Slayer1B: benchmark section links to Slayer1B-Benchmarks

benchmarks-contract.js

@@ -1,110 +0,0 @@
-"use strict";
-/* Local, dependency-free checks for the keyword subset used by N05 v0.3's
-   pinned results.schema.json (01a947d7, authority 18a79884). Not a general
-   Draft2020 implementation. Unknown keywords fail closed. The authoritative
-   schema is benchmarks.schema.json; the plan is tasks_50_v01.json, byte-exact. */
-(() => {
-  const keywords = new Set(["$schema", "$id", "$defs", "$ref", "type", "const", "enum", "properties", "required", "additionalProperties", "items", "pattern", "minLength", "minimum", "maximum", "anyOf", "allOf", "if", "then", "else"]);
-  const own = (value, key) => Object.prototype.hasOwnProperty.call(value, key);
-  const object = value => value !== null && typeof value === "object" && !Array.isArray(value);
-  function matches(value, rule, root) {
-    for (const key of Object.keys(rule)) if (!keywords.has(key)) throw new Error(`Unsupported schema keyword: ${key}`);
-    if (rule.$ref) {
-      if (!rule.$ref.startsWith("#/")) throw new Error("External schema references are not allowed");
-      let target = root;
-      for (const key of rule.$ref.slice(2).split("/")) {
-        if (!own(target, key)) throw new Error("Unresolved schema reference");
-        target = target[key];
-      }
-      if (!matches(value, target, root)) return false;
-    }
-    if (own(rule, "const") && value !== rule.const) return false;
-    if (rule.enum && !rule.enum.includes(value)) return false;
-    if (rule.type) {
-      const types = Array.isArray(rule.type) ? rule.type : [rule.type];
-      if (!types.some(type => type === "null" ? value === null : type === "array" ? Array.isArray(value) : type === "object" ? object(value) : type === "integer" ? Number.isInteger(value) : type === "number" ? typeof value === "number" && Number.isFinite(value) : typeof value === type)) return false;
-    }
-    if (typeof value === "string") {
-      if (rule.minLength !== undefined && [...value].length < rule.minLength) return false;
-      if (rule.pattern && !new RegExp(rule.pattern).test(value)) return false;
-    }
-    if (typeof value === "number") {
-      if (!Number.isFinite(value)) return false;
-      if (rule.minimum !== undefined && value < rule.minimum) return false;
-      if (rule.maximum !== undefined && value > rule.maximum) return false;
-    }
-    if (Array.isArray(value) && rule.items && !value.every(item => matches(item, rule.items, root))) return false;
-    if (object(value)) {
-      if (rule.required && !rule.required.every(key => own(value, key))) return false;
-      const props = rule.properties || {};
-      for (const key of Object.keys(value)) {
-        if (own(props, key)) {
-          if (!matches(value[key], props[key], root)) return false;
-        } else if (rule.additionalProperties === false) return false;
-      }
-    }
-    if (rule.anyOf && !rule.anyOf.some(part => matches(value, part, root))) return false;
-    if (rule.allOf && !rule.allOf.every(part => matches(value, part, root))) return false;
-    if (rule.if) {
-      const branch = matches(value, rule.if, root) ? rule.then : rule.else;
-      if (branch && !matches(value, branch, root)) return false;
-    }
-    return true;
-  }
-  const key = (...parts) => JSON.stringify(parts);
-  function unique(items, getKey, name) {
-    const map = new Map();
-    for (const item of items) {
-      const id = getKey(item);
-      if (map.has(id)) throw new Error(`Duplicate ${name}: ${id}`);
-      map.set(id, item);
-    }
-    return map;
-  }
-  function validCI(ci) {
-    if (ci !== null && ci.lower > ci.upper) throw new Error("CI lower exceeds upper");
-  }
-  function validate(packet, inventory, schema, inventoryRevision) {
-    if (inventory.protocol !== protocol || !protocolIds.every(id => schema.properties.protocol_id.enum.includes(id))) throw new Error("Pinned plan or schema is not N05 v0.3");
-    if (!matches(packet, schema, schema)) throw new Error("Packet does not match the pinned N05 schema");
-    if (packet.provenance.kind !== "measurement") throw new Error("Contract example is not a measurement");
-    if (packet.provenance.inventory_commit !== inventoryRevision) throw new Error("Inventory revision differs from the displayed protocol");
-    if (!protocolIds.includes(packet.protocol_id)) throw new Error("Unknown protocol scale");
-    const models = unique(packet.models, m => m.model_id, "model");
-    const tasks = unique(packet.tasks, t => t.task_id, "task");
-    const plan = new Map(inventory.rows.map(t => [t.id, t]));
-    for (const task of tasks.values()) {
-      const item = plan.get(task.task_id);
-      if (!item || ["task", "family", "language", "split"].some(field => task[field] !== item[field])) throw new Error(`Task metadata differs: ${task.task_id}`);
-    }
-    const observations = unique(packet.observations, o => key(o.task_id, o.model_id, o.protocol_id), "observation");
-    for (const o of observations.values()) {
-      if (!tasks.has(o.task_id) || !models.has(o.model_id) || o.protocol_id !== packet.protocol_id) throw new Error("Unknown task, model or protocol in observation");
-      const item = plan.get(o.task_id);
-      if (o.metric !== item.metric || o.unit !== item.unit || o.higher_is_better !== item.higher_is_better) throw new Error(`Primary metric differs from the plan: ${o.task_id}`);
-      if ((o.n_selected !== null && o.n_scored > o.n_selected) || (o.n_selected !== null && o.n_population !== null && o.n_selected > o.n_population)) throw new Error("Inconsistent sample counts");
-      validCI(o.ci95);
-    }
-    const contrasts = unique(packet.contrasts, c => key(c.task_id, c.model_id, c.model_ref, c.protocol_id), "contrast");
-    for (const c of contrasts.values()) {
-      if (!tasks.has(c.task_id) || !models.has(c.model_id) || !models.has(c.model_ref) || c.protocol_id !== packet.protocol_id) throw new Error("Unknown key in contrast");
-      validCI(c.ci95);
-      if (c.verdict !== "withheld") {
-        const left = observations.get(key(c.task_id, c.model_id, c.protocol_id));
-        const right = observations.get(key(c.task_id, c.model_ref, c.protocol_id));
-        if (!left || !right || left.state !== "ok" || right.state !== "ok" || left.metric !== right.metric || left.unit !== right.unit || left.higher_is_better !== right.higher_is_better) throw new Error("Accepted contrast lacks comparable observations");
-        if ((c.verdict === "better" || c.verdict === "worse") && c.p_holm > 0.05) throw new Error("Decisive verdict conflicts with the declared Holm rule");
-      }
-    }
-    return {models, tasks, observations, contrasts};
-  }
-  const protocol = "N05-50-v0.3";
-  const protocolIds = [`${protocol}-panel200`, `${protocol}-fullB`];
-  const api = {validate, key, protocol, protocolIds,
-    revision: "18a798843d300fa82cceb50c8ba5032d17be36d5",
-    inventorySHA: "b0a7d9a79f3d80273e90f90c996f4b04b815054c036a048fc6cd87b66110887f",
-    schemaSHA: "01a947d79411c5e635b92bf9d808d0406a068eb735cab255130bb4458066706e"
-  };
-  if (typeof module !== "undefined" && module.exports) module.exports = api;
-  else window.N05Contract = api;
-})();

benchmarks-feed.json

@@ -1,3 +0,0 @@
-{
-  "results": null
-}

benchmarks-plan.json

@@ -1,1896 +0,0 @@
-{
-  "schema_version": 2,
-  "protocol": "N05-50-v0.3",
-  "status": "selected_source_registry_not_measurements_or_execution_approval",
-  "scope": "50 distinct upstream benchmark identities; variants, splits, translations, rounds and suite members are not extra benchmarks",
-  "counts": {
-    "rows": 50,
-    "distinct_benchmarks": 50,
-    "EN": 38,
-    "PL": 12,
-    "source_members": 204,
-    "dataset_repositories": 44
-  },
-  "distinctness": {
-    "key": "benchmark_id and reviewed upstream collection, not YAML task name",
-    "umbrella_suites_not_added_to_components": true,
-    "statistical_independence_claimed": false,
-    "language_balance": "source diversity first; original user directive did not impose25PL/25EN"
-  },
-  "sources": {
-    "lm_eval_commit": "6d2abda4fd171e68a8789330c4149e37c1ca0bda",
-    "openpl_commit": "21d0ea9cf4fd6153dfff4d84d6ad0aab5488f302",
-    "source_registry": "benchmark_sources_v03.json",
-    "origins": {
-      "en": "canonical pinned EN checkout",
-      "pl": "canonical pinned PL checkout",
-      "registry": "this release tasks/ definitions"
-    }
-  },
-  "selection": {
-    "seed": 20261028,
-    "max_documents_per_benchmark": 200,
-    "unit": "source document after the original process_docs; group member namespace included",
-    "ordering": "SHA256(UTF8(20261028|benchmark_id|member_task|source_id)); ties by canonical source bytes",
-    "when": "seal all requested benchmark/member data, source IDs, support and requests before loading model weights",
-    "group_allocation": "reserve min(2,eligible_population) per member; then allocate each remaining slot to the non-full member with largest (budget*source_weight - allocated), ties by member task name; never200 per member",
-    "group_weighting": "source macro/equal-member or eligible-population-size weights retained independently of sample quota; reaggregate member metrics with those fixed weights",
-    "support_policy": "configured source count; hash-selected disjoint support per member unless source supplies fixed examples, which retain source order; record every demo and exclude matching scored inputs",
-    "context_policy": "float32,batch1,max4096,no automaticBOS/chat; reserve task generation limit (default256); drop optional demos from end, never query/options; explicit failure if still over limit",
-    "wikitext": "full source test stream, canonical weighted byte_perplexity, not Glint conversion; descriptive comparison only",
-    "full_protocol_B": "separate full-data evaluation of these selected primary protocols; not the old23-definition OpenPL replication",
-    "harness_seed_tuple": {
-      "python": 0,
-      "numpy": 1234,
-      "torch": 1234,
-      "fewshot": 1234
-    },
-    "empty_group_member": "explicit failure; never silently remove or reweight a required source member"
-  },
-  "rows": [
-    {
-      "id": "T01",
-      "benchmark_id": "blimp",
-      "task": "blimp",
-      "name": "BLiMP",
-      "language": "EN",
-      "family": "blimp",
-      "domain": "syntax",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "group",
-      "split": "train",
-      "shots": 0,
-      "rationale": "syntax",
-      "member_count": 67,
-      "source_record": "blimp",
-      "license": {
-        "declared_tags": [
-          "cc-by-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "nyu-mll/blimp",
-            "revision": "877fba0801ffb7cbd8c39c1ff314a46f053f6036",
-            "metadata_source": "https://huggingface.co/api/datasets/nyu-mll/blimp"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/blimp/_blimp.yaml"
-    },
-    {
-      "id": "T02",
-      "benchmark_id": "arc",
-      "task": "arc_challenge",
-      "name": "ARC Challenge",
-      "language": "EN",
-      "family": "arc",
-      "domain": "science_reasoning",
-      "metric": "acc_norm,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "science reasoning",
-      "member_count": 1,
-      "source_record": "arc",
-      "license": {
-        "declared_tags": [
-          "cc-by-sa-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "allenai/ai2_arc",
-            "revision": "210d026faf9955653af8916fad021475a3f00453",
-            "metadata_source": "https://huggingface.co/api/datasets/allenai/ai2_arc"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "ARC Easy and Polish ARC translation are the same counted family, not extra main benchmarks."
-      ],
-      "definition": "lm_eval/tasks/arc/arc_challenge.yaml"
-    },
-    {
-      "id": "T03",
-      "benchmark_id": "wikitext2",
-      "task": "wikitext",
-      "name": "WikiText-2",
-      "language": "EN",
-      "family": "wikitext2",
-      "domain": "language_modeling",
-      "metric": "byte_perplexity,none",
-      "unit": "byte_ppl",
-      "higher_is_better": false,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "language modeling",
-      "member_count": 1,
-      "source_record": "wikitext2",
-      "license": {
-        "declared_tags": [
-          "cc-by-sa-3.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "EleutherAI/wikitext_document_level",
-            "revision": "647234772b9554e208af6c826f23b99e3cac88c8",
-            "metadata_source": "https://huggingface.co/api/datasets/EleutherAI/wikitext_document_level"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Canonical harness byte_perplexity, not the historical Glint tp^(N/B) conversion; full evaluation stream."
-      ],
-      "definition": "lm_eval/tasks/wikitext/wikitext.yaml"
-    },
-    {
-      "id": "T04",
-      "benchmark_id": "multiblimp",
-      "task": "multiblimp_pl",
-      "name": "MultiBLiMP-PL",
-      "language": "PL",
-      "family": "multiblimp",
-      "domain": "morphosyntax",
-      "metric": "accuracy",
-      "unit": "percent",
-      "higher_is_better": true,
-      "instrument": "custom_pl",
-      "entrypoint_kind": "custom",
-      "split": "pol/data.tsv",
-      "shots": 0,
-      "rationale": "morphosyntax",
-      "member_count": 1,
-      "source_record": "multiblimp",
-      "license": {
-        "declared_tags": [
-          "cc-by-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "jumelet/multiblimp",
-            "revision": "de923efa8d2483d6b13364ee68e65308e990a991",
-            "metadata_source": "https://huggingface.co/api/datasets/jumelet/multiblimp/revision/de923efa8d2483d6b13364ee68e65308e990a991"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Independent UD/UniMorph construction, not BLiMP translation. Preserve the explicit historical space-prefix log-probability-sum instrument."
-      ]
-    },
-    {
-      "id": "T05",
-      "benchmark_id": "hellaswag",
-      "task": "hellaswag",
-      "name": "HellaSwag",
-      "language": "EN",
-      "family": "hellaswag",
-      "domain": "commonsense",
-      "metric": "acc_norm,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "commonsense",
-      "member_count": 1,
-      "source_record": "hellaswag",
-      "license": {
-        "declared_tags": [
-          "unknown"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "Rowan/hellaswag",
-            "revision": "218ec52e09a7e7462a5400043bb9a69a41d06b76",
-            "metadata_source": "https://huggingface.co/api/datasets/Rowan/hellaswag/revision/218ec52e09a7e7462a5400043bb9a69a41d06b76"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "SWAG is excluded conservatively because the collections reuse ActivityNet context sources.",
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/hellaswag/hellaswag.yaml"
-    },
-    {
-      "id": "T06",
-      "benchmark_id": "piqa",
-      "task": "piqa",
-      "name": "PIQA",
-      "language": "EN",
-      "family": "piqa",
-      "domain": "physical_reasoning",
-      "metric": "acc_norm,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "physical reasoning",
-      "member_count": 1,
-      "source_record": "piqa",
-      "license": {
-        "declared_tags": [
-          "unknown"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "ybisk/piqa",
-            "revision": "2e8ac2dffd59bac8c3c6714948f4c551a0848bb0",
-            "metadata_source": "https://huggingface.co/api/datasets/ybisk/piqa/revision/2e8ac2dffd59bac8c3c6714948f4c551a0848bb0"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/piqa/piqa.yaml"
-    },
-    {
-      "id": "T07",
-      "benchmark_id": "winogrande",
-      "task": "winogrande",
-      "name": "WinoGrande",
-      "language": "EN",
-      "family": "winogrande",
-      "domain": "coreference",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "coreference",
-      "member_count": 1,
-      "source_record": "winogrande",
-      "license": {
-        "declared_tags": [
-          "unknown"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "allenai/winogrande",
-            "revision": "01e74176c63542e6b0bcb004dcdea22d94fb67b5",
-            "metadata_source": "https://huggingface.co/api/datasets/allenai/winogrande/revision/01e74176c63542e6b0bcb004dcdea22d94fb67b5"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/winogrande/default.yaml"
-    },
-    {
-      "id": "T08",
-      "benchmark_id": "openbookqa",
-      "task": "openbookqa",
-      "name": "OpenBookQA",
-      "language": "EN",
-      "family": "openbookqa",
-      "domain": "science_reasoning",
-      "metric": "acc_norm,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "science reasoning",
-      "member_count": 1,
-      "source_record": "openbookqa",
-      "license": {
-        "declared_tags": [
-          "unknown"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "allenai/openbookqa",
-            "revision": "388097ea7776314e93a529163e0fea805b8a6454",
-            "metadata_source": "https://huggingface.co/api/datasets/allenai/openbookqa/revision/388097ea7776314e93a529163e0fea805b8a6454"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/openbookqa/openbookqa.yaml"
-    },
-    {
-      "id": "T09",
-      "benchmark_id": "sciq",
-      "task": "sciq",
-      "name": "SciQ",
-      "language": "EN",
-      "family": "sciq",
-      "domain": "science_knowledge",
-      "metric": "acc_norm,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "science knowledge",
-      "member_count": 1,
-      "source_record": "sciq",
-      "license": {
-        "declared_tags": [
-          "cc-by-nc-3.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "allenai/sciq",
-            "revision": "2c94ad3e1aafab77146f384e23536f97a4849815",
-            "metadata_source": "https://huggingface.co/api/datasets/sciq"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "NC declaration observed: evaluation-use basis must be independently resolved; this is not training permission or run approval."
-      ],
-      "definition": "lm_eval/tasks/sciq/sciq.yaml"
-    },
-    {
-      "id": "T10",
-      "benchmark_id": "boolq",
-      "task": "boolq",
-      "name": "BoolQ",
-      "language": "EN",
-      "family": "boolq",
-      "domain": "reading",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "reading",
-      "member_count": 1,
-      "source_record": "boolq",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "aps/super_glue",
-            "revision": "3de24cf8022e94f4ee4b9d55a6f539891524d646",
-            "metadata_source": "https://huggingface.co/api/datasets/super_glue"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/super_glue/boolq/default.yaml"
-    },
-    {
-      "id": "T11",
-      "benchmark_id": "copa",
-      "task": "copa",
-      "name": "COPA",
-      "language": "EN",
-      "family": "copa",
-      "domain": "causal_reasoning",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "causal reasoning",
-      "member_count": 1,
-      "source_record": "copa",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "aps/super_glue",
-            "revision": "3de24cf8022e94f4ee4b9d55a6f539891524d646",
-            "metadata_source": "https://huggingface.co/api/datasets/super_glue"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/super_glue/copa/default.yaml"
-    },
-    {
-      "id": "T12",
-      "benchmark_id": "cb",
-      "task": "cb",
-      "name": "CommitmentBank",
-      "language": "EN",
-      "family": "cb",
-      "domain": "entailment",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "entailment",
-      "member_count": 1,
-      "source_record": "cb",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "aps/super_glue",
-            "revision": "3de24cf8022e94f4ee4b9d55a6f539891524d646",
-            "metadata_source": "https://huggingface.co/api/datasets/super_glue"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/super_glue/cb/default.yaml"
-    },
-    {
-      "id": "T13",
-      "benchmark_id": "wic",
-      "task": "wic",
-      "name": "WiC",
-      "language": "EN",
-      "family": "wic",
-      "domain": "word_sense",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "word sense",
-      "member_count": 1,
-      "source_record": "wic",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "aps/super_glue",
-            "revision": "3de24cf8022e94f4ee4b9d55a6f539891524d646",
-            "metadata_source": "https://huggingface.co/api/datasets/super_glue"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/super_glue/wic/default.yaml"
-    },
-    {
-      "id": "T14",
-      "benchmark_id": "wsc273",
-      "task": "wsc273",
-      "name": "Winograd Schema Challenge",
-      "language": "EN",
-      "family": "wsc273",
-      "domain": "coreference",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "coreference",
-      "member_count": 1,
-      "source_record": "wsc273",
-      "license": {
-        "declared_tags": [
-          "cc-by-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "ErnestSDavis/winograd_wsc",
-            "revision": "8052c534a4cecd8328c0bc879f6a5aa07404c4da",
-            "metadata_source": "https://huggingface.co/api/datasets/winograd_wsc"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/wsc273/default.yaml"
-    },
-    {
-      "id": "T15",
-      "benchmark_id": "rte",
-      "task": "sglue_rte",
-      "name": "RTE",
-      "language": "EN",
-      "family": "rte",
-      "domain": "entailment",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "entailment",
-      "member_count": 1,
-      "source_record": "rte",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "aps/super_glue",
-            "revision": "3de24cf8022e94f4ee4b9d55a6f539891524d646",
-            "metadata_source": "https://huggingface.co/api/datasets/super_glue"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/super_glue/rte/default.yaml"
-    },
-    {
-      "id": "T16",
-      "benchmark_id": "anli",
-      "task": "anli_r3",
-      "name": "ANLI (R3 primary)",
-      "language": "EN",
-      "family": "anli",
-      "domain": "adversarial_entailment",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test_r3",
-      "shots": 0,
-      "rationale": "adversarial entailment",
-      "member_count": 1,
-      "source_record": "anli",
-      "license": {
-        "declared_tags": [
-          "cc-by-nc-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "facebook/anli",
-            "revision": "8e4813d81f46d313dac7892e1c28076917cfcdf9",
-            "metadata_source": "https://huggingface.co/api/datasets/anli"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "R3 is the primary protocol; R1/R2 do not increase benchmark count.",
-        "NC declaration observed: evaluation-use basis must be independently resolved; this is not training permission or run approval."
-      ],
-      "definition": "lm_eval/tasks/anli/anli_r3.yaml"
-    },
-    {
-      "id": "T17",
-      "benchmark_id": "lambada",
-      "task": "lambada_openai",
-      "name": "LAMBADA",
-      "language": "EN",
-      "family": "lambada",
-      "domain": "contextual_prediction",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "contextual prediction",
-      "member_count": 1,
-      "source_record": "lambada",
-      "license": {
-        "declared_tags": [
-          "mit"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "EleutherAI/lambada_openai",
-            "revision": "900124bf3b8235c6daf21033af9948b3f07346c4",
-            "metadata_source": "https://huggingface.co/api/datasets/EleutherAI/lambada_openai"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/lambada/lambada_openai.yaml"
-    },
-    {
-      "id": "T18",
-      "benchmark_id": "logiqa",
-      "task": "logiqa",
-      "name": "LogiQA",
-      "language": "EN",
-      "family": "logiqa",
-      "domain": "logical_reasoning",
-      "metric": "acc_norm,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "logical reasoning",
-      "member_count": 1,
-      "source_record": "logiqa",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "EleutherAI/logiqa",
-            "revision": "c1eee1b2fd0ddc87777e36490f7ad54d0b97d141",
-            "metadata_source": "https://huggingface.co/api/datasets/EleutherAI/logiqa"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/logiqa/logiqa.yaml"
-    },
-    {
-      "id": "T19",
-      "benchmark_id": "mathqa",
-      "task": "mathqa",
-      "name": "MathQA",
-      "language": "EN",
-      "family": "mathqa",
-      "domain": "mathematics_mc",
-      "metric": "acc_norm,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "mathematics mc",
-      "member_count": 1,
-      "source_record": "mathqa",
-      "license": {
-        "declared_tags": [
-          "apache-2.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "allenai/math_qa",
-            "revision": "c4f1cc784c04c4957b50c97858f23893b633eea6",
-            "metadata_source": "https://huggingface.co/api/datasets/math_qa"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/mathqa/mathqa.yaml"
-    },
-    {
-      "id": "T20",
-      "benchmark_id": "prost",
-      "task": "prost",
-      "name": "PROST",
-      "language": "EN",
-      "family": "prost",
-      "domain": "physical_reasoning",
-      "metric": "acc_norm,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "physical reasoning",
-      "member_count": 1,
-      "source_record": "prost",
-      "license": {
-        "declared_tags": [
-          "apache-2.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "corypaik/prost",
-            "revision": "b3efebf08969fc19335ba894353316878b6fa493",
-            "metadata_source": "https://huggingface.co/api/datasets/corypaik/prost"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/prost/corypaik_prost.yaml"
-    },
-    {
-      "id": "T21",
-      "benchmark_id": "sst2",
-      "task": "sst2",
-      "name": "SST-2",
-      "language": "EN",
-      "family": "sst2",
-      "domain": "sentiment",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "sentiment",
-      "member_count": 1,
-      "source_record": "sst2",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "nyu-mll/glue",
-            "revision": "bcdcba79d07bc864c1c254ccfcedcce55bcc9a8c",
-            "metadata_source": "https://huggingface.co/api/datasets/glue"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/glue/sst2/default.yaml"
-    },
-    {
-      "id": "T22",
-      "benchmark_id": "polemo2",
-      "task": "polemo2_in_multiple_choice",
-      "name": "PoLEMo2 (in-domain MC)",
-      "language": "PL",
-      "family": "polemo2",
-      "domain": "sentiment",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "openpl_polish4",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 5,
-      "rationale": "sentiment",
-      "member_count": 1,
-      "source_record": "polemo2",
-      "license": {
-        "declared_tags": [
-          "cc-by-sa-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "allegro/klej-polemo2-in",
-            "revision": "9843af31facd613eb091deaa4141df4331d4f918",
-            "metadata_source": "https://huggingface.co/api/datasets/allegro/klej-polemo2-in"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Other response-format, domain or language protocols of this source are not extra main benchmarks."
-      ],
-      "definition": "lm_eval/tasks/polemo2/polemo2_in_mc.yaml"
-    },
-    {
-      "id": "T23",
-      "benchmark_id": "8tags",
-      "task": "polish_8tags_multiple_choice",
-      "name": "8tags",
-      "language": "PL",
-      "family": "8tags",
-      "domain": "topic_classification",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "openpl_polish4",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 5,
-      "rationale": "topic classification",
-      "member_count": 1,
-      "source_record": "8tags",
-      "license": {
-        "declared_tags": [
-          "cc-by-nc-sa-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "sdadas/8tags",
-            "revision": "82ddf9c0d06ffc982aeccf2473b7ce31f2167adf",
-            "metadata_source": "https://huggingface.co/api/datasets/sdadas/8tags"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Other response-format, domain or language protocols of this source are not extra main benchmarks.",
-        "NC declaration observed: evaluation-use basis must be independently resolved; this is not training permission or run approval."
-      ],
-      "definition": "lm_eval/tasks/polish_8tags/8tags_mc.yaml"
-    },
-    {
-      "id": "T24",
-      "benchmark_id": "belebele",
-      "task": "polish_belebele_mc",
-      "name": "Belebele-PL",
-      "language": "PL",
-      "family": "belebele",
-      "domain": "reading",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "openpl_polish4",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 5,
-      "rationale": "reading",
-      "member_count": 1,
-      "source_record": "belebele",
-      "license": {
-        "declared_tags": [
-          "cc-by-sa-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "facebook/belebele",
-            "revision": "7899cdfa4e1e0d733fd77c848e2c273cb1d32be2",
-            "metadata_source": "https://huggingface.co/api/datasets/facebook/belebele/revision/7899cdfa4e1e0d733fd77c848e2c273cb1d32be2"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Other response-format, domain or language protocols of this source are not extra main benchmarks."
-      ],
-      "definition": "lm_eval/tasks/polish_belebele/belebele_mc.yaml"
-    },
-    {
-      "id": "T25",
-      "benchmark_id": "dyk",
-      "task": "polish_dyk_multiple_choice",
-      "name": "CzyWiesz / DYK",
-      "language": "PL",
-      "family": "dyk",
-      "domain": "question_relevance",
-      "metric": "f1,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "openpl_polish4",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 5,
-      "rationale": "question relevance",
-      "member_count": 1,
-      "source_record": "dyk",
-      "license": {
-        "declared_tags": [
-          "cc-by-sa-3.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "allegro/klej-dyk",
-            "revision": "dd7c3c3bb336738c853ea17c64b85d876e6714a9",
-            "metadata_source": "https://huggingface.co/api/datasets/allegro/klej-dyk"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Other response-format, domain or language protocols of this source are not extra main benchmarks."
-      ],
-      "definition": "lm_eval/tasks/polish_dyk/dyk_mc.yaml"
-    },
-    {
-      "id": "T26",
-      "benchmark_id": "ppc",
-      "task": "polish_ppc_multiple_choice",
-      "name": "Polish Paraphrase Corpus",
-      "language": "PL",
-      "family": "ppc",
-      "domain": "paraphrase",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "openpl_polish4",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 5,
-      "rationale": "paraphrase",
-      "member_count": 1,
-      "source_record": "ppc",
-      "license": {
-        "declared_tags": [
-          "cc-by-nc-sa-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "sdadas/ppc",
-            "revision": "073012dc81efb47b0fd66b0ab48bf06ddb62f528",
-            "metadata_source": "https://huggingface.co/api/datasets/sdadas/ppc"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Other response-format, domain or language protocols of this source are not extra main benchmarks.",
-        "NC declaration observed: evaluation-use basis must be independently resolved; this is not training permission or run approval."
-      ],
-      "definition": "lm_eval/tasks/polish_ppc/ppc_mc.yaml"
-    },
-    {
-      "id": "T27",
-      "benchmark_id": "psc",
-      "task": "polish_psc_multiple_choice",
-      "name": "Polish Summaries Corpus (matching)",
-      "language": "PL",
-      "family": "psc",
-      "domain": "summary_matching",
-      "metric": "f1,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "openpl_polish4",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 5,
-      "rationale": "summary matching",
-      "member_count": 1,
-      "source_record": "psc",
-      "license": {
-        "declared_tags": [
-          "cc-by-sa-3.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "allegro/klej-psc",
-            "revision": "9585582aef37e7747ef174b0ec3b74855da8bad2",
-            "metadata_source": "https://huggingface.co/api/datasets/allegro/klej-psc"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Other response-format, domain or language protocols of this source are not extra main benchmarks."
-      ],
-      "definition": "lm_eval/tasks/polish_psc/psc_mc.yaml"
-    },
-    {
-      "id": "T28",
-      "benchmark_id": "cbd",
-      "task": "polish_cbd_multiple_choice",
-      "name": "Polish Cyberbullying Dataset",
-      "language": "PL",
-      "family": "cbd",
-      "domain": "toxicity_detection",
-      "metric": "f1,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "openpl_polish4",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 5,
-      "rationale": "toxicity detection",
-      "member_count": 1,
-      "source_record": "cbd",
-      "license": {
-        "declared_tags": [
-          "cc-by-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "ptaszynski/PolishCyberbullyingDataset",
-            "revision": "be3b1236598a02eff6db05ea7ac386afaabc33e8",
-            "metadata_source": "https://huggingface.co/api/datasets/ptaszynski/PolishCyberbullyingDataset"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Other response-format, domain or language protocols of this source are not extra main benchmarks."
-      ],
-      "definition": "lm_eval/tasks/polish_cbd/cbd_mc.yaml"
-    },
-    {
-      "id": "T29",
-      "benchmark_id": "klej_ner",
-      "task": "polish_klej_ner_multiple_choice",
-      "name": "KLEJ NKJP-NER (sentence-level)",
-      "language": "PL",
-      "family": "klej_ner",
-      "domain": "sentence_entity_classification",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "openpl_polish4",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 5,
-      "rationale": "entity recognition",
-      "member_count": 1,
-      "source_record": "klej_ner",
-      "license": {
-        "declared_tags": [
-          "unknown"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "allegro/klej-nkjp-ner",
-            "revision": "bfae4047738b985bc2ad533d339dd89c3f7de00d",
-            "metadata_source": "https://huggingface.co/api/datasets/allegro/klej-nkjp-ner/revision/bfae4047738b985bc2ad533d339dd89c3f7de00d"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Other response-format, domain or language protocols of this source are not extra main benchmarks.",
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/polish_klej_ner/klej_ner_mc.yaml"
-    },
-    {
-      "id": "T30",
-      "benchmark_id": "polqa",
-      "task": "polish_polqa_open_book",
-      "name": "PolQA (open book)",
-      "language": "PL",
-      "family": "polqa",
-      "domain": "question_answering",
-      "metric": "levenshtein,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "openpl_polish4",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 5,
-      "rationale": "question answering",
-      "member_count": 1,
-      "source_record": "polqa",
-      "license": {
-        "declared_tags": [
-          "cc-by-sa-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "ipipan/polqa",
-            "revision": "d78d036ef08ab3b9f4d85a2893f4d3a0c95a6f37",
-            "metadata_source": "https://huggingface.co/api/datasets/ipipan/polqa"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Other response-format, domain or language protocols of this source are not extra main benchmarks."
-      ],
-      "definition": "lm_eval/tasks/polish_polqa/polqa_open_book.yaml"
-    },
-    {
-      "id": "T31",
-      "benchmark_id": "poquad",
-      "task": "polish_poquad_open_book",
-      "name": "PoQuAD",
-      "language": "PL",
-      "family": "poquad",
-      "domain": "question_answering",
-      "metric": "levenshtein,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "openpl_polish4",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 5,
-      "rationale": "question answering",
-      "member_count": 1,
-      "source_record": "poquad",
-      "license": {
-        "declared_tags": [
-          "cc-by-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "clarin-pl/poquad",
-            "revision": "a60f228d836fbbf990d11b4590c60b3e7f2aec2d",
-            "metadata_source": "https://huggingface.co/api/datasets/clarin-pl/poquad"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Other response-format, domain or language protocols of this source are not extra main benchmarks."
-      ],
-      "definition": "lm_eval/tasks/polish_poquad/poquad_open_book.yaml"
-    },
-    {
-      "id": "T32",
-      "benchmark_id": "mmlu",
-      "task": "mmlu",
-      "name": "MMLU",
-      "language": "EN",
-      "family": "mmlu",
-      "domain": "academic_knowledge",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "group",
-      "split": "test",
-      "shots": 5,
-      "rationale": "academic knowledge",
-      "member_count": 57,
-      "source_record": "mmlu",
-      "license": {
-        "declared_tags": [
-          "mit"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "hails/mmlu_no_train",
-            "revision": "b2e1ec9aa795adafe68e8e983248dbd4b52a1c60",
-            "metadata_source": "https://huggingface.co/api/datasets/hails/mmlu_no_train"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "57 subjects count as one benchmark; MMLU-Pro and translations are not additional sources."
-      ],
-      "definition": "lm_eval/tasks/mmlu/default/_mmlu.yaml"
-    },
-    {
-      "id": "T33",
-      "benchmark_id": "gsm8k",
-      "task": "gsm8k",
-      "name": "GSM8K",
-      "language": "EN",
-      "family": "gsm8k",
-      "domain": "mathematics_generation",
-      "metric": "exact_match,strict-match",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 5,
-      "rationale": "mathematics generation",
-      "member_count": 1,
-      "source_record": "gsm8k",
-      "license": {
-        "declared_tags": [
-          "mit"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "openai/gsm8k",
-            "revision": "740312add88f781978c0658806c59bc2815b9866",
-            "metadata_source": "https://huggingface.co/api/datasets/gsm8k"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/gsm8k/gsm8k.yaml"
-    },
-    {
-      "id": "T34",
-      "benchmark_id": "math",
-      "task": "hendrycks_math",
-      "name": "MATH",
-      "language": "EN",
-      "family": "math",
-      "domain": "competition_mathematics",
-      "metric": "exact_match,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "group",
-      "split": "test",
-      "shots": 0,
-      "rationale": "competition mathematics",
-      "member_count": 7,
-      "source_record": "math",
-      "license": {
-        "declared_tags": [
-          "mit"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "EleutherAI/hendrycks_math",
-            "revision": "21a5633873b6a120296cce3e2df9d5550074f4a3",
-            "metadata_source": "https://huggingface.co/api/datasets/EleutherAI/hendrycks_math"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/hendrycks_math/hendrycks_math.yaml"
-    },
-    {
-      "id": "T35",
-      "benchmark_id": "truthfulqa",
-      "task": "truthfulqa_mc2",
-      "name": "TruthfulQA (MC2)",
-      "language": "EN",
-      "family": "truthfulqa",
-      "domain": "truthfulness",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "truthfulness",
-      "member_count": 1,
-      "source_record": "truthfulqa",
-      "license": {
-        "declared_tags": [
-          "apache-2.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "truthfulqa/truthful_qa",
-            "revision": "741b8276f2d1982aa3d5b832d3ee81ed3b896490",
-            "metadata_source": "https://huggingface.co/api/datasets/truthful_qa"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "MC2 is normalized probability mass on true answers, not MC1 classification accuracy; source fixed QA preamble retained."
-      ],
-      "definition": "lm_eval/tasks/truthfulqa/truthfulqa_mc2.yaml"
-    },
-    {
-      "id": "T36",
-      "benchmark_id": "ifeval",
-      "task": "ifeval",
-      "name": "IFEval",
-      "language": "EN",
-      "family": "ifeval",
-      "domain": "instruction_following",
-      "metric": "prompt_level_strict_acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "train",
-      "shots": 0,
-      "rationale": "instruction following",
-      "member_count": 1,
-      "source_record": "ifeval",
-      "license": {
-        "declared_tags": [
-          "apache-2.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "google/IFEval",
-            "revision": "966cd89545d6b6acfd7638bc708b98261ca58e84",
-            "metadata_source": "https://huggingface.co/api/datasets/google/IFEval"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/ifeval/ifeval.yaml"
-    },
-    {
-      "id": "T37",
-      "benchmark_id": "llmzszl",
-      "task": "n05_llmzszl",
-      "name": "LLMzSzŁ",
-      "language": "PL",
-      "family": "llmzszl",
-      "domain": "native_exam_knowledge",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "n05_static_yaml",
-      "entrypoint_kind": "local_yaml",
-      "split": "test",
-      "shots": 0,
-      "rationale": "native exam knowledge",
-      "member_count": 1,
-      "source_record": "llmzszl",
-      "license": {
-        "declared_tags": [
-          "unknown"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "amu-cai/llmzszl-dataset",
-            "revision": "9c11d52a415147f1e2c44038a9d4d4155f064e1a",
-            "metadata_source": "https://huggingface.co/api/datasets/amu-cai/llmzszl-dataset"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Dataset card has no license tag: internal evaluation and aggregate export only, per N04. Known training overlap requires revision/ID-bound audit and common clean-subset decision.",
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "tasks/llmzszl.yaml",
-      "contamination_status": "known overlap reported; exact current revision and ID-bound clean-cohort audit required"
-    },
-    {
-      "id": "T38",
-      "benchmark_id": "squad2",
-      "task": "squadv2",
-      "name": "SQuAD 2.0",
-      "language": "EN",
-      "family": "squad2",
-      "domain": "unanswerable_reading",
-      "metric": "f1,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "legacy_task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "unanswerable reading",
-      "member_count": 1,
-      "source_record": "squad2",
-      "license": {
-        "declared_tags": [
-          "cc-by-sa-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "rajpurkar/squad_v2",
-            "revision": "3ffb306f725f7d2ce8394bc1873b24868140c412",
-            "metadata_source": "https://huggingface.co/api/datasets/squad_v2"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Do not also count QNLI, XQuAD or SQuAD completion. Preserve the legacy Task and pinned squad_v2 metric, not a fabricated ConfigurableTask replacement."
-      ],
-      "definition": "lm_eval/tasks/squadv2/task.py"
-    },
-    {
-      "id": "T39",
-      "benchmark_id": "drop",
-      "task": "drop",
-      "name": "DROP",
-      "language": "EN",
-      "family": "drop",
-      "domain": "discrete_reading",
-      "metric": "f1,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "discrete reading",
-      "member_count": 1,
-      "source_record": "drop",
-      "license": {
-        "declared_tags": [
-          "cc-by-4.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "EleutherAI/drop",
-            "revision": "619386fc7ffe6dace3cc6d3483c69b164ebf6bf3",
-            "metadata_source": "https://huggingface.co/api/datasets/EleutherAI/drop"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/drop/default.yaml"
-    },
-    {
-      "id": "T40",
-      "benchmark_id": "race",
-      "task": "race",
-      "name": "RACE (high primary)",
-      "language": "EN",
-      "family": "race",
-      "domain": "reading",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "reading",
-      "member_count": 1,
-      "source_record": "race",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "EleutherAI/race",
-            "revision": "66ca2e6374282f5e35b11559e87185db911a6900",
-            "metadata_source": "https://huggingface.co/api/datasets/EleutherAI/race"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence.",
-        "Pinned harness high protocol includes earlier article Q/A context; not a claim of full original RACE middle+high paper parity."
-      ],
-      "definition": "lm_eval/tasks/race/race.yaml"
-    },
-    {
-      "id": "T41",
-      "benchmark_id": "coqa",
-      "task": "coqa",
-      "name": "CoQA",
-      "language": "EN",
-      "family": "coqa",
-      "domain": "conversational_reading",
-      "metric": "f1,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "conversational reading",
-      "member_count": 1,
-      "source_record": "coqa",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "EleutherAI/coqa",
-            "revision": "82e11af842af6c1396f5e9a5c7de260107c50cf1",
-            "metadata_source": "https://huggingface.co/api/datasets/EleutherAI/coqa"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/coqa/default.yaml"
-    },
-    {
-      "id": "T42",
-      "benchmark_id": "nq_open",
-      "task": "nq_open",
-      "name": "Natural Questions Open",
-      "language": "EN",
-      "family": "nq_open",
-      "domain": "closed_book_knowledge",
-      "metric": "exact_match,remove_whitespace",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "closed book knowledge",
-      "member_count": 1,
-      "source_record": "nq_open",
-      "license": {
-        "declared_tags": [
-          "cc-by-sa-3.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "google-research-datasets/nq_open",
-            "revision": "5dd9790a83002ad084ddeb7c420dc716852c6f28",
-            "metadata_source": "https://huggingface.co/api/datasets/nq_open"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/nq_open/nq_open.yaml"
-    },
-    {
-      "id": "T43",
-      "benchmark_id": "triviaqa",
-      "task": "triviaqa",
-      "name": "TriviaQA",
-      "language": "EN",
-      "family": "triviaqa",
-      "domain": "closed_book_knowledge",
-      "metric": "exact_match,remove_whitespace",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "closed book knowledge",
-      "member_count": 1,
-      "source_record": "triviaqa",
-      "license": {
-        "declared_tags": [
-          "unknown"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "mandarjoshi/trivia_qa",
-            "revision": "0f7faf33a3908546c6fd5b73a660e0f8ff173c2f",
-            "metadata_source": "https://huggingface.co/api/datasets/mandarjoshi/trivia_qa/revision/0f7faf33a3908546c6fd5b73a660e0f8ff173c2f"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/triviaqa/default.yaml"
-    },
-    {
-      "id": "T44",
-      "benchmark_id": "pubmedqa",
-      "task": "pubmedqa",
-      "name": "PubMedQA",
-      "language": "EN",
-      "family": "pubmedqa",
-      "domain": "biomedical_reading",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "biomedical reading",
-      "member_count": 1,
-      "source_record": "pubmedqa",
-      "license": {
-        "declared_tags": [
-          "mit"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "bigbio/pubmed_qa",
-            "revision": "15578e80ef02c2c9636d33fdd7eb6b05b987ba60",
-            "metadata_source": "https://huggingface.co/api/datasets/bigbio/pubmed_qa"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/pubmedqa/pubmedqa.yaml"
-    },
-    {
-      "id": "T45",
-      "benchmark_id": "medmcqa",
-      "task": "medmcqa",
-      "name": "MedMCQA",
-      "language": "EN",
-      "family": "medmcqa",
-      "domain": "medical_exam_knowledge",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "medical exam knowledge",
-      "member_count": 1,
-      "source_record": "medmcqa",
-      "license": {
-        "declared_tags": [
-          "apache-2.0"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "openlifescienceai/medmcqa",
-            "revision": "91c6572c454088bf71b679ad90aa8dffcd0d5868",
-            "metadata_source": "https://huggingface.co/api/datasets/medmcqa"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [],
-      "definition": "lm_eval/tasks/medmcqa/medmcqa.yaml"
-    },
-    {
-      "id": "T46",
-      "benchmark_id": "social_iqa",
-      "task": "social_iqa",
-      "name": "Social IQa",
-      "language": "EN",
-      "family": "social_iqa",
-      "domain": "social_reasoning",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "social reasoning",
-      "member_count": 1,
-      "source_record": "social_iqa",
-      "license": {
-        "declared_tags": [
-          "unknown"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "allenai/social_i_qa",
-            "revision": "8835ceb9141d7896d9d968634a9b21ae440e3ec5",
-            "metadata_source": "https://huggingface.co/api/datasets/allenai/social_i_qa/revision/8835ceb9141d7896d9d968634a9b21ae440e3ec5"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/siqa/siqa.yaml"
-    },
-    {
-      "id": "T47",
-      "benchmark_id": "bbh",
-      "task": "bbh_fewshot",
-      "name": "BIG-Bench Hard (direct)",
-      "language": "EN",
-      "family": "bbh",
-      "domain": "formal_reasoning",
-      "metric": "exact_match,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "group",
-      "split": "test",
-      "shots": 3,
-      "rationale": "formal reasoning",
-      "member_count": 27,
-      "source_record": "bbh",
-      "license": {
-        "declared_tags": [
-          "unknown"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "lukaemon/bbh",
-            "revision": "982bb89fd79532a8ac676a61fc42eb1aeec63f99",
-            "metadata_source": "https://huggingface.co/api/datasets/lukaemon/bbh/revision/982bb89fd79532a8ac676a61fc42eb1aeec63f99"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "27 subtasks count once; direct source-provided fixed examples, not an additional CoT benchmark.",
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/bbh/fewshot/_bbh_fewshot.yaml"
-    },
-    {
-      "id": "T48",
-      "benchmark_id": "paws",
-      "task": "paws_en",
-      "name": "PAWS (English PAWS-X protocol)",
-      "language": "EN",
-      "family": "paws",
-      "domain": "adversarial_paraphrase",
-      "metric": "acc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "test",
-      "shots": 0,
-      "rationale": "adversarial paraphrase",
-      "member_count": 1,
-      "source_record": "paws",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "google-research-datasets/paws-x",
-            "revision": "4cd8187c404bda33cb1f62b49b001115862acf37",
-            "metadata_source": "https://huggingface.co/api/datasets/paws-x"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/paws-x/paws_en.yaml"
-    },
-    {
-      "id": "T49",
-      "benchmark_id": "cola",
-      "task": "cola",
-      "name": "CoLA",
-      "language": "EN",
-      "family": "cola",
-      "domain": "acceptability",
-      "metric": "mcc,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "acceptability",
-      "member_count": 1,
-      "source_record": "cola",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "nyu-mll/glue",
-            "revision": "bcdcba79d07bc864c1c254ccfcedcce55bcc9a8c",
-            "metadata_source": "https://huggingface.co/api/datasets/glue"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "MCC may be negative; do not clamp to accuracy0..1.",
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/glue/cola/default.yaml"
-    },
-    {
-      "id": "T50",
-      "benchmark_id": "record",
-      "task": "record",
-      "name": "ReCoRD",
-      "language": "EN",
-      "family": "record",
-      "domain": "entity_reading",
-      "metric": "f1,none",
-      "unit": "score",
-      "higher_is_better": true,
-      "instrument": "lm_eval_0.4.8",
-      "entrypoint_kind": "task",
-      "split": "validation",
-      "shots": 0,
-      "rationale": "entity reading",
-      "member_count": 1,
-      "source_record": "record",
-      "license": {
-        "declared_tags": [
-          "other"
-        ],
-        "basis": "revision-bound dataset-card metadata, not legal or execution approval",
-        "source_revisions": [
-          {
-            "repo_id": "aps/super_glue",
-            "revision": "3de24cf8022e94f4ee4b9d55a6f539891524d646",
-            "metadata_source": "https://huggingface.co/api/datasets/super_glue"
-          }
-        ]
-      },
-      "data_gate": "required_before_evaluation",
-      "notes": [
-        "News passages may overlap broad media sources of CoQA/RACE; the curated entity-cloze questions are a distinct benchmark, not a translation or answer-format variant.",
-        "Undeclared/umbrella data terms are a gate, not an inferred permissive licence."
-      ],
-      "definition": "lm_eval/tasks/super_glue/record/default.yaml"
-    }
-  ],
-  "verification": {
-    "source_identities": 50,
-    "source_members": 204,
-    "repository_revision_metadata": 44,
-    "declaration_files": 218,
-    "execution_ready": false,
-    "model_quality_measured": false
-  }
-}

benchmarks.css

@@ -1,27 +0,0 @@
-.bench-panel .bench-content{margin-top:20px;min-width:0;overflow-wrap:anywhere}
-.bench-panel .bench-notice{border-left:3px solid var(--acc);padding:12px 16px;background:var(--card);color:var(--soft);max-width:82ch}
-.bench-panel .bench-controls{display:flex;flex-wrap:wrap;align-items:end;gap:12px;margin:20px 0 12px}
-.bench-panel label{display:grid;gap:6px;color:var(--muted);font-size:.88rem}
-.bench-panel input,.bench-panel select,.bench-panel button{font:inherit;background:var(--card);color:var(--fg);border:1px solid var(--line2);border-radius:8px;padding:10px 12px;max-width:100%}
-.bench-panel input{width:260px}
-.bench-panel button{cursor:pointer}
-.bench-panel :focus-visible{outline:2px solid var(--acc);outline-offset:3px}
-.bench-panel .bench-summary{color:var(--soft);font-variant-numeric:tabular-nums;margin:12px 0}
-.bench-panel .bench-explanation{color:var(--muted);font-size:.9rem;max-width:82ch}
-.bench-panel .bench-wrap{overflow:auto;border:1px solid var(--line2);border-radius:12px;max-height:640px;scrollbar-gutter:stable}
-.bench-panel table{min-width:820px;width:100%;border-collapse:separate;border-spacing:0}
-.bench-panel th,.bench-panel td{padding:14px;text-align:left;white-space:normal;min-width:180px;vertical-align:top;border-bottom:1px solid var(--line)}
-.bench-panel thead th{position:sticky;top:0;background:var(--card2);z-index:2;text-transform:none;letter-spacing:normal;font-size:.9rem}
-.bench-panel th:first-child,.bench-panel td:first-child{position:sticky;left:0;width:250px;min-width:220px;background:var(--card);z-index:1}
-.bench-panel thead th:first-child{z-index:3;background:var(--card2)}
-.bench-panel .bench-task{font-weight:650;overflow-wrap:anywhere;text-transform:none;letter-spacing:normal;font-size:.9rem}
-.bench-panel .bench-meta{display:block;color:var(--muted);font-size:.82rem;line-height:1.55;margin-top:6px;overflow-wrap:anywhere}
-.bench-panel .bench-value{display:block;font-size:1.12rem;font-weight:650;font-variant-numeric:tabular-nums}
-.bench-panel .bench-state{display:inline-block;color:var(--muted);font-size:.85rem;margin-top:4px}
-.bench-panel .bench-verdict{display:block;margin:8px 0 0;font-size:.85rem}
-.bench-panel details{margin:10px 0;font-size:.84rem;color:var(--muted)}
-.bench-panel summary{cursor:pointer}
-.bench-panel code{overflow-wrap:anywhere;white-space:normal}
-.bench-panel .bench-provenance{margin-top:18px;color:var(--muted);font-size:.84rem;max-width:85ch}
-.bench-panel [hidden]{display:none!important}
-@media(max-width:640px){.bench-panel .bench-controls{display:grid;grid-template-columns:1fr}.bench-panel input,.bench-panel select,.bench-panel button{width:100%}.bench-panel th,.bench-panel td{padding:12px;min-width:180px}.bench-panel th:first-child,.bench-panel td:first-child{min-width:150px;width:150px}.bench-panel .bench-wrap{max-height:590px}.bench-panel table{min-width:760px}}

benchmarks.js

@@ -1,230 +0,0 @@
-"use strict";
-(() => {
-  const contract = window.N05Contract;
-  const plannedModels = [
-    {model_id:"planned-slayer", repo:"SlayerLab/Slayer1B-1.06"},
-    {model_id:"planned-bielik", repo:"speakleash/Bielik-1.5B-v3"},
-    {model_id:"planned-lfm", repo:"LiquidAI/LFM2.5-1.2B-Base"}
-  ];
-  const modelLabels = new Map(plannedModels.map(m => [m.repo, m.repo.split("/")[1]]));
-  const words = {
-    pl: {
-      search:"Szukaj benchmarku / dziedziny", language:"Język", all:"Wszystkie", clear:"Wyczyść filtry",
-      inventory:"Rejestr benchmarków", shown:"Pokazano", of:"z", rows:"odrębnych benchmarków",
-      task:"Benchmark / dziedzina", protocol:"Protokół / miara", source:"Źródło / licencja", planned:"Plan · brak danych w widoku", absent:"Nie dostarczono obserwacji",
-      missingSource:"Źródło wyników nie jest jeszcze podłączone. Pokazuję wyłącznie plan, nie wyniki 50 benchmarków. Historyczne liczby powyżej nie zostały do niego przepisane.",
-      loadError:"Nie udało się wczytać przypiętego kontraktu. Nie pokazuję danych zastępczych.", invalidResults:"Wyniki ukryte — nie udało się odebrać paczki pomiarowej",
-      empty:"Brak benchmarków pasujących do filtrów.",
-      explanation:"Każdy benchmark zachowuje własną miarę, jednostkę i kierunek; nie ma średniej przez benchmarki. CI95 jest opisowy (paired bootstrap), nie „po Holmie”. Brak lub blokada wyniku to stan, nigdy zero; brak istotności nie oznacza remisu. UI nie wylicza werdyktów.",
-      scope:(c, groups) => `${c.distinct_benchmarks} odrębnych benchmarków (${c.EN} EN / ${c.PL} PL), łącznie ${c.source_members} zadań źródłowych. Warianty, splity, tłumaczenia i członkowie zestawów nie są dodatkowymi benchmarkami. Benchmarki grupowe liczone raz (liczba zadań źródłowych): ${groups}.`,
-      sample:"Panel-200: najwyżej 200 dokumentów źródłowych na benchmark (nie na członka grupy); WikiText-2 — pełny strumień testowy i kanoniczna perpleksja na bajt. Full-B to osobny pełny odczyt tych samych protokołów, nie replika tablicy Open PL. Liczba shotów jest planem; actual_shots i odcięcia pochodzą z manifestu wykonania.",
-      policy:"Publikujemy wyłącznie identyfikator benchmarku, rewizję, licencję, wynik zagregowany, n i CI95 — bez pytań, odpowiedzi, przykładów few-shot i odpowiedzi modelu per pozycja. Tagi licencji to metadane karty zbioru, nie opinia prawna.",
-      planStatus:"Dobór źródeł — nie odebrany pakiet uruchomieniowy i nie pomiar jakości modeli.", revision:"Rewizja rejestru", measured:"obserwacji ok", supplied:"obserwacji dostarczonych", noResults:"bez odebranej paczki wyników",
-      group:(n) => `benchmark grupowy: ${n} zadań źródłowych, liczony raz`, licence:"licencja (tag)", planShots:"plan",
-      ci:"CI95 opisowy", noCI:"Brak CI", against:"względem", review:"Odbiór kontrastu", provenance:"Pochodzenie", weights:"SHA wag", unknown:"nie dostarczono",
-      higher:"więcej ↑", lower:"mniej ↓", counts:"n: populacja / wybrane / ocenione", metrics:"miara", state:"Stan", run:"Bieg", scale:"Protokół / skala",
-      states:{ok:"Pomiar",not_run:"Nie uruchomiono",blocked_access:"Brak dostępu",blocked_runtime:"Blokada środowiska",blocked_security:"Blokada bezpieczeństwa",blocked_judge:"Brak odebranego sędziego",unsupported:"Nieobsługiwane",failed:"Błąd wykonania",skipped:"Pominięte"},
-      verdicts:{withheld:"Werdykt wstrzymany",better:"Lepszy",worse:"Gorszy",inconclusive:"Nierozstrzygnięte — nie remis"}
-    },
-    en: {
-      search:"Search benchmark / domain", language:"Language", all:"All", clear:"Clear filters",
-      inventory:"Benchmark registry", shown:"Showing", of:"of", rows:"distinct benchmarks",
-      task:"Benchmark / domain", protocol:"Protocol / metric", source:"Source / licence", planned:"Planned · no data in this view", absent:"Observation not supplied",
-      missingSource:"The result source is not connected yet. This is the plan, not fifty benchmark results. Historical measurements above have not been copied into it.",
-      loadError:"The pinned contract could not be loaded. No substitute data is shown.", invalidResults:"Results hidden — measurement packet could not be accepted",
-      empty:"No benchmarks match the filters.",
-      explanation:"Each benchmark keeps its own metric, unit and direction; there is no average across benchmarks. CI95 is descriptive (paired bootstrap), not “Holm-adjusted”. A missing or blocked result is shown as its state, never as zero; lack of significance does not imply equivalence. The UI does not compute verdicts.",
-      scope:(c, groups) => `${c.distinct_benchmarks} distinct benchmarks (${c.EN} EN / ${c.PL} PL), ${c.source_members} source tasks in total. Variants, splits, translations and suite members are not extra benchmarks. Grouped benchmarks counted once each (source tasks): ${groups}.`,
-      sample:"Panel-200: at most 200 source documents per benchmark (not per group member); WikiText-2 uses the full test stream and canonical byte perplexity. Full-B is a separate full-data read of the same protocols, not an Open PL leaderboard replication. A benchmark's shot count is planned; actual_shots and truncation belong to the execution manifest.",
-      policy:"Published values are limited to benchmark id, revision, licence, aggregate result, n and CI95 — no questions, answers, few-shot examples or per-item model outputs. Licence tags are dataset-card metadata, not legal clearance.",
-      planStatus:"Source selection — not an accepted execution package and not a model-quality measurement.", revision:"Registry revision", measured:"ok observations", supplied:"supplied observations", noResults:"no accepted result packet",
-      group:(n) => `grouped benchmark: ${n} source tasks, counted once`, licence:"licence (tag)", planShots:"planned",
-      ci:"Descriptive CI95", noCI:"CI not supplied", against:"versus", review:"Contrast review", provenance:"Provenance", weights:"Weights SHA", unknown:"not supplied",
-      higher:"higher ↑", lower:"lower ↓", counts:"n: population / selected / scored", metrics:"metric", state:"State", run:"Run", scale:"Protocol / scale",
-      states:{ok:"Measured",not_run:"Not run",blocked_access:"Access blocked",blocked_runtime:"Runtime blocked",blocked_security:"Security blocked",blocked_judge:"Judge not accepted",unsupported:"Unsupported",failed:"Execution failed",skipped:"Skipped"},
-      verdicts:{withheld:"Verdict withheld",better:"Better",worse:"Worse",inconclusive:"Inconclusive — not equivalent"}
-    }
-  };
-  function el(tag, text, className) {
-    const node = document.createElement(tag);
-    if (text !== undefined) node.textContent = String(text);
-    if (className) node.className = className;
-    return node;
-  }
-  function option(value, text) { const node = el("option", text); node.value = value; return node; }
-  function label(text, input) { const node = el("label", text); node.append(input); return node; }
-  function modelName(model) { return modelLabels.get(model.repo) || model.repo; }
-  function number(value, locale, unit) {
-    const digits = unit === "percent" ? 2 : unit === "byte_ppl" ? 4 : 6;
-    return new Intl.NumberFormat(locale === "pl" ? "pl-PL" : "en-GB", {maximumFractionDigits:digits}).format(value);
-  }
-  function interval(ci, locale, unit, text) {
-    return ci === null ? text.noCI : `${text.ci}: [${number(ci.lower, locale, unit)}; ${number(ci.upper, locale, unit)}]`;
-  }
-  function detail(title, lines) {
-    const node = el("details");
-    node.append(el("summary", title));
-    for (const line of lines) node.append(el("p", line));
-    return node;
-  }
-  function observationCell(observation, task, model, context, locale, text) {
-    const cell = el("td");
-    if (!observation) {
-      cell.append(el("span", context.packet ? text.absent : text.planned, "bench-state"));
-      return cell;
-    }
-    const o = observation;
-    cell.append(el("span", text.states[o.state], "bench-state"));
-    if (o.state === "ok") {
-      const unit = o.unit === "percent" ? "%" : o.unit === "byte_ppl" ? "byte-PPL" : "score";
-      cell.append(el("span", `${number(o.value, locale, o.unit)} ${unit}`, "bench-value"),
-        el("span", `${text.metrics}: ${o.metric} · ${o.higher_is_better ? text.higher : text.lower}`, "bench-meta"),
-        el("span", interval(o.ci95, locale, o.unit, text), "bench-meta"));
-    }
-    cell.append(el("span", `${text.counts}: ${o.n_population ?? text.unknown} / ${o.n_selected ?? text.unknown} / ${o.n_scored}`, "bench-meta"));
-    for (const contrast of context.index.contrasts.values()) {
-      if (contrast.task_id !== task.id || contrast.model_id !== model.model_id) continue;
-      const ref = context.index.models.get(contrast.model_ref);
-      const heading = `${text.verdicts[contrast.verdict]} ${text.against} ${modelName(ref)}`;
-      cell.append(el("span", heading, "bench-verdict"));
-      if (contrast.verdict !== "withheld") {
-        cell.append(detail(text.review, [
-          `Δ: ${number(contrast.delta, locale, o.unit)}`,
-          interval(contrast.ci95, locale, o.unit, text),
-          `p_raw: ${contrast.p_raw}; p_holm: ${contrast.p_holm}; family_size: ${contrast.family_size}`,
-          `${contrast.review.actor} · artifact_sha256: ${contrast.review.artifact_sha256}`
-        ]));
-      }
-    }
-    cell.append(detail(text.provenance, [
-      `source_id_digest: ${o.source_id_digest ?? text.unknown}`,
-      `results_sha256: ${o.results_sha256 ?? text.unknown}`,
-      `runner_sha256: ${o.runner_sha256 ?? text.unknown}`
-    ]));
-    return cell;
-  }
-  function build(section, context) {
-    const locale = section.dataset.locale;
-    const text = words[locale];
-    const inventory = context.inventory;
-    const models = context.packet && context.packet.models.length ? context.packet.models : plannedModels;
-    const root = section.querySelector(".bench-content");
-    root.removeAttribute("role");
-    root.replaceChildren();
-    const message = context.error ? `${text.invalidResults}: ${context.error}` : context.packet ? `${text.run}: ${context.packet.run_id} · ${text.scale}: ${context.packet.protocol_id}` : text.missingSource;
-    const notice = el("p", message, "bench-notice");
-    const groups = inventory.rows.filter(task => task.entrypoint_kind === "group").map(task => `${task.name}: ${task.member_count}`).join("; ");
-    const scope = el("p", text.scope(inventory.counts, groups), "bench-explanation");
-    const search = el("input");
-    search.type = "search";
-    const language = el("select");
-    language.append(option("all", text.all), option("PL", "PL"), option("EN", "EN"));
-    const clear = el("button", text.clear);
-    clear.type = "button";
-    const controls = el("div", undefined, "bench-controls");
-    controls.append(label(text.search, search), label(text.language, language), clear);
-    const summary = el("p", undefined, "bench-summary");
-    summary.setAttribute("role", "status");
-    summary.setAttribute("aria-live", "polite");
-    const explanation = el("p", text.explanation, "bench-explanation");
-    explanation.id = `bench-note-${locale}`;
-    const wrap = el("div", undefined, "bench-wrap");
-    wrap.tabIndex = 0;
-    wrap.setAttribute("role", "region");
-    wrap.setAttribute("aria-label", text.inventory);
-    const table = el("table");
-    table.setAttribute("aria-labelledby", `bench-title-${locale}`);
-    table.setAttribute("aria-describedby", explanation.id);
-    const head = el("thead");
-    const header = el("tr");
-    for (const name of [text.task, text.protocol, text.source]) { const th = el("th", name); th.scope = "col"; header.append(th); }
-    for (const model of models) {
-      const th = el("th", modelName(model));
-      th.scope = "col";
-      if (context.packet && context.index.models.has(model.model_id)) th.append(detail(text.provenance, [
-        `repo: ${model.repo}`, `revision: ${model.revision ?? text.unknown}`, `${text.weights}: ${model.weights_sha256 ?? text.unknown}`
-      ]));
-      header.append(th);
-    }
-    head.append(header);
-    const body = el("tbody");
-    table.append(head, body);
-    wrap.append(table);
-    const empty = el("p", text.empty);
-    const origin = el("div", undefined, "bench-provenance");
-    const planLink = el("a", "N05 · tasks_50_v01.json");
-    planLink.href = "benchmarks-plan.json";
-    const schemaLink = el("a", "N05 · results.schema.json");
-    schemaLink.href = "benchmarks.schema.json";
-    origin.append(el("p", text.planStatus), el("p", text.sample), el("p", text.policy), planLink, el("span", " · "), schemaLink,
-      el("p", `${text.revision}: ${contract.revision}`), el("p", `inventory SHA-256: ${contract.inventorySHA}`), el("p", `schema SHA-256: ${contract.schemaSHA}`));
-    if (context.packet) origin.append(el("p", `packet SHA-256: ${context.packetSHA}`));
-    root.append(notice, scope, controls, summary, explanation, wrap, empty, origin);
-    const scale = context.packet ? context.packet.protocol_id : contract.protocolIds.join(" / ");
-    function render() {
-      const query = search.value.trim().toLocaleLowerCase(locale);
-      const tasks = inventory.rows.filter(task => (language.value === "all" || task.language === language.value) &&
-        `${task.id} ${task.benchmark_id} ${task.name} ${task.family} ${task.domain}`.toLocaleLowerCase(locale).includes(query));
-      const fragment = document.createDocumentFragment();
-      for (const task of tasks) {
-        const row = el("tr");
-        const th = el("th", `${task.id} · ${task.name}`, "bench-task");
-        th.scope = "row";
-        th.append(el("span", `${task.language} · ${task.family} / ${task.domain}`, "bench-meta"));
-        if (task.entrypoint_kind === "group") th.append(el("span", text.group(task.member_count), "bench-meta"));
-        const procedure = el("td", scale);
-        procedure.append(el("span", `${task.instrument} · ${task.split} · ${text.planShots}: ${task.shots}-shot`, "bench-meta"),
-          el("span", `${text.metrics}: ${task.metric} · ${task.unit} · ${task.higher_is_better ? text.higher : text.lower}`, "bench-meta"));
-        const source = el("td");
-        for (const pin of task.license.source_revisions) source.append(el("span", `${pin.repo_id} @ ${pin.revision ?? text.unknown}`, "bench-meta"));
-        source.append(el("span", `${text.licence}: ${task.license.declared_tags.join(", ") || text.unknown}`, "bench-meta"));
-        row.append(th, procedure, source);
-        for (const model of models) {
-          const o = context.index && context.index.observations.get(contract.key(task.id, model.model_id, context.packet.protocol_id));
-          row.append(observationCell(o, task, model, context, locale, text));
-        }
-        fragment.append(row);
-      }
-      body.replaceChildren(fragment);
-      const measured = context.packet ? `${context.packet.observations.filter(o => o.state === "ok").length} ${text.measured} / ${context.packet.observations.length} ${text.supplied}` : text.noResults;
-      summary.textContent = `${inventory.protocol} · ${text.shown} ${tasks.length} ${text.of} ${inventory.rows.length} ${text.rows} · ${measured}`;
-      empty.hidden = tasks.length !== 0;
-      wrap.hidden = tasks.length === 0;
-    }
-    search.addEventListener("input", render);
-    language.addEventListener("change", render);
-    clear.addEventListener("click", () => { search.value = ""; language.value = "all"; render(); search.focus(); });
-    render();
-  }
-  async function read(path, expectedSHA) {
-    const response = await fetch(path, {cache:"no-store"});
-    if (!response.ok) throw new Error(`${path}: HTTP ${response.status}`);
-    const bytes = await response.arrayBuffer();
-    const hash = await crypto.subtle.digest("SHA-256", bytes);
-    const sha = [...new Uint8Array(hash)].map(v => v.toString(16).padStart(2, "0")).join("");
-    if (expectedSHA && sha !== expectedSHA) throw new Error(`Pinned bytes changed: ${path}`);
-    return {data:JSON.parse(new TextDecoder().decode(bytes)), sha};
-  }
-  async function start() {
-    const [plan, schema] = await Promise.all([
-      read("benchmarks-plan.json", contract.inventorySHA), read("benchmarks.schema.json", contract.schemaSHA)
-    ]);
-    const context = {inventory:plan.data, packet:null, index:null, error:null, packetSHA:null};
-    try {
-      const feed = await read("benchmarks-feed.json");
-      if (feed.data.results !== null) {
-        if (feed.data.results !== "benchmarks-results.json") throw new Error("Only the local accepted result path is allowed");
-        const results = await read(feed.data.results);
-        context.index = contract.validate(results.data, plan.data, schema.data, contract.revision);
-        context.packet = results.data;
-        context.packetSHA = results.sha;
-      }
-    } catch (error) { context.error = error.message; }
-    document.querySelectorAll(".bench-panel").forEach(section => build(section, context));
-  }
-  start().catch(error => {
-    document.querySelectorAll(".bench-panel").forEach(section => {
-      section.querySelector(".bench-content").replaceChildren(el("p", `${words[section.dataset.locale].loadError} (${error.message})`, "bench-notice"));
-    });
-  });
-})();

benchmarks.schema.json

@@ -1,596 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "urn:kolektyw:n05:benchmark-results:1:protocol-0.3",
-  "type": "object",
-  "properties": {
-    "schema_version": {
-      "const": 1
-    },
-    "protocol_id": {
-      "enum": ["N05-50-v0.3-panel200", "N05-50-v0.3-fullB"]
-    },
-    "run_id": {
-      "type": "string",
-      "minLength": 1
-    },
-    "models": {
-      "type": "array",
-      "items": {
-        "type": "object",
-        "properties": {
-          "model_id": {
-            "type": "string",
-            "minLength": 1
-          },
-          "repo": {
-            "type": "string",
-            "minLength": 1
-          },
-          "revision": {
-            "type": [
-              "string",
-              "null"
-            ]
-          },
-          "weights_sha256": {
-            "anyOf": [
-              {
-                "type": "string",
-                "pattern": "^[0-9a-f]{64}$"
-              },
-              {
-                "type": "null"
-              }
-            ]
-          }
-        },
-        "required": [
-          "model_id",
-          "repo",
-          "revision",
-          "weights_sha256"
-        ],
-        "additionalProperties": false
-      }
-    },
-    "tasks": {
-      "type": "array",
-      "items": {
-        "type": "object",
-        "properties": {
-          "task_id": {
-            "type": "string",
-            "pattern": "^T(0[1-9]|[1-4][0-9]|50)$"
-          },
-          "task": {
-            "type": "string",
-            "minLength": 1
-          },
-          "family": {
-            "type": "string",
-            "minLength": 1
-          },
-          "language": {
-            "enum": [
-              "PL",
-              "EN"
-            ]
-          },
-          "split": {
-            "type": "string",
-            "minLength": 1
-          }
-        },
-        "required": [
-          "task_id",
-          "task",
-          "family",
-          "language",
-          "split"
-        ],
-        "additionalProperties": false
-      }
-    },
-    "observations": {
-      "type": "array",
-      "items": {
-        "$ref": "#/$defs/observation"
-      }
-    },
-    "contrasts": {
-      "type": "array",
-      "items": {
-        "$ref": "#/$defs/contrast"
-      }
-    },
-    "provenance": {
-      "type": "object",
-      "properties": {
-        "inventory_commit": {
-          "type": "string",
-          "pattern": "^[0-9a-f]{40}$"
-        },
-        "kind": {
-          "enum": [
-            "measurement",
-            "contract_example"
-          ]
-        }
-      },
-      "required": [
-        "inventory_commit",
-        "kind"
-      ],
-      "additionalProperties": false
-    }
-  },
-  "required": [
-    "schema_version",
-    "protocol_id",
-    "run_id",
-    "models",
-    "tasks",
-    "observations",
-    "contrasts",
-    "provenance"
-  ],
-  "additionalProperties": false,
-  "$defs": {
-    "ci95": {
-      "type": "object",
-      "properties": {
-        "lower": {
-          "type": "number"
-        },
-        "upper": {
-          "type": "number"
-        },
-        "level": {
-          "const": 0.95
-        },
-        "method": {
-          "const": "paired_bootstrap"
-        },
-        "replicates": {
-          "const": 10000
-        },
-        "seed": {
-          "const": 20261028
-        }
-      },
-      "required": [
-        "lower",
-        "upper",
-        "level",
-        "method",
-        "replicates",
-        "seed"
-      ],
-      "additionalProperties": false
-    },
-    "observation": {
-      "type": "object",
-      "properties": {
-        "task_id": {
-          "type": "string",
-          "pattern": "^T(0[1-9]|[1-4][0-9]|50)$"
-        },
-        "model_id": {
-          "type": "string",
-          "minLength": 1
-        },
-        "protocol_id": {
-          "enum": ["N05-50-v0.3-panel200", "N05-50-v0.3-fullB"]
-        },
-        "metric": {
-          "type": "string",
-          "minLength": 1
-        },
-        "unit": {
-          "enum": [
-            "percent",
-            "score",
-            "byte_ppl"
-          ]
-        },
-        "higher_is_better": {
-          "type": "boolean"
-        },
-        "n_population": {
-          "type": [
-            "integer",
-            "null"
-          ],
-          "minimum": 0
-        },
-        "n_selected": {
-          "type": [
-            "integer",
-            "null"
-          ],
-          "minimum": 0
-        },
-        "n_scored": {
-          "type": "integer",
-          "minimum": 0
-        },
-        "state": {
-          "enum": [
-            "ok",
-            "not_run",
-            "blocked_access",
-            "blocked_runtime",
-            "blocked_security",
-            "blocked_judge",
-            "unsupported",
-            "failed",
-            "skipped"
-          ]
-        },
-        "value": {
-          "type": [
-            "number",
-            "null"
-          ]
-        },
-        "ci95": {
-          "anyOf": [
-            {
-              "type": "object",
-              "properties": {
-                "lower": {
-                  "type": "number"
-                },
-                "upper": {
-                  "type": "number"
-                },
-                "level": {
-                  "const": 0.95
-                },
-                "method": {
-                  "const": "paired_bootstrap"
-                },
-                "replicates": {
-                  "const": 10000
-                },
-                "seed": {
-                  "const": 20261028
-                }
-              },
-              "required": [
-                "lower",
-                "upper",
-                "level",
-                "method",
-                "replicates",
-                "seed"
-              ],
-              "additionalProperties": false
-            },
-            {
-              "type": "null"
-            }
-          ]
-        },
-        "source_id_digest": {
-          "anyOf": [
-            {
-              "type": "string",
-              "pattern": "^[0-9a-f]{64}$"
-            },
-            {
-              "type": "null"
-            }
-          ]
-        },
-        "results_sha256": {
-          "anyOf": [
-            {
-              "type": "string",
-              "pattern": "^[0-9a-f]{64}$"
-            },
-            {
-              "type": "null"
-            }
-          ]
-        },
-        "runner_sha256": {
-          "anyOf": [
-            {
-              "type": "string",
-              "pattern": "^[0-9a-f]{64}$"
-            },
-            {
-              "type": "null"
-            }
-          ]
-        }
-      },
-      "required": [
-        "task_id",
-        "model_id",
-        "protocol_id",
-        "metric",
-        "unit",
-        "higher_is_better",
-        "n_population",
-        "n_selected",
-        "n_scored",
-        "state",
-        "value",
-        "ci95",
-        "source_id_digest",
-        "results_sha256",
-        "runner_sha256"
-      ],
-      "additionalProperties": false,
-      "allOf": [
-        {
-          "if": {
-            "properties": {
-              "state": {
-                "const": "ok"
-              }
-            }
-          },
-          "then": {
-            "properties": {
-              "value": {
-                "type": "number"
-              },
-              "n_scored": {
-                "type": "integer",
-                "minimum": 1
-              },
-              "source_id_digest": {
-                "type": "string",
-                "pattern": "^[0-9a-f]{64}$"
-              },
-              "results_sha256": {
-                "type": "string",
-                "pattern": "^[0-9a-f]{64}$"
-              },
-              "runner_sha256": {
-                "type": "string",
-                "pattern": "^[0-9a-f]{64}$"
-              }
-            }
-          },
-          "else": {
-            "properties": {
-              "value": {
-                "type": "null"
-              },
-              "ci95": {
-                "type": "null"
-              }
-            }
-          }
-        }
-      ]
-    },
-    "contrast": {
-      "type": "object",
-      "properties": {
-        "task_id": {
-          "type": "string",
-          "pattern": "^T(0[1-9]|[1-4][0-9]|50)$"
-        },
-        "model_id": {
-          "type": "string",
-          "minLength": 1
-        },
-        "protocol_id": {
-          "enum": ["N05-50-v0.3-panel200", "N05-50-v0.3-fullB"]
-        },
-        "model_ref": {
-          "type": "string",
-          "minLength": 1
-        },
-        "delta": {
-          "type": [
-            "number",
-            "null"
-          ]
-        },
-        "ci95": {
-          "anyOf": [
-            {
-              "type": "object",
-              "properties": {
-                "lower": {
-                  "type": "number"
-                },
-                "upper": {
-                  "type": "number"
-                },
-                "level": {
-                  "const": 0.95
-                },
-                "method": {
-                  "const": "paired_bootstrap"
-                },
-                "replicates": {
-                  "const": 10000
-                },
-                "seed": {
-                  "const": 20261028
-                }
-              },
-              "required": [
-                "lower",
-                "upper",
-                "level",
-                "method",
-                "replicates",
-                "seed"
-              ],
-              "additionalProperties": false
-            },
-            {
-              "type": "null"
-            }
-          ]
-        },
-        "p_raw": {
-          "type": [
-            "number",
-            "null"
-          ],
-          "minimum": 0,
-          "maximum": 1
-        },
-        "p_holm": {
-          "type": [
-            "number",
-            "null"
-          ],
-          "minimum": 0,
-          "maximum": 1
-        },
-        "family_size": {
-          "type": "integer",
-          "minimum": 1
-        },
-        "verdict": {
-          "enum": [
-            "withheld",
-            "better",
-            "worse",
-            "inconclusive"
-          ]
-        },
-        "review": {
-          "type": "object",
-          "properties": {
-            "status": {
-              "enum": [
-                "pending",
-                "accepted",
-                "rejected"
-              ]
-            },
-            "actor": {
-              "type": [
-                "string",
-                "null"
-              ]
-            },
-            "artifact_sha256": {
-              "anyOf": [
-                {
-                  "type": "string",
-                  "pattern": "^[0-9a-f]{64}$"
-                },
-                {
-                  "type": "null"
-                }
-              ]
-            }
-          },
-          "required": [
-            "status",
-            "actor",
-            "artifact_sha256"
-          ],
-          "additionalProperties": false,
-          "allOf": [
-            {
-              "if": {
-                "properties": {
-                  "status": {
-                    "const": "accepted"
-                  }
-                }
-              },
-              "then": {
-                "properties": {
-                  "actor": {
-                    "type": "string",
-                    "minLength": 1
-                  },
-                  "artifact_sha256": {
-                    "type": "string",
-                    "pattern": "^[0-9a-f]{64}$"
-                  }
-                }
-              }
-            }
-          ]
-        }
-      },
-      "required": [
-        "task_id",
-        "model_id",
-        "protocol_id",
-        "model_ref",
-        "delta",
-        "ci95",
-        "p_raw",
-        "p_holm",
-        "family_size",
-        "verdict",
-        "review"
-      ],
-      "additionalProperties": false,
-      "allOf": [
-        {
-          "if": {
-            "properties": {
-              "verdict": {
-                "enum": [
-                  "better",
-                  "worse",
-                  "inconclusive"
-                ]
-              }
-            }
-          },
-          "then": {
-            "properties": {
-              "review": {
-                "properties": {
-                  "status": {
-                    "const": "accepted"
-                  }
-                }
-              },
-              "delta": {
-                "type": "number"
-              },
-              "p_raw": {
-                "type": "number"
-              },
-              "p_holm": {
-                "type": "number"
-              }
-            }
-          }
-        },
-        {
-          "if": {
-            "properties": {
-              "review": {
-                "properties": {
-                  "status": {
-                    "enum": [
-                      "pending",
-                      "rejected"
-                    ]
-                  }
-                }
-              }
-            }
-          },
-          "then": {
-            "properties": {
-              "verdict": {
-                "const": "withheld"
-              }
-            }
-          }
-        }
-      ]
-    }
-  }
-}

import-benchmarks.cjs

@@ -1,34 +0,0 @@
-"use strict";
-// Offline adapter, not a scorer or publisher. Validates N05 v0.3's pinned wire
-// contract (plan, schema and revision pins live in benchmarks-contract.js) and
-// cross-field invariants before replacing the local result feed. Contract
-// examples, legacy v0.2 protocol ids and short inventory pins are refused.
-// Usage: node import-benchmarks.cjs PATH_TO_MEASUREMENT_PACKET.json
-const fs = require("node:fs");
-const path = require("node:path");
-const crypto = require("node:crypto");
-const contract = require("./benchmarks-contract.js");
-function pinned(name, expected) {
-  const raw = fs.readFileSync(path.join(__dirname, name));
-  if (crypto.createHash("sha256").update(raw).digest("hex") !== expected) throw new Error(`Pinned input changed: ${name}`);
-  return JSON.parse(raw.toString("utf8"));
-}
-function main() {
-  if (process.argv.length !== 3) throw new Error("Usage: node import-benchmarks.cjs PACKET.json");
-  const inventory = pinned("benchmarks-plan.json", contract.inventorySHA);
-  const schema = pinned("benchmarks.schema.json", contract.schemaSHA);
-  const raw = fs.readFileSync(process.argv[2]);
-  const packet = JSON.parse(raw.toString("utf8"));
-  contract.validate(packet, inventory, schema, contract.revision);
-  // Validation happens before any write. Feed configuration is written last.
-  const output = path.join(__dirname, "benchmarks-results.json");
-  const staging = output + ".new";
-  fs.writeFileSync(staging, raw);
-  fs.renameSync(staging, output);
-  const feed = path.join(__dirname, "benchmarks-feed.json");
-  fs.writeFileSync(feed + ".new", '{\n  "results": "benchmarks-results.json"\n}\n');
-  fs.renameSync(feed + ".new", feed);
-  console.log(JSON.stringify({run_id:packet.run_id,protocol_id:packet.protocol_id,kind:packet.provenance.kind,
-    observations:packet.observations.length,results_sha256:crypto.createHash("sha256").update(raw).digest("hex")}));
-}
-try { main(); } catch (error) { console.error(`STOP: ${error.message}`); process.exitCode = 1; }

index.html

@@ -95,9 +95,6 @@
     figure:has(> img) img { width:760px; max-width:none; }
   }
 </style>
-<link rel="stylesheet" href="benchmarks.css">
-<script src="benchmarks-contract.js" defer></script>
-<script src="benchmarks.js" defer></script>
 </head>
 <body data-lang="en">
 <nav class="lang" aria-label="Language"><button type="button" data-set="en" aria-pressed="true">EN</button><button type="button" data-set="pl" aria-pressed="false">PL</button></nav>
@@ -245,11 +242,9 @@
   used a constant learning rate; a final decay has not been applied, so these are not end-of-training numbers for the model line.</p>
 </section>
 
-<section class="bench-panel" data-locale="en" aria-labelledby="bench-title-en">
-  <h2 id="bench-title-en">Benchmark campaign · N05-50 v0.3</h2>
-  <p class="note">50 distinct benchmarks (38 EN / 12 PL), not fifty completed measurements. They cover 204 source tasks: the grouped BLiMP (67), MMLU (57), BBH (27) and MATH (7) each count as one benchmark. Each benchmark reports its own result with CI95; there is no cross-benchmark average. Panel-200 (at most 200 documents per benchmark) and full-B are separate scales.</p>
-  <div class="bench-content" role="status">Loading benchmark registry…</div>
-  <noscript><p>JavaScript is required for filtering. <a href="benchmarks-plan.json">Download the pinned benchmark registry</a>.</p></noscript>
+<section aria-labelledby="bench-title-en">
+  <h2 id="bench-title-en">Benchmarks</h2>
+  <p>Results on fifty distinct public benchmarks (38 English, 12 Polish), run with one protocol and checked for contamination against the training corpus, are in a separate Space: <a href="https://huggingface.co/spaces/SlayerLab/Slayer1B-Benchmarks">Slayer1B Benchmarks</a>.</p>
 </section>
 
 <section>
@@ -431,11 +426,9 @@
   szła przy stałym tempie uczenia; końcowego wygaszania nie zastosowano, więc to nie są końcowe liczby tej linii modelu.</p>
 </section>
 
-<section class="bench-panel" data-locale="pl" aria-labelledby="bench-title-pl">
-  <h2 id="bench-title-pl">Kampania benchmarków · N05-50 v0.3</h2>
-  <p class="note">50 odrębnych benchmarków (38 EN / 12 PL), nie pięćdziesiąt wykonanych pomiarów. Obejmują 204 zadania źródłowe: grupowe BLiMP (67), MMLU (57), BBH (27) i MATH (7) liczą się każdy jako jeden benchmark. Każdy benchmark ma własny wynik z CI95; nie ma średniej przez benchmarki. Panel-200 (najwyżej 200 dokumentów na benchmark) i full-B to osobne skale.</p>
-  <div class="bench-content" role="status">Wczytuję rejestr benchmarków…</div>
-  <noscript><p>Filtrowanie wymaga JavaScript. <a href="benchmarks-plan.json">Pobierz przypięty rejestr benchmarków</a>.</p></noscript>
+<section aria-labelledby="bench-title-pl">
+  <h2 id="bench-title-pl">Benchmarki</h2>
+  <p>Wyniki na pięćdziesięciu odrębnych publicznych benchmarkach (38 angielskich, 12 polskich), liczone jednym protokołem i sprawdzone pod kątem kontaminacji względem korpusu treningowego, są w osobnym Space: <a href="https://huggingface.co/spaces/SlayerLab/Slayer1B-Benchmarks">Slayer1B Benchmarks</a>.</p>
 </section>
 
 <section>