Dataset subset reported in Genie 3 primary paper v1, Table 3. Exact split manifest remains unextracted; source-table identity is retained.
These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.
Release 2026-09-29-06401fd5b220 · Evidence verified: Not verified
Exact outcomes, predictions, identifiers and evaluator are connected.
Missing or unresolved evidence
Verified: Not verified
Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.
Missing or unresolved evidence
Verified: Not verified
A pinned recipe describes the inputs, environment and resource requirements.
Missing or unresolved evidence
Verified: Not verified
Separate data and exposure records support an independent test.
Missing or unresolved evidence
Verified: Not verified
Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.
No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.
13 evaluations · 65 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Ambient (short) | Protocol: Genie 3 short monomer generation designability: Unconditional short monomer Designability Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.97 designability reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 12 (Ambient (short)), column Designability |
| Configuration: Ambient (short) | Protocol: Genie 3 short monomer generation diversity-tm-05: Unconditional short monomer Diversity, TM < 0.5 Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.76 diversity_tm_05 reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 12 (Ambient (short)), column Diversity, TM < 0.5 |
| Configuration: Ambient (short) | Protocol: Genie 3 short monomer generation diversity-tm-06: Unconditional short monomer Diversity, TM < 0.6 Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.93 diversity_tm_06 reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 12 (Ambient (short)), column Diversity, TM < 0.6 |
| Configuration: Ambient (short) | Protocol: Genie 3 short monomer generation novelty-afdb: Unconditional short monomer Novelty, AFDB Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.39 novelty_afdb reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 12 (Ambient (short)), column Novelty, AFDB |
| Configuration: Ambient (short) | Protocol: Genie 3 short monomer generation novelty-pdb: Unconditional short monomer Novelty, PDB Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.41 novelty_pdb reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 12 (Ambient (short)), column Novelty, PDB |
| Configuration: FoldFlow 2 (base) | Protocol: Genie 3 short monomer generation designability: Unconditional short monomer Designability Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.97 designability reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 4 (FoldFlow 2 (base)), column Designability |
| Configuration: FoldFlow 2 (base) | Protocol: Genie 3 short monomer generation diversity-tm-05: Unconditional short monomer Diversity, TM < 0.5 Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.43 diversity_tm_05 reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 4 (FoldFlow 2 (base)), column Diversity, TM < 0.5 |
| Configuration: FoldFlow 2 (base) | Protocol: Genie 3 short monomer generation diversity-tm-06: Unconditional short monomer Diversity, TM < 0.6 Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.77 diversity_tm_06 reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 4 (FoldFlow 2 (base)), column Diversity, TM < 0.6 |
| Configuration: FoldFlow 2 (base) | Protocol: Genie 3 short monomer generation novelty-afdb: Unconditional short monomer Novelty, AFDB Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.32 novelty_afdb reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 4 (FoldFlow 2 (base)), column Novelty, AFDB |
| Configuration: FoldFlow 2 (base) | Protocol: Genie 3 short monomer generation novelty-pdb: Unconditional short monomer Novelty, PDB Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.34 novelty_pdb reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 4 (FoldFlow 2 (base)), column Novelty, PDB |
| Configuration: FoldFlow 2 (reft) | Protocol: Genie 3 short monomer generation designability: Unconditional short monomer Designability Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.83 designability reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 5 (FoldFlow 2 (reft)), column Designability |
| Configuration: FoldFlow 2 (reft) | Protocol: Genie 3 short monomer generation diversity-tm-05: Unconditional short monomer Diversity, TM < 0.5 Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.44 diversity_tm_05 reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 5 (FoldFlow 2 (reft)), column Diversity, TM < 0.5 |
| Configuration: FoldFlow 2 (reft) | Protocol: Genie 3 short monomer generation diversity-tm-06: Unconditional short monomer Diversity, TM < 0.6 Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.59 diversity_tm_06 reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 5 (FoldFlow 2 (reft)), column Diversity, TM < 0.6 |
| Configuration: FoldFlow 2 (reft) | Protocol: Genie 3 short monomer generation novelty-afdb: Unconditional short monomer Novelty, AFDB Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.36 novelty_afdb reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 5 (FoldFlow 2 (reft)), column Novelty, AFDB |
| Configuration: FoldFlow 2 (reft) | Protocol: Genie 3 short monomer generation novelty-pdb: Unconditional short monomer Novelty, PDB Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.36 novelty_pdb reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 5 (FoldFlow 2 (reft)), column Novelty, PDB |
| Configuration: FrameFlow | Protocol: Genie 3 short monomer generation designability: Unconditional short monomer Designability Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.9 designability reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 2 (FrameFlow), column Designability |
| Configuration: FrameFlow | Protocol: Genie 3 short monomer generation diversity-tm-05: Unconditional short monomer Diversity, TM < 0.5 Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.5 diversity_tm_05 reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 2 (FrameFlow), column Diversity, TM < 0.5 |
| Configuration: FrameFlow | Protocol: Genie 3 short monomer generation diversity-tm-06: Unconditional short monomer Diversity, TM < 0.6 Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.7 diversity_tm_06 reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 2 (FrameFlow), column Diversity, TM < 0.6 |
| Configuration: FrameFlow | Protocol: Genie 3 short monomer generation novelty-afdb: Unconditional short monomer Novelty, AFDB Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.33 novelty_afdb reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 2 (FrameFlow), column Novelty, AFDB |
| Configuration: FrameFlow | Protocol: Genie 3 short monomer generation novelty-pdb: Unconditional short monomer Novelty, PDB Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.34 novelty_pdb reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceFrameFlow on Genie 3 short monomer generation novelty-pdb: Unconditional short monomer Novelty, PDB Unconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 2 (FrameFlow), column Novelty, PDB |
| Configuration: Genie 2 | Protocol: Genie 3 short monomer generation designability: Unconditional short monomer Designability Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.94 designability reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceGenie 2 on Genie 3 short monomer generation designability: Unconditional short monomer Designability Unconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 11 (Genie 2), column Designability |
| Configuration: Genie 2 | Protocol: Genie 3 short monomer generation diversity-tm-05: Unconditional short monomer Diversity, TM < 0.5 Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.62 diversity_tm_05 reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 11 (Genie 2), column Diversity, TM < 0.5 |
| Configuration: Genie 2 | Protocol: Genie 3 short monomer generation diversity-tm-06: Unconditional short monomer Diversity, TM < 0.6 Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.89 diversity_tm_06 reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceUnconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 11 (Genie 2), column Diversity, TM < 0.6 |
| Configuration: Genie 2 | Protocol: Genie 3 short monomer generation novelty-afdb: Unconditional short monomer Novelty, AFDB Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.37 novelty_afdb reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceGenie 2 on Genie 3 short monomer generation novelty-afdb: Unconditional short monomer Novelty, AFDB Unconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 11 (Genie 2), column Novelty, AFDB |
| Configuration: Genie 2 | Protocol: Genie 3 short monomer generation novelty-pdb: Unconditional short monomer Novelty, PDB Dataset subset: 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) | 0.39 novelty_pdb reported score · higher Uncertainty: Not reported Coverage: generated per run: 500; repeats: 3; note: Three repeated runs; metric-specific valid subsets not assigned a pooled denominator. | Author-reported evaluation · Source checkedMethods, coverage and sourceGenie 2 on Genie 3 short monomer generation novelty-pdb: Unconditional short monomer Novelty, PDB Unconditional short monomer generation: 100 structures at each length 50, 100, 150, 200 and 250 (500 samples per run); 3 repeated runs; Table 3 reports the authors’ average across runs. Designability uses minimum C-alpha scRMSD <2 angstrom across 8 ProteinMPNN sequences refolded with ESMFold. Diversity and novelty use FoldSeek release 10 (2025-01-19); exact definitions and reference sets in Appendix B.1. Method-specific checkpoints and sampling settings remain as Appendix B.2. Aggregation: Mean over three repeated runs Genie 3 primary paper v1, Table 3 · PDF page 20, Appendix B.3, Table 3, data row 11 (Genie 2), column Novelty, PDB |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
2 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| description Dataset subset reported in Genie 3 primary paper v1, Table 3. Exact split manifest remains unextracted; source-table identity is retained. Context-only references | Genie 3 primary paper v1, Table 3 No field-specific location recorded Version: 10.64898/2026.05.01.722168v1; posted 2026-05-05 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| name 500 generated monomers per run; lengths 50–250 in steps of 50; three runs (Genie 3 short monomer generation split) Context-only references | Genie 3 primary paper v1, Table 3 No field-specific location recorded Version: 10.64898/2026.05.01.722168v1; posted 2026-05-05 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: source checked
Stable ID: genie3-2026-table3-dataset-500-generated-monomers-per-run-lengths-50-250-in-steps-of-50-three-runs