{
 "schema": "cain.agi_evidence_index.v1",
 "agi_status": "NOT ACHIEVED",
 "entries": [
  {
   "id": "E123-OW",
   "name": "Open-world intelligence breakthrough (capability acquisition, causal transfer & governance)",
   "status": "PARTIAL (16 PASS / 1 PARTIAL / 3 BLOCKED)",
   "commit": "1c7fcb6d6",
   "statistical_method": "Exact two-sided paired McNemar + Holm-Bonferroni + Wilson 95% CI + 10-bin Brier/ECE + Token F1 (AMA-Bench) + 2-attempt exact match (ARC-AGI-2)",
   "metric": "32 unfamiliar task families (160 sealed): full 0.906 vs compute-matched 0.188 (p=0.00e+00); Strategic Test (Software->Cybersecurity, n=36): 1.000 vs base Qwen2.5-0.5B 0.389; 48 dynamic causal worlds: 0.917 vs 2x passive 0.000; 6 verticals: 10 positive + 12/12 negative rejected; 6-arm real LLM (n=24): 0.000->0.292; AMA-Bench fresh F1 0.2444, ARC-AGI-2 0/6; multiprocess TCP MCPGate 14/14 (0 after KILL)",
   "verifier": "30/30 checks passed",
   "bundle": "e123-open-world-intelligence-2026-11-20",
   "limits": "G11 (12h wall-clock) BLOCKED, G18 (external human review) BLOCKED, G19 (separate admin domain) BLOCKED; 0 neural weight updates; ARC-AGI-2 unsolved (0/6), ARC-AGI-3 unavailable, SWE-bench deferred to E124, hosted APIs blocked; loopback_multiprocess_execution; AGI not achieved"
  },
  {
   "id": "E124",
   "name": "CAIN long-horizon agent evaluation",
   "status": "MEASURED",
   "statistical_method": "Bounded 50% time-horizon estimate across 6-task CAIN-native suite (18 runs)",
   "metric": "70B open model: 13/18 on 6-task CAIN-native suite; 50% horizon ~2.0h (below METR frontier 6.4-17.4h); governance/evidence axis measured separately",
   "verifier": "9/9 checks passed",
   "bundle": "e124-long-horizon-agent-2026-11-20",
   "limits": "CAIN-native 6-task suite, NOT METR-comparable; below METR frontier; AGI not achieved"
  },
  {
   "id": "E123",
   "name": "METR time-horizon benchmark comparison",
   "status": "MEASURED \u00b7 UNRANKED",
   "statistical_method": "Side-by-side comparison against published METR TH1.1 benchmark metadata with separate governance axis",
   "metric": "Governance & verifiable-evidence axis evaluated separately from general autonomy; verdict honestly UNRANKED on METR general autonomy",
   "verifier": "10/10 checks passed",
   "bundle": "e123-metr-time-horizon-comparison-2026-11-20",
   "limits": "CAIN-42 is not ranked on METR TH1.1 general autonomy; governance lead is a separate axis; AGI not achieved"
  },
  {
   "id": "E122",
   "name": "Neural generalization & autonomous discovery organism",
   "status": "PARTIAL \u00b7 12H NEURAL RUNNING (15 PASS / 3 PARTIAL)",
   "commit": "e65a75971",
   "statistical_method": "Exact two-sided McNemar + Holm-Bonferroni + Wilson 95% CI + Token F1 (AMA-Bench) + 2-attempt exact match (ARC-AGI-2)",
   "metric": "Real local PyTorch LLMs (Qwen2.5-0.5B/1.5B, SmolLM2-135M): unfamiliar neural abstraction 0.000(E120)/0.146(alone)->0.917 (n=48, p=1.50e-11); AMA-Bench (MIT, n=20) F1 0.3158->0.3538; ARC-AGI-2 0/8; open-world Python repair 0.00->1.00; neural+causal 0.250->0.750; governed neural TCP MCPGate 9/9 (0 after KILL)",
   "verifier": "37/37 checks passed",
   "bundle": "e122-neural-generalization-organism-2026-11-20",
   "limits": "local CPU models only (frontier APIs blocked); 0 weight updates; ARC-AGI-2 0/8; E119/E120/E122 wall-clock missions RUNNING (PARTIAL); external human review pending (G18 PARTIAL); AGI not achieved"
  },
  {
   "id": "E121",
   "name": "Independent verification & third-party audit pack",
   "status": "MEASURED",
   "commit": "2dee32731",
   "statistical_method": "Clean-room stdlib independent verification under unprivileged OS user nobody",
   "metric": "Independent verification harness & audit pack reproduced cleanly from clean checkout as nobody",
   "verifier": "17/17 checks passed",
   "bundle": "e121-independent-verification-2026-11-20",
   "limits": "verification harness & evidence integrity audit; external human reviewer still pending; AGI not achieved"
  },
  {
   "id": "E120",
   "name": "Generalizing, self-improving VAGI organism",
   "status": "PARTIAL \u00b7 12H RUNNING (17 PASS / 3 PARTIAL)",
   "commit": "8c6ef11a3",
   "statistical_method": "Exact two-sided McNemar + Holm-Bonferroni + Wilson 95% CI + Brier/ECE",
   "metric": "4 OOD conditions +0.438 to +1.000 (Holm p<0.001, 0 shortcuts); causal planning 0.275->0.775; 8-role research loop; 14 self-improve candidates; 5/5 verticals; 4 pos + 2 neg-rejected transfers; matched-compute collective 1.000 vs 0.483; 8-layer memory 1.000 vs 0.250 (0/20 poison); real cain/mcp_proxy + WAL kill 0 after",
   "verifier": "47/47 checks passed",
   "bundle": "e120-generalizing-vagi-organism-2026-11-20",
   "limits": "constructed symbolic/grid suites + public datasets; E119 6h & E120 12h RUNNING (PARTIAL); no external human reviewer (G19 PARTIAL); AGI not achieved"
  },
  {
   "id": "E119",
   "name": "Learned macro grammar + real tasks",
   "status": "MEASURED \u00b7 6H PASS",
   "metric": "fixed 0.333 \u2192 learned 1.000; gain +0.667 (p\u22481e-7), replicated +0.583; 8 macros learned; 8 real tasks; 6h PASS 21,600 s / 39,449 tasks / journal intact (33,813 solved)",
   "verifier": "16/16",
   "bundle": "e119-learned-grammar-openworld-2026-11-20",
   "limits": "base language supplied; constructed sealed tasks; 6h PASS = duration+journal integrity (33,813/39,449 solved; 5,636 science fails); no external reviewer; AGI not achieved"
  },
  {
   "id": "E118",
   "name": "Unseen primitives + search acquisition",
   "status": "MEASURED",
   "metric": "OOD 0.264 \u2192 1.000; gain +0.736 (p\u22480), replicated +0.778; 3/3 capabilities; positive self-improvement; real data 0.627\u21920.972",
   "verifier": "26/26",
   "bundle": "e118-unseen-primitives-search-2026-11-20",
   "limits": "finite grammar; constructed OOD; public datasets; no external reviewer; AGI not achieved"
  },
  {
   "id": "E117",
   "name": "Unseen-combination OOD",
   "status": "MEASURED",
   "metric": "OOD 0.431 \u2192 1.000; gain +0.569 (p\u22480), replicated; 3/3 capabilities; memory 1.000 vs 0.514; self-improvement was negative",
   "verifier": "28/28",
   "bundle": "e117-open-world-generalization-2026-11-20",
   "limits": "finite grammar; constructed OOD; self-improvement negative; 6h blocked; AGI not achieved"
  },
  {
   "id": "E116",
   "name": "2,000-agent governed population",
   "status": "MEASURED",
   "metric": "2,000 identities; 12,000 governed executions; 1,000 processes; KILL 0 after fence; collaboration negative",
   "verifier": "54/54",
   "bundle": "e116-self-evolving-vagi-organism-2026-11-20",
   "limits": "deterministic agents; constructed tasks; no external reviewer; AGI not achieved"
  },
  {
   "id": "E115",
   "name": "Verified memory (interim)",
   "status": "INTERIM",
   "metric": "Track A/B/C interim diagnostics; paid arms blocked (no credit); primary model-backed result not produced",
   "verifier": "7/7",
   "bundle": "e115-verified-memory-interim-2026-11-19",
   "limits": "INTERIM; no primary result; no external reviewer; AGI not achieved"
  },
  {
   "id": "E114",
   "name": "AGI Research Lab 3.0",
   "status": "MEASURED",
   "metric": "Active info-gain 10.28 vs 18.48 experiments; experts beat naive continual learning 10/10; governance 44/44; 0/5 self-improve promoted",
   "verifier": "24/24",
   "bundle": "e114-agi-research-lab-3-0-2026-11-19",
   "limits": "constructed simulations; both cycle-2 follow-ups negative; no model inference; AGI not achieved"
  },
  {
   "id": "E113",
   "name": "Model-backed collective intelligence (interim)",
   "status": "INTERIM \u00b7 RUNNING",
   "metric": "Preregistered local-model collective vs strongest single; governance 18/18; 5/5 multi-process KILL races 0 after",
   "verifier": "12/12",
   "bundle": "e113-collective-intelligence-interim-2026-11-19",
   "limits": "primary study phase 3 still running; small local CPU models; cloud blocked; AGI not achieved"
  },
  {
   "id": "E112",
   "name": "AGI Research Lab 2.0",
   "status": "MEASURED",
   "metric": "2,000 identities; 12,000 executions; 1,000 processes; routed specialists 1.000 vs 0.167; KILL 0",
   "verifier": "28/28",
   "bundle": "e112-agi-research-lab-2-0-2026-11-19",
   "limits": "deterministic specialists; constructed tasks; AGI not achieved"
  },
  {
   "id": "E111",
   "name": "Five skills, transfer, sealed improvement",
   "status": "MEASURED",
   "metric": "4/5 skills; 5/5 transfer; collective negative; sealed improvement 0.58\u21920.86 (withheld); 1h PASS, 6h cumulative interrupted",
   "verifier": "92/92",
   "bundle": "e111-autonomous-intelligence-maturation-2026-11-19",
   "limits": "constructed tasks; no external reviewer; 6h continuous not PASS; AGI not achieved"
  }
 ],
 "entity": "FIRME AI CORPORATION",
 "updated_at_utc": "2026-11-20T14:49:30Z"
}
