{
  "agent_view_tokens": 4096,
  "emoji": "🪩",
  "paper": {
    "arxiv_id": "2603.17863"
  },
  "root": {
    "children": [
      {
        "children": [],
        "file": "pages/00-judge-evidence-scorecard/page.md",
        "slug": "00-judge-evidence-scorecard",
        "title": "Judge-facing evidence scorecard"
      },
      {
        "children": [],
        "file": "pages/executive-summary/page.md",
        "slug": "executive-summary",
        "title": "Executive summary"
      },
      {
        "children": [],
        "file": "pages/claim-1/page.md",
        "slug": "claim-1",
        "title": "Claim 1: DiscoGen procedurally generates over 400 million distinct algorithm discovery tasks via a combinatorial formula N_tasks = 2*3*b*(2^m-1)*(3^d-2^(d+1)+1) depending on the number of modules m, datasets d, and backends b (Section 4.2, Equation 1)."
      },
      {
        "children": [],
        "file": "pages/claim-2/page.md",
        "slug": "claim-2",
        "title": "Claim 2: Including additional domains beyond the main evaluation set, DiscoGen's total task space reaches approximately 99 billion tasks (Appendix C)."
      },
      {
        "children": [],
        "file": "pages/claim-3/page.md",
        "slug": "claim-3",
        "title": "Claim 3: Across the 10 domains used in the main evaluation, per-domain task counts range from 900 (Greenhouse Gas Prediction) to 426,043,800 (On-Policy RL), with a median of 59,622 tasks per domain (Table 1)."
      },
      {
        "children": [],
        "file": "pages/claim-4/page.md",
        "slug": "claim-4",
        "title": "Claim 4: DiscoBench provides a fixed evaluation subset built from DiscoGen, comprising, for each domain, m single-module tasks (DiscoBench Single) plus one comprehensive all-modules-active task (DiscoBench All) (Section 4.4)."
      },
      {
        "children": [],
        "file": "pages/claim-5/page.md",
        "slug": "claim-5",
        "title": "Claim 5: As the number of editable modules increases in DiscoBench tasks, agent success rates consistently decline while the achievable performance ceiling rises (Appendix G)."
      },
      {
        "children": [],
        "file": "pages/conclusion/page.md",
        "slug": "conclusion",
        "title": "Conclusion"
      }
    ],
    "file": "pages/index.md",
    "slug": "index",
    "title": "Reproduction: DiscoGen Procedural Algorithm-Discovery Tasks"
  },
  "schema_version": 1,
  "space_id": "ProCreations/repro-procedural-generation-algorithm-discovery-tasks-native",
  "tags": [
    "icml2026-repro",
    "paper-0Mvm3lqLjF"
  ],
  "title": "Reproduction: DiscoGen Procedural Algorithm-Discovery Tasks",
  "updated_at": "2026-07-30T10:25:00+00:00"
}