paper-0144 · paper · 2022
Long Ouyang et al.
InstructGPT; RLHF at scale, the technique behind aligned chat models.
Academic, score -0.1939
| Metric | Status | Value | Norm. | Weight | Contribution | Source | Confidence | Provenance |
|---|---|---|---|---|---|---|---|---|
| citation_count | present | 4292.0 | 0.019316 | 0.5 | 0.009658 | OpenAlex | high | link |
| library_holdings | missing | recorded as missing, penalized by rule, never imputed | −0.1 | recorded as missing; penalized by rule, never imputed | ||||
| readership_persistence | present | 7.0 | 0.428571 | 0.05 | 0.021429 | OpenAlex | medium | link |
| syllabus_adoptions | missing | recorded as missing, penalized by rule, never imputed | −0.125 | recorded as missing; penalized by rule, never imputed | ||||
Broad Influence, score -0.0247
| Metric | Status | Value | Norm. | Weight | Contribution | Source | Confidence | Provenance |
|---|---|---|---|---|---|---|---|---|
| citation_count | present | 4292.0 | 0.019316 | 0.2 | 0.003863 | OpenAlex | high | link |
| library_holdings | missing | recorded as missing, penalized by rule, never imputed | −0.125 | recorded as missing; penalized by rule, never imputed | ||||
| readership_persistence | present | 7.0 | 0.428571 | 0.4 | 0.171429 | OpenAlex | medium | link |
| syllabus_adoptions | missing | recorded as missing, penalized by rule, never imputed | −0.075 | recorded as missing; penalized by rule, never imputed | ||||
Governance Practitioner, score -0.2773
| Metric | Status | Value | Norm. | Weight | Contribution | Source | Confidence | Provenance |
|---|---|---|---|---|---|---|---|---|
| citation_count | present | 4292.0 | 0.019316 | 0.25 | 0.004829 | OpenAlex | high | link |
| library_holdings | missing | recorded as missing, penalized by rule, never imputed | −0.15 | recorded as missing; penalized by rule, never imputed | ||||
| readership_persistence | present | 7.0 | 0.428571 | 0.1 | 0.042857 | OpenAlex | medium | link |
| syllabus_adoptions | missing | recorded as missing, penalized by rule, never imputed | −0.175 | recorded as missing; penalized by rule, never imputed | ||||
A rank is not a verdict on intrinsic worth. It is a transparent output of declared evidence, weights, and missing-data rules at a specific release date.
Disagree with this rank or a number? Challenge it with your evidence. Every challenge gets a public identifier and a published resolution.