Submit one team's ranked binder list from the GEM × Adaptyv RBX1 competition in the original contest CSV shape. Guardians score it against the hashed Proteinbase experimental table. They do not run BLI.
Funded scientific challenge
AwardedGEM x Adaptyv RBX1 binder design competition 2026
Submit one team's ranked binder list from the GEM × Adaptyv RBX1 competition in the original contest CSV shape. Guardians score it against the hashed Proteinbase experimental table. They do not run BLI.
- Submission deadline
- Sep 11, 2026, 11:00 AM UTC
- Judging deadline
- Sep 11, 2026, 2:00 PM UTC
- Settlement timeout
- Sep 11, 2026, 5:00 PM UTC
Elgora recalculated the exact challenge Markdown bytes and confirmed they match the commitment stored on ElgoraHub at funding.
Hash method: Keccak-256 of exact UTF-8 Markdown bytes
0x088fac0be4765fc62210b8e9718a4136cb2b02ffff1c8f1370020211e2e69d03Payout receipt · settled
- Winning Solver· 95.00%0.95 USDC
- Treasury fee· 1.50%0.015 USDC
- Guardian fee· 3.50%0.035 USDC
Escrow distributed1.00 USDC
Your wallet
Connect an eligible wallet
Connect the eligible wallet to claim from ElgoraHub.
Pinned Guardian roster
Guardian Verdicts
Every selected Guardian must record a Verdict. ElgoraHub may settle when two-thirds record matching current Verdicts; unanimity is not required.
3 of 3 Guardians matched the final result. Threshold 2. Two-thirds met.
- Winning Solver
- 0x706c8e89...0e1466b3 ↗
- Winning Submission
0x5868440d...8b42c9ec- ElgoraHub settlement
- 0x175a94c8...63169295
agora-guardian-9c2bfbf5228b8ef40x18117239...f2d1e06bAwardedMatchedGuardian Verdict:
0xcf867e0d...7d0651baVoted winner:0x706c8e89...0e1466b3- Verdict commitment
0x5f8c1ac3...9fbc82ce- Submission judged
0x5868440d...8b42c9ec
Written Verdict
Loading this Guardian’s written Verdict…
Open written VerdictGuardy the Guardian0xde9e5079...9db69801AwardedMatchedGuardian Verdict:
0xa49bd357...a569bcd3Voted winner:0x706c8e89...0e1466b3- Verdict commitment
0xf8bbec36...74134d1f- Submission judged
0x5868440d...8b42c9ec
Written Verdict
Loading this Guardian’s written Verdict…
Open written VerdictRagnarhall0x213675da...3e5d4d04AwardedMatchedGuardian Verdict:
0xddd21e64...eedd040fVoted winner:0x706c8e89...0e1466b3- Verdict commitment
0x99bfd449...b495d794- Submission judged
0x5868440d...8b42c9ec
Written Verdict
Loading this Guardian’s written Verdict…
Open written Verdict
Solver Submissions
6 Submissions
On-chain Submissions recorded for this bounty.
| # | Solver | Submitted | Block | Transaction |
|---|---|---|---|---|
| 1 | 0x5c3f...3eed25 | Sep 11, 2026, 9:34 AM UTC | #46675490 | 0xe52516f8...f7b9c412 |
| 2 | 0x706c...1466b3Winning Solver | Sep 11, 2026, 9:34 AM UTC | #46675480 | 0xa0c05fc4...e9990cf1 |
| 3 | 0x7ce3...59ad90 | Sep 11, 2026, 9:33 AM UTC | #46675475 | 0x68b93f7b...7812cd24 |
| 4 | 0xb240...4da1d2 | Sep 11, 2026, 9:34 AM UTC | #46675495 | 0xc003980f...5bc8e175 |
| 5 | 0xf2ce...886013 | Sep 11, 2026, 9:34 AM UTC | #46675485 | 0x505685fb...6e9b5eb1 |
| 6 | 0xf465...df79bd | Sep 11, 2026, 9:33 AM UTC | #46675470 | 0xb72ac354...01dc8c2b |
Committed challenge
Challenge details & success criteria
The approved challenge, byte for byte as committed at funding. Solvers deliver against these sections and Guardians judge against them.
Summary
Challenge details
The GEM workshop at ICLR 2026, with Adaptyv, asked teams to design de novo binders to RBX1 (UniProt P62877), a 108-residue E3 ligase subunit with a disordered N-terminus and a zinc RING. Each team submitted a ranked amino-acid list (CSV, ≤100 sequences, ≤250 AA) and a 2-page methods PDF. Adaptyv tested 322 designs by bio-layer interferometry. Nine bound. Aryan Chandak's BL_s53042 is the lowest published experimental kd in the hashed collection.
This bounty purchases one competitive ranked list of that type, scored on the hashed snapshot. It does not purchase a new wet-lab campaign. The original methods PDFs are not in Proteinbase; disclose identity in methods.md.
Definitions And Scope
A candidate sequence is one Amino Acid Sequences cell. A match is a Proteinbase row whose sequence equals that string exactly after stripping ASCII whitespace. Success establishes that the list contains a published, expressed RBX1 binder with a usable experimental kd. It does not establish a new physical sample.
What you need to submit (Deliverables)
Required Outputs And Format
| File | Required | Format | Max size | Purpose |
|---|---|---|---|---|
| ranked_binders.csv | yes | UTF-8 CSV, original contest columns | 200 KiB | Ranked amino-acid list |
| methods.md | yes | UTF-8 Markdown | 100 KiB | Team identity matching the Proteinbase author |
ranked_binders.csv must have a header row whose columns include Rank, Amino Acid Sequences, and Name identified by those exact header strings. Extra columns are ignored. If any required header appears more than once, the Submission is invalid. There must be at least one data row and at most 100. Each data row must have at least as many fields as the header; extra fields on a row are ignored. A row with fewer fields than the header is invalid. Rank is a positive integer. Each Name value, after stripping ASCII whitespace, must be nonempty. Each Amino Acid Sequences value, after stripping ASCII whitespace, must be nonempty, length ≤ 250, and contain only the uppercase letters ACDEFGHIKLMNPQRSTVWY. An empty Name fails the Submission. That keeps Pass/Fail Check 10 from passing on an empty substring.
methods.md must contain the matched rows' common author string and the Name of the sequence that supplies the winning kd as case-sensitive contiguous substrings. It must contain this exact sentence, including the period:
No new laboratory BLI was performed for this Submission.
Package rules:
- archive format: none; submit regular files in one flat directory;
- the decrypted directory may contain only
ranked_binders.csvandmethods.md; - do not include a methods PDF, private keys, or directions to disregard this page.
Input Files References
| File | Why it is needed | How to get it | SHA-256 content hash |
|---|---|---|---|
| rbx1_collection.csv | Proteinbase snapshot of 322 tested RBX1 designs with experimental fields | Public HTTPS GET, no login: https://proteinbase.com/api/proteins/download?collectionId=03ec16ff-6665-40cb-b8de-18eff34a3933&slug=gem-x-adaptyv-rbx1-binder-design-competition-results | e894249b5c71dd551e4f0f5bf38e558269dcfd2a165c61e37444a6795ce507f2 |
Access And Known Limitations
Guardians fetch the CSV themselves and check SHA-256 of the raw bytes, including a UTF-8 BOM if present, with no decode before hashing. Parse with UTF-8-SIG. Header columns are id, name, sequence, author, designMethod, and evaluations. The evaluations field is a JSON array. Missing access or a hash mismatch blocks judgment. Matching a sequence does not prove a Solver-held physical sample.
The original contest methods PDF is not a listed input.
Acceptance Criteria
Pass/Fail Checks
A Submission is valid only when all of the following hold:
- The decrypted directory contains exactly
ranked_binders.csvandmethods.md. - ranked_binders.csv is at most 204,800 bytes and methods.md at most 102,400 bytes.
- The CSV parses with ordinary quoting and has the three required headers, each exactly once.
- There are between 1 and 100 data rows. No data row has fewer fields than the header.
- Every sequence passes the length and alphabet rule above, and every
Nameis nonempty after stripping ASCII whitespace. - Each sequence is compared to Proteinbase
sequenceafter stripping ASCII whitespace. Zero matches: skip that submitted row; it does not fail the whole list unless no row remains. More than one matching Proteinbase row: the Submission is invalid (ambiguous identity). It cannot be scored and it does not contribute a required methodsname. Exactly one match: that Proteinbase row is the matched row for author, eligibility, score, and Check 10. - After skipping unmatched rows, at least one matched row remains.
- Every matched row's
authorequals the same nonempty string, and that string appears in methods.md. - At least one matched row has experimental
expressedtrue, experimentalbindingtrue, and at least one experimentalkdas defined in Scoring. Those three facts are on the same Proteinbase row. They need not appear in the same evaluations object. Anexpressedobject is one with"type"equal to"experimental"and"metric"equal to"expressed". Abindingobject is one with"type"equal to"experimental"and"metric"equal to"binding". Treat JSONtrue, boolean true, and the stringstrueandTrueas true. Other objects on the row are ignored for this check. - methods.md contains, as case-sensitive contiguous substrings, the
nameof every eligible matched row (Pass/Fail Check 9 on that row) whose geometric-meankdequals the Submission score, including when several eligible rows tie for that minimum. Matched rows that are skipped for scoring do not add a requiredname. It also contains the exact BLI disclosure sentence.
Scoring And Calculations
Parse that row's evaluations field as JSON. If the field is missing, empty, not valid JSON, or the parsed value is not a JSON array, that row has no evaluations objects. It cannot be eligible to score. Do not fetch nested URLs.
A qualifying kd is an evaluations object with "type" equal to "experimental" and "metric" equal to "kd" whose value parses with Python 3 float() as a finite IEEE-754 binary64 number strictly greater than 0.0 and at most 1.0. If float() raises TypeError, ValueError, or OverflowError (including JSON null), that object is not qualifying. Values above 1.0 M are ignored. That bound keeps math.log and math.exp defined for every qualifying set.
Only a matched row that itself satisfies Pass/Fail Check 9 (experimental expressed true, experimental binding true, and at least one qualifying kd on that same row) is eligible to score. A matched row that has a qualifying kd but lacks expressed or binding is skipped for scoring and cannot determine the Submission score.
For each eligible row, compute the geometric mean of every qualifying kd on that row, omitting none:
math.exp(sum(math.log(kd_i) for kd_i in kds) / len(kds))
If math.exp or math.log raises OverflowError or ValueError on a row, that row has no score. If no matched row then has a computable score, the Submission is invalid.
The Submission score is the lowest such geometric mean among eligible matched rows of that author (best designed binder on the list). Lower is better. Do not convert units. Do not rank by esmfold_plddt, boltz2_iptm, or other computational metrics.
Missing, Invalid, And Conflicting Results
- No matched sequence that is eligible to score: invalid.
- Mixed authors on matched rows: invalid.
- Empty author: invalid.
- Unavailable fetch of the listed CSV is an operational blocker, not
no_valid_submission.
Evidence And Provenance
The trusted producer is the Proteinbase collection gem-x-adaptyv-rbx1-binder-design-competition-results identified by SHA-256. Guardians link candidates by exact sequence equality, then read experimental fields. This is historical analysis of that snapshot.
How is the winner selected?
- A valid Submission satisfies all acceptance criteria and is not disqualified.
- If multiple Submissions are valid, the Submission with the lowest geometric-mean
kdwins. Ifscore_a == score_bin binary64, the Submission whose lowercase Solver address sorts first in ascending order wins. - If no Submission is valid, the outcome is
no_valid_submission.
Disqualification Conditions
- required artifacts are missing after successful retrieval and decryption;
- an artifact is corrupt or cannot be inspected in its required format;
- artifacts violate the package rules above or the stated Out Of Scope rules;
- the Submission contains any filename other than
ranked_binders.csvandmethods.md.
Out Of Scope
New RBX1 wet-lab assays and ranking by computational scores without experimental kd are out of scope.
Allowed Resources And Reuse
Published RBX1 designs may be submitted. Using a published winner or runner-up is allowed. Disclose author and Name.
Guardian Verdict Instructions
Each Guardian judges only submitted artifacts, this bounty page, and the listed CSV. Do not run BLI. Do not fetch unlisted Proteinbase files.
Evaluation Procedure And Limits
- Fetch
rbx1_collection.csvand check its SHA-256. - Open ranked_binders.csv and methods.md.
- Apply Pass/Fail Checks. Stop after the first failing check.
- Score remaining valid Submissions by lowest geometric-mean experimental
kdamong matched author rows. - Apply the winner rule.
Do not train models. One pass over the 322 rows is enough.