paper-0096 · paper · 2017
Paul F. Christiano et al.
Learning reward from human comparisons; the seed of RLHF.
Academic, score -0.1953
| Metric | Status | Value | Norm. | Weight | Contribution | Source | Confidence | Provenance |
|---|---|---|---|---|---|---|---|---|
| citation_count | present | 508.0 | 0.002282 | 0.5 | 0.001141 | 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 | 9.0 | 0.571429 | 0.05 | 0.028571 | 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 0.0290
| Metric | Status | Value | Norm. | Weight | Contribution | Source | Confidence | Provenance |
|---|---|---|---|---|---|---|---|---|
| citation_count | present | 508.0 | 0.002282 | 0.2 | 0.000456 | 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 | 9.0 | 0.571429 | 0.4 | 0.228571 | 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 -0.2673
| Metric | Status | Value | Norm. | Weight | Contribution | Source | Confidence | Provenance |
|---|---|---|---|---|---|---|---|---|
| citation_count | present | 508.0 | 0.002282 | 0.25 | 0.000571 | 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 | 9.0 | 0.571429 | 0.1 | 0.057143 | 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.