Buildability / Receipt
This public receipt window renders only fields present in the canonical receipt object, deterministic fixture receipt, or canonical evidence receipt. Missing compute, demo, hash, signature, approval, telemetry, and adoption fields stay explicit.
Public buildability page receipt window
/buildability/when-rlhf-fails-a-mechanistic-taxonomy-of-reward-hacking-collapse-and-evaluator-gaming
Subject: When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming
Verdict
Watch
Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.
Time to first demo
Insufficient data
No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.
Data
{"file name": "input.pdf", "number of pages": 20, "author": "Zelalem Abahana", "title": "When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming"
Truth Boundary
Buildability surfaces only report computed viability and proof receipts. They do not claim live production usage, pilot outcomes, founder sign-off, public Brier calibration, judge divergence, or external adoption unless explicitly sourced.
Compute
{"file name": "input.pdf", "number of pages": 20, "author": "Zelalem Abahana", "title": "When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming", "creation date": null, "modification date": null, "kids": []}
Inference
{"file name": "input.pdf", "number of pages": 20, "author": "Zelalem Abahana", "title": "When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming", "creation date": null, "modification date": null, "kids": []}
Hardware
{"file name": "input.pdf", "number of pages": 20, "author": "Zelalem Abahana", "title": "When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming", "creation date": null, "modification date": null, "kids": []}
Receipt path
/buildability/when-rlhf-fails-a-mechanistic-taxonomy-of-reward-hacking-collapse-and-evaluator-gaming
Paper ref
when-rlhf-fails-a-mechanistic-taxonomy-of-reward-hacking-collapse-and-evaluator-gaming
arXiv id
2606.03238
Generated at
2026-06-03T20:43:31.790Z
Evidence freshness
fresh
Last verification
2026-06-03T20:43:31.790Z
Sources
3
References
0
Coverage
50%
Lineage hash
0d9bad6107a4fe53189e8999a85d049f90d087339ab9eb741952a2ae52943b3f
Canonical opportunity-kernel lineage hash.
External signature
unsigned_external
No founder, registry, pilot, or production-adoption signature is attached to this receipt.
Verification
not_verified
Verification is blocked until an external signature is provided.
Canonical opportunity-kernel evidence is available for this receipt window.
repo_url
references