rpl-23
C. elegans
Large ribosomal subunit protein uL14
What the model saw
Gene: rpl-23 Organism: Caenorhabditis elegans Known functions: Large ribosomal subunit protein uL14. large ribosomal subunit rRNA binding. structural constituent of ribosome.
View unredacted entry
Large ribosomal subunit protein uL14. large ribosomal subunit rRNA binding. structural constituent of ribosome.
Solver output
rpl-23 encodes the large ribosomal subunit protein uL14, a structural component of the 60S ribosomal subunit that binds 28S rRNA. In C. elegans, partial loss-of-function of large ribosomal subunit proteins (including rpl genes) has been repeatedly shown to extend lifespan by attenuating global translation rates, which mimics dietary restriction and downregulates TOR (TORC1) signaling—a key nutrient-sensing pathway. Reduced ribosomal activity lowers the production of pro-aging proteins and activates stress-response pathways. Thus, the normal function of rpl-23 (supporting full translational capacity) is associated with higher TOR-driven translation and shorter lifespan, meaning its loss is pro-longevity; conversely, its normal presence is anti-longevity in the context of aging. However, since the question asks about the gene's normal function influence on longevity, full ribosomal activity sustains high translation rates that promote aging via nutrient-sensing/TOR axis, making rpl-23's normal function anti-longevity.
GenAge curators classify each gene's normal function as promoting (Pro-Longevity) or opposing (Anti-Longevity) longevity, based on synthesis across studies. Loss-of-function effects can vary from this depending on the manipulation.
Advisor judgment
The model's final prediction is "pro_longevity" but the ground truth is "anti_longevity." Ironically, the model's own reasoning correctly identifies that rpl-23's normal function is anti-longevity (supporting high translation rates that promote aging), but then contradicts itself by outputting "pro_longevity" as the final answer. The mechanistic reasoning about ribosomal subunit knockdown extending lifespan via TOR/translation rate reduction is correct, but the model got confused about the framing (loss-of-function vs. normal function) and ultimately submitted the wrong label. This is a self-contradictory response where the reasoning supports the correct answer but the final output is wrong.
Raw API responses
solver
{
"reasoning": "rpl-23 encodes the large ribosomal subunit protein uL14, a structural component of the 60S ribosomal subunit that binds 28S rRNA. In C. elegans, partial loss-of-function of large ribosomal subunit proteins (including rpl genes) has been repeatedly shown to extend lifespan by attenuating global translation rates, which mimics dietary restriction and downregulates TOR (TORC1) signaling—a key nutrient-sensing pathway. Reduced ribosomal activity lowers the production of pro-aging proteins and activates stress-response pathways. Thus, the normal function of rpl-23 (supporting full translational capacity) is associated with higher TOR-driven translation and shorter lifespan, meaning its loss is pro-longevity; conversely, its normal presence is anti-longevity in the context of aging. However, since the question asks about the gene's normal function influence on longevity, full ribosomal activity sustains high translation rates that promote aging via nutrient-sensing/TOR axis, making rpl-23's normal function anti-longevity.",
"confidence": 0.62,
"key_pathways": [
"TOR/TORC1 nutrient sensing",
"ribosomal translation rate regulation",
"dietary restriction mimicry"
],
"mechanism_class": "deregulated_nutrient_sensing",
"longevity_influence": "pro_longevity"
}advisor
{
"notes": "The model's final prediction is \"pro_longevity\" but the ground truth is \"anti_longevity.\" Ironically, the model's own reasoning correctly identifies that rpl-23's normal function is anti-longevity (supporting high translation rates that promote aging), but then contradicts itself by outputting \"pro_longevity\" as the final answer. The mechanistic reasoning about ribosomal subunit knockdown extending lifespan via TOR/translation rate reduction is correct, but the model got confused about the framing (loss-of-function vs. normal function) and ultimately submitted the wrong label. This is a self-contradictory response where the reasoning supports the correct answer but the final output is wrong.",
"failure_mode": "right_answer_wrong_reasoning",
"answer_correct": false,
"mechanism_correct": true,
"reasoning_quality": 2,
"ground_truth_questionable": false
}