      "role": "the addendum's runtime provenance: the ollama version it ran on, the full digest, size and quantisation of the late arm's weights, and the sealed round's three local tags re-resolved today with the one fact that qualifies them — whether each tag's file predates the seal. It also records, in its own words, that the sealed round's runtime was never written down: this file is the receipt for the caveat the page cannot cure, including the part of it that is an inference rather than a reading",
      "media_type": "application/json",
      "bytes": 1921,
      "sha256": "4ef9f335ef4ad17aacda84dc1ed380afb6e0c35427c07d7699eca95c1e192fcb",
      "source": "a copy of the round's own artifact",
      "scrub": [
        {
          "scrub": "daemon-address",
          "why": "the private address the local lane's requests went to. Which machine answered is already published as its hardware class; the address itself is estate detail and reaching it is not something this kit is offering"
        }
      ],
      "annotations": null
    },
    {
      "file": "addendum-probe.json",
      "role": "the release re-probe, all 16 calls: four request configurations against both the late arm and the local judge seat, run on the new runtime BEFORE any reply was captured, testing whether asking for JSON with reasoning switched off silently drops the constraint. Every call's verdict, its latency and the first 200 characters it returned — so the claim that the trap did not reproduce is checkable rather than asserted",
      "media_type": "application/json",
      "bytes": 19186,
      "sha256": "c86923cd8148465576a8fec9c3c17d06b9639102ead5c352d2e25d907ecdf1d8",
      "source": "a copy of the round's own artifact",
      "scrub": [
        {
          "scrub": "daemon-address",
          "why": "the private address the local lane's requests went to. Which machine answered is already published as its hardware class; the address itself is estate detail and reaching it is not something this kit is offering"
        },
        {
          "scrub": "box-name",
          "why": "a machine's estate name in a title line, restated as its role; the exact phrase is scrubbed rather than the bare word, because the bare word is canon text in the sealed scoring file"
        }
      ],
      "annotations": null
    },
    {
      "file": "addendum-bill.json",
      "role": "the addendum round's own bill, in bill.json's shape: a line per judge seat with the token counts it was billed on, the rate they were priced at and that multiplication performed, the three seats that bill nothing published with their counts too, and the sealed round's total beside this one with a note on why the two add rather than overlap. It exists because the addendum published with $0.3579 on the page and no token counts behind it — this is the file that makes that figure re-derive",
      "media_type": "application/json",
      "bytes": 12976,
      "sha256": "7815061fc9cc7152505c8307d235a8e69cc735916c973e1b622ce0eb0eff2bcf",
      "source": "derived — built from the round's artifacts by tools/opencall_kit.py",
      "scrub": null,
      "annotations": null
    },
    {
      "file": "README.md",
      "role": "the kit's own README: licence, how to check the page against these files, what is withheld and why, the scrub and the annotations declared, and the limits",
      "media_type": "text/markdown",
      "bytes": 17901,
      "sha256": "763bac572800d0db8f8ded0074a583eab7942e8bd00d5dabd7fe931c354baa4a",
      "source": "derived — built by tools/opencall_kit.py",
      "scrub": null,
      "annotations": null
    }
  ],
  "self": {
    "file": "index.json",
    "note": "this listing; its own sha is not carried inside itself"
  }
}