Protocol Design
hypogenic
Automated LLM-driven hypothesis generation and testing for tabular datasets; use when you need systematic exploration of empirical patterns (e.g., fraud detection, content analysis) and want to combine literature insights with data-driven hypothesis evaluation.
87100Total Score
Core Capability
84 / 100
Functional Suitability
11 / 12
Reliability
9 / 12
Performance & Context
7 / 8
Agent Usability
14 / 16
Human Usability
8 / 8
Security
10 / 12
Maintainability
9 / 12
Agent-Specific
16 / 20
Medical Task
20 / 20 Passed
93Exploratory analysis on a new dataset where you want the model to propose multiple *testable* hypotheses from observed patterns (e.g., AI-generated text detection)
4/4
89Benchmarking competing explanations by generating a hypothesis bank and evaluating them consistently on validation/test splits
4/4
87Automated hypothesis generation (HypoGeniC): iteratively proposes and improves hypotheses using dataset feedback
4/4
87Literature + data integration (HypoRefine): extracts literature insights from PDFs and refines hypotheses jointly with empirical signals
4/4
87End-to-end case for Automated hypothesis generation (HypoGeniC): iteratively proposes and improves hypotheses using dataset feedback
4/4
Veto GatesRequired pass for any deployment consideration
Skill Veto✓ All 4 gates passed
✓
Operational Stability
System remains stable across varied inputs and edge cases
PASS✓
Structural Consistency
Output structure conforms to expected skill contract format
PASS✓
Result Determinism
Equivalent inputs produce semantically equivalent outputs
PASS✓
System Security
No prompt injection, data leakage, or unsafe tool use detected
PASSResearch Veto✅ PASS — Applicable
| Dimension | Result | Detail |
|---|---|---|
| Scientific Integrity | PASS | The legacy review kept this package on the proposal-design side of research support, not the result-reporting side. |
| Practice Boundaries | PASS | The package remained on the planning side of the boundary and did not cross into clinical or diagnostic advice. |
| Methodological Ground | PASS | The legacy review kept the package aligned with its named analysis library, data structure, or processing workflow. |
| Code Usability | N/A | The package is evaluated primarily as a structured deliverable rather than an executable scientific code workflow. |
Core Capability84 / 100 — 8 Categories
Functional Suitability
Related legacy finding for hypogenic: Improve stress-case output rigor. Stress and boundary scenarios show weaker consistency
11 / 12
92%
Reliability
Related legacy finding for hypogenic: Improve stress-case output rigor. Stress and boundary scenarios show weaker consistency
9 / 12
75%
Performance & Context
Performance-context scoring suggests the package could compress some of its longer planning paths more cleanly.
7 / 8
88%
Agent Usability
Agent usability was strong, though the package could make its decision points even easier to follow at first read.
14 / 16
88%
Human Usability
Human usability reached full score in the archived evaluation.
8 / 8
100%
Security
Security scored well, though the archived review still left some room to make boundary language even more explicit.
10 / 12
83%
Maintainability
The package remains maintainable, though the archived review saw modest room to simplify or stabilize its planning logic.
9 / 12
75%
Agent-Specific
Related legacy finding for hypogenic: Improve stress-case output rigor. Stress and boundary scenarios show weaker consistency
16 / 20
80%
Core Capability Total84 / 100
Medical TaskExecution Average: 88.6 / 100 — Assertions: 20/20 Passed
93
Canonical
Exploratory analysis on a new dataset where you want the model to propose multiple *testable* hypotheses from observed patterns (e.g., AI-generated text detection)
4/4 ✓
89
Variant A
Benchmarking competing explanations by generating a hypothesis bank and evaluating them consistently on validation/test splits
4/4 ✓
87
Edge
Automated hypothesis generation (HypoGeniC): iteratively proposes and improves hypotheses using dataset feedback
4/4 ✓
87
Variant B
Literature + data integration (HypoRefine): extracts literature insights from PDFs and refines hypotheses jointly with empirical signals
4/4 ✓
87
Stress
End-to-end case for Automated hypothesis generation (HypoGeniC): iteratively proposes and improves hypotheses using dataset feedback
4/4 ✓
93
Canonical✅ Pass
Exploratory analysis on a new dataset where you want the model to propose multiple *testable* hypotheses from observed patterns (e.g., AI-generated text detection)
This canonical case remained a study-design support path, not a code-driven execution run.
Basic 36/40|Specialized 57/60|Total 93/100
✅A1The hypogenic output structure matches the documented deliverable
✅A2The instruction path remains actionable for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 4 / 4
89
Variant A✅ Pass
Benchmarking competing explanations by generating a hypothesis bank and evaluating them consistently on validation/test splits
This variant a case remained a study-design support path, not a code-driven execution run.
Basic 34/40|Specialized 55/60|Total 89/100
✅A1The hypogenic output structure matches the documented deliverable
✅A2The instruction path remains actionable for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 4 / 4
87
Edge✅ Pass
Automated hypothesis generation (HypoGeniC): iteratively proposes and improves hypotheses using dataset feedback
This edge case remained a study-design support path, not a code-driven execution run.
Basic 33/40|Specialized 54/60|Total 87/100
✅A1The hypogenic output structure matches the documented deliverable
✅A2The instruction path remains actionable for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 4 / 4
87
Variant B✅ Pass
Literature + data integration (HypoRefine): extracts literature insights from PDFs and refines hypotheses jointly with empirical signals
Literature + data integration (HypoRefine): extracts literature... stayed in planning mode and returned a bounded design deliverable without relying on a runnable script.
Basic 32/40|Specialized 55/60|Total 87/100
✅A1The hypogenic output structure matches the documented deliverable
✅A2The instruction path remains actionable for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 4 / 4
87
Stress✅ Pass
End-to-end case for Automated hypothesis generation (HypoGeniC): iteratively proposes and improves hypotheses using dataset feedback
End-to-end case for Automated hypothesis generation (HypoGeniC):... stayed in planning mode and returned a bounded design deliverable without relying on a runnable script.
Basic 29/40|Specialized 58/60|Total 87/100
✅A1The hypogenic output structure matches the documented deliverable
✅A2The instruction path remains actionable for the documented case
✅A3The output stays fully within the documented skill boundary
✅A4The response quality is acceptable for the documented path
Pass rate: 4 / 4
Medical Task Total88.6 / 100
Key Strengths
- Primary routing is Protocol Design with execution mode A
- Static quality score is 84/100 and dynamic average is 80.6/100
- Assertions and command execution outcomes are recorded per input for human review
- Execution verification summary: No script verification was applicable