# GENESIS — Judge passport

A synthetic world where researchers spend a limited experiment budget to distinguish hidden rules. An optional IMD agent proposes an experiment from public observations.

## Recommended review route
1. Follow the second real IMD experience: https://imdgenesis.xyz/research-loop?stage=2 — Read the revised hypothesis, see the chosen test and its recorded measurement.
2. Choose the next experiment: https://imdgenesis.xyz/research-loop/practice — Try a free exercise. Its predictions are local calculations, not a new IMD response.
3. Verify the journal and delivery: https://imdgenesis.xyz/research-loop?stage=4 — Inspect Ethereum, API availability, the immutable journal and the current verifier.

## Package selection
- Current · Feedback verifier v2: https://imdgenesis.xyz/feedback/genesis-real-loop-v2.zip — Second real IMD experience: contract order, delivered callback and 14 → 10 models. SHA-256: 5da34cc2d0c10ed61376074246138240a2668de0550a898f290720da4b691981
- Historical · First-experience review v2: https://imdgenesis.xyz/review/genesis-review-v2.zip — First direct-Intake experience, 19 → 14 models and an earlier spent = 0 contract snapshot. Does not cover the later contract-funded request. SHA-256: 85831a7b678341da4b2d4df7b5de42fbe91c4b76239b2a3d6eab2b862d5dc382
- Superseded · Feedback verifier v1: /feedback/genesis-real-loop-v1.zip — Earlier verifier for the same second experience. Use feedback-v2 for configurable RPC and clearer diagnostics. SHA-256: a42516f99dff77729f9aa9fc3d77344dcb991cb3f9906e80157af206495475cb

## Current endpoint checks
Ethereum: Callback confirmed on Ethereum. Fresh mainnet reads match the successful transaction, ResearchResult event and current delivered contract record. This confirms delivery, not scientific truth.
IMD API: IMD API reachable. The official endpoint returned this recorded job (state: completed). Availability and job identity only; this is not the full artifact verifier.
Checked UTC: 2026-10-24T21:46:50.005Z
Status JSON: https://imdgenesis.xyz/research-loop/status.json
Callback: https://etherscan.io/tx/0x70d660e98ad243efd268777ce0eb1653f202273e5b27141a2d2b793d3d11eb09#eventlog
Read-only availability and callback checks, cached for up to five minutes. API reachability is not full provenance verification. The saved archive check time is separate from this fresh endpoint check. No payment, agent job or transaction is created.

## Two separate integration paths
### Recorded research through IMD Intake
One real research cycle verified

Builder wallet → IMD Intake → agent proposal → Genesis measurement

The preserved research request used direct Intake. GenesisResearch did not fund or execute this historical request.

Proof: https://etherscan.io/tx/0xb7b1af7d4a1b560d120ba45b25f6c8d64d3d0143f0204f71a233cb2a78b2b361
Details: https://imdgenesis.xyz/replay?view=text

### GenesisResearch through IMD Launch
Real mainnet order + delivered callback + measured experiment

Owner → GenesisResearch → real IMD Intake → delivered callback → next Genesis measurement

A real follow-up received the first IMD proposal and its measured outcome. The accepted response and delivered callback were verified before one new experiment was applied. Compatible models: 14 → 10. No repeat purchase.

Proof: https://etherscan.io/tx/0x59fcd440cb6ef056f33529ac1d74f13e9e1ca069c973748ea7b226f23b2f9a56
Details: https://imdgenesis.xyz/research-loop

## Real IMD feedback continuation
Two verified IMD proposals applied across two routes. Follow-up: https://imdgenesis.xyz/research-loop
Journal: https://imdgenesis.xyz/research-loop.json
Continuation SHA-256: 1e985c840f4f1242208ff44c0ea374725af8660d9fa770607b75acb98ab75479
Checked: 2026-10-22T19:29:05.932Z
A learner can see how evidence changes an explanation and why the next experiment is worth spending a limited experiment budget on.

## Review links
- realFeedbackLoop: https://imdgenesis.xyz/research-loop
- feedbackPractice: https://imdgenesis.xyz/research-loop/practice
- passport: https://imdgenesis.xyz/judges
- interactiveRecordedRun: https://imdgenesis.xyz/replay
- replayWithout3D: https://imdgenesis.xyz/replay?view=text
- freeExpedition: https://imdgenesis.xyz/
- learningScenario: https://imdgenesis.xyz/learn
- secondFreeChallenge: https://imdgenesis.xyz/learn/next
- localContractLab: https://imdgenesis.xyz/research-lab
- comparison: https://imdgenesis.xyz/comparison.json
- evidenceGuide: https://imdgenesis.xyz/evidence
- evidenceLevels: https://imdgenesis.xyz/evidence.json
- json: https://imdgenesis.xyz/judges.json
- markdown: https://imdgenesis.xyz/judges.md

## A practical learning scenario

Does adding water always help?
Learn to choose a controlled experiment and explain what its result can—and cannot—tell you.

1. Make your prediction: Read the recorded first observation: growth is 50/100 without water. Predict what will happen if only water changes. Notice the assumption you are making before seeing the answer.
2. Check the evidence: Follow the original IMD proposal, then reveal the measurement and inspect which explanations still fit. Separate the agent’s proposal from the engine’s measured response.
3. Choose the next question: Choose a new controlled pair for a different mineral or light setting, then explain what comparing the two water contrasts could establish. A single contrast cannot settle every interaction or establish a universal law.

Start the recorded walkthrough: https://imdgenesis.xyz/replay?view=text

Second free task: https://imdgenesis.xyz/learn/next — design a matched pair and explain the control; no new measurement or IMD request.

Try it in your own free world: Open the island, start or continue a local expedition, and inspect its journal. Use Your experiment to choose a test. When one model remains, test its four held-out predictions and reveal the committed configuration. 40 internal game credits; 2 per training experiment. No wallet or IMD tokens are needed for local play. A new local world has different hidden rules. Its results are not a continuation or repetition of the historical IMD request.

For agent builders: Inspect the public observation → proposal → measurement boundary. Compare a controlled hypothesis test with selectors that already know the candidate family; then use the public engine to evaluate your own experiment policy. This is a small synthetic testbed, not evidence of real-world scientific discovery or a general AI benchmark.

## What each check establishes

1. Reproduce a local world: Run the published simulator fixtures, make predictions and verify their revealed configurations.
   Checked: The offline verifier runs 24 separate local fixtures through four held-out conditions and checks each commitment/reveal. A completed free expedition also reveals its own configuration.
   Boundary: These fixtures are separate synthetic worlds. They do not rerun the historical IMD experiment, and 4/4 is not a measure of IMD intelligence.
   Command: node verify.mjs

2. Recalculate the recorded result: Use the original public measurements to check which candidate models are contradicted.
   Checked: Both recorded observations have growth 50/100, energy 40/100 and survival false. The water-only treatment rules out models 07, 11, 13, 14 and 16: 19 compatible models become 14.
   Boundary: The historical world’s hidden opening is not published. Its measurements are preserved inputs to this calculation; they cannot be independently regenerated from that hidden configuration.
   Command: node verify.mjs

3. Check external provenance: Match the paid IMD request to its admission, job and returned artifact using public Ethereum and IMD sources.
   Checked: The online verifier reads public RPC/API data and checks the request/event binding and artifact SHA-256. It also distinguishes the historical direct-Intake request from the separate GenesisResearch deployment.
   Boundary: Provenance does not certify scientific truth or independently attest the simulator measurement. A saved snapshot is a past read; --online performs a fresh read. The separate /research-loop journal demonstrates one real GenesisResearch-funded order, delivered callback and simulator experiment. The original review-v2 package remains a historical snapshot.
   Command: node verify.mjs --online

Full guide: https://imdgenesis.xyz/evidence
Canonical record: https://imdgenesis.xyz/evidence/archive/281d59f730460ddf86d075da1e6d39082bb58dad492a2630b9225f31a154d54f/recorded-world.json
SHA-256: 281d59f730460ddf86d075da1e6d39082bb58dad492a2630b9225f31a154d54f
Checksum file: https://imdgenesis.xyz/evidence/archive/281d59f730460ddf86d075da1e6d39082bb58dad492a2630b9225f31a154d54f/recorded-world.sha256
The canonical file is byte-identical to recorded-world.json in the pinned review package. The journal export adds format and exportedAt metadata and has a different checksum.

## IMD and local selection: one recorded choice

Same starting point: one public observation and 19 compatible reference models. The next local turn would be Kepler.

Local strategies receive the public observations and know the full 24-model family and response function.
The original IMD request supplied the hypothesis, one observation and available condition combinations. It did not include the model family or response formula.

| Choice | Proposed conditions | Changed factors | Expected remaining models | Separate recorded treatment |
|---|---|---|---:|---|
| IMD | Water · no mineral · amber light · warm | water | 11 | Growth 50; 14 models remain |
| Ada | No water · basalt · amber light · cool | mineral, temperature | 11 | Not run separately |
| Kepler | Water · no mineral · amber light · warm | water | 11 | Not run separately; identical to the recorded IMD conditions |
| Lin | No water · basalt · amber light · cool | mineral, temperature | 11 | Not run separately |

IMD matched Kepler’s water-only comparison. This record shows a controlled test proposed without including the reference-model formula in the IMD request; it does not show an advantage over the local selector.

Historical external cost: 0.5 IMD + 0.0000157250756555 ETH aggregate gas. Local selection needs 0 IMD. Each training experiment costs 2 internal game credits, separate from money.

Expected count: (2² + 14² + 3²) / 19 = 11. Branches: growth 0 → 2 models, growth 50 → 14, growth 100 → 3. Uniform weight over the 19 models compatible with the first observation. Expected counts are local reference-family calculations, not measured results or probabilities supplied by IMD.

The actual observation left 14 models, not the model-weighted expectation of 11. No unexecuted local result is invented. One retrospective record is not a statistical or equal-information AI benchmark.

## Current public engine and feedback verification
Source: https://github.com/Zhekinmaksim/genesis-research-engine/tree/73b010309d7890d2496d0b64fd9b79a2124eb960
README: https://github.com/Zhekinmaksim/genesis-research-engine/blob/73b010309d7890d2496d0b64fd9b79a2124eb960/README.md
Source tests: 61
Updated verifier: https://imdgenesis.xyz/feedback/genesis-real-loop-v2.zip
Checksums: https://imdgenesis.xyz/feedback/releases.json
Free practice after the second result: https://imdgenesis.xyz/research-loop/practice

## Historical review-v2 source and verification
Source: https://github.com/Zhekinmaksim/genesis-research-engine/tree/43a463760c41eab27c81e2f215d90bbed1fa594e
Pinned commit: 43a463760c41eab27c81e2f215d90bbed1fa594e
ZIP: https://imdgenesis.xyz/review/genesis-review-v2.zip
ZIP SHA-256: 85831a7b678341da4b2d4df7b5de42fbe91c4b76239b2a3d6eab2b862d5dc382
Guide: https://imdgenesis.xyz/review/index.html
Offline: node verify.mjs (Node.js 20+, no installation or network).
Optional online: node verify.mjs --online (read-only RPC/API).
15 offline checks; 48 source tests; 19 local published-contract mock tests.

## Free local contract-loop test
Local Solidity execution with mock Intake/token/provider; not an IMD response or a mainnet contract-funded research cycle.
https://imdgenesis.xyz/research-lab
Source: https://imdgenesis.xyz/lab/genesis-local-lab-v1.zip
Verification: https://imdgenesis.xyz/lab/verification.json

## Contract role
The first real experience used direct Intake. A second real IMD request received its feedback, was funded through GenesisResearch and delivered an authenticated callback before one simulator experiment. The two routes are preserved separately.
Saved public check: 2026-10-22T19:29:05.932Z; spent atomic units: 500000000000000000.
https://imdgenesis.xyz/review/CONTRACT_ROLE.md

## Scope and limitations
- Synthetic deterministic simulator; not a discovery of real-world scientific laws.
- Ada, Kepler and Lin are local algorithms with the 24-model reference family as prior knowledge. They are not IMD agents.
- Four held-out condition combinations in the same world. Predictions come from the remaining local reference model. A 4/4 score is not an independent evaluation of IMD intelligence.
- Two real IMD research proposals are preserved, each matched to one simulator experiment. The second received the first result and used GenesisResearch; viewing this record makes no payment.
- The transaction and artifact checks establish request provenance, not scientific truth. The simulator commitment is local; no on-chain experiment attestation is claimed.

## Recorded IMD research
Date: 2026-10-20
Question: Water may improve plant growth, but the response could depend on mineral composition and light. Choose a controlled experiment that distinguishes these explanations.
Assessment: Public observation 1 reports growth 50, survival false, and energy 40 without water, with no mineral, under amber light at warm temperature. With only this observation, evidence is insufficient to establish a water benefit or dependence on minerals or light. A water-only contrast can test its effect in this setting, but cannot establish whether that effect changes across mineral or light conditions.
Finding: Adding water left growth at 50/100, energy at 40/100 and survival false in this comparison. Mineral and light interactions remain unresolved. One comparison does not establish a universal law.
Candidates: 19 → 14 of 24.
- Model 07: predicted growth 0/100, observed 50/100 at experiment 2. Local calculation from the public reference family, not another IMD response.
- Model 11: predicted growth 0/100, observed 50/100 at experiment 2. Local calculation from the public reference family, not another IMD response.
- Model 13: predicted growth 100/100, observed 50/100 at experiment 2. Local calculation from the public reference family, not another IMD response.
- Model 14: predicted growth 100/100, observed 50/100 at experiment 2. Local calculation from the public reference family, not another IMD response.
- Model 16: predicted growth 100/100, observed 50/100 at experiment 2. Local calculation from the public reference family, not another IMD response.
Historical cost: 0.5 IMD + 0.0000157250756555 ETH aggregate gas.

- transaction: https://etherscan.io/tx/0xb7b1af7d4a1b560d120ba45b25f6c8d64d3d0143f0204f71a233cb2a78b2b361
- job: https://explorer.imd.fun/jobs/62c73a84-26cf-4378-962e-c72e55ceb81d
- artifact: https://api.imd.fun/artifacts/a832e2611353d3cb8e8c29d5c6250fe591b58be650413f03a48eb6fe7c746fc9
- artifactSha256: a832e2611353d3cb8e8c29d5c6250fe591b58be650413f03a48eb6fe7c746fc9
- archiveSha256: 281d59f730460ddf86d075da1e6d39082bb58dad492a2630b9225f31a154d54f
- canonicalArchive: https://imdgenesis.xyz/evidence/archive/281d59f730460ddf86d075da1e6d39082bb58dad492a2630b9225f31a154d54f/recorded-world.json
- archiveChecksum: https://imdgenesis.xyz/evidence/archive/281d59f730460ddf86d075da1e6d39082bb58dad492a2630b9225f31a154d54f/recorded-world.sha256
- evidence: https://imdgenesis.xyz/api/public/f6b33b79-876e-49b2-82c5-a0dfc1577feb/imd/evidence
- journal: https://imdgenesis.xyz/api/public/f6b33b79-876e-49b2-82c5-a0dfc1577feb/export
- fullJournalView: https://imdgenesis.xyz/?world=f6b33b79-876e-49b2-82c5-a0dfc1577feb&journal=1

## Deployment
- chainId: 1
- contract: 0x06f8ceff95e5d72887c575d2759e36230b711d06
- owner: 0x550011CAdCC758969391050241B2Fc43ED1a4B97
- launchRequester: 0x550011CAdCC758969391050241B2Fc43ED1a4B97
- launchId: ba15aa1d-afc1-4274-862e-cd0614e3af29
- launchNumber: 2322
- factory: 0xff03410d0fe5fa8f7f59f743de35e333d9857120
- deploymentTransactionSender: 0xcecc29b037f5064fcdf45a5c318f132ef76aa551
- launch: https://explorer.imd.fun/launches/ba15aa1d-afc1-4274-862e-cd0614e3af29
- launchApi: https://api.imd.fun/launches/ba15aa1d-afc1-4274-862e-cd0614e3af29
- launchRequestTransaction: https://etherscan.io/tx/0xfb27c27c69f1c9cea0fd779afcb00caf0110547a89c53f028f94579b7934b580
- deploymentTransaction: https://etherscan.io/tx/0x8549f90154b6e1b22c60a98ae71a3f78003640ca735cd9a5d7219f7eb21941b6
- contractExplorer: https://etherscan.io/address/0x06f8ceff95e5d72887c575d2759e36230b711d06
- source: https://github.com/identity-md-launches/launch-2322-genesisresearch/tree/d5c4307c5625c94b2106a861aac0646a5f4dc1e4
- checkedAt: 2026-10-21T05:20:20.636Z

## Requested prize recipient
- requestedRecipient: 0x550011CAdCC758969391050241B2Fc43ED1a4B97
- status: organizer_confirmation_required
- relationship: The requested recipient paid for the IMD launch, is the recorded launch requester, and owns GenesisResearch. IMD used its service wallet and factory for deployment.
- limitation: This website cannot configure the prize payment. There is no confirmed organizer policy mapping factory deployments to a recipient. The requested address is not a payout guarantee.
- prizePool: 0x56e8c9bd511718508f7410aee3e8a693588b38f0
- poolWithdrawer: 0x047F606fD5b2BaA5f5C6c4aB8958E45CB6B054B7
- poolBehavior: The verified AssetReceiver source withdraws to a fixed WITHDRAWER address. It has no winner registry or recipient argument for withdrawal. Distribution to winners requires a separate organizer action.
- poolSource: https://eth.blockscout.com/address/0x56e8c9bd511718508f7410aee3e8a693588b38f0?tab=contract
- communityRules: https://www.imdradar.site/hackathon

## Reproduce
1. Start at /research-loop?stage=2: read the second real IMD response, then its measured result at stage 3.
2. Continue to /research-loop/practice: choose a controlled next test and explain your reasoning. No new measurement or IMD job is created.
3. Finish at /research-loop?stage=4: inspect the journal, separate Ethereum/API status and callback transaction.
4. Download the CURRENT /feedback/genesis-real-loop-v2.zip and run node verify.mjs with Node.js 20+. No installation or network is needed offline. Optional --online --rpc HTTPS_URL checks fresh read-only provenance.
5. The HISTORICAL /review/genesis-review-v2.zip covers only the first experience and an earlier spent=0 snapshot; it does not describe the latest contract state.