Claims Browser

Absolute revisit scores are sensitive to rendering stability, repetitive content, and failed motion, making them unreliable metrics

"This ambiguity makes absolute revisit scores sensitive to rendering stability, repetitive content, and failed motion."

R2M-Bench's Overall NMR metric correlates with human consistency judgments at Spearman's ρ=0.547

"Overall NMR correlates with human consistency judgments at Spearman's $ρ=0.547$ (95\% CI $[0.45,0.63]$)."

Relative calibration substantially reduces the slow-motion shortcut in video world model evaluation, with within-model correlation magnitude of 0.072 compared to 0.207 for raw revisit similarity

"Its within-model correlation magnitude with generated motion is $0.072$, compared with $0.207$ for raw revisit similarity, indicating that relative calibration substantially reduces the slow-motion shortcut."

DreamX-World-Memo achieves the highest Overall NMR among evaluated video models

"DreamX-World-Memo achieves the highest Overall NMR among the evaluated video models."

Same-rollout relative calibration is a practical way to distinguish revisit-specific consistency from generic temporal stability in video world models

"these results support same-rollout relative calibration as a practical way to distinguish revisit-specific consistency from generic temporal stability."

Industrial sites contain large volumes of read-only telemetry, but few benchmarks specify how to compile these records into executable multi-turn agent tasks

"Industrial sites contain large volumes of read-only telemetry, but few benchmarks specify how to compile these records into executable multi-turn agent tasks."

BTS-AgentBench provides a telemetry-to-episode construction method that successfully produces 532 rows with multiple advanced features including clarification, goal revision, and evidence attribution

"The 532-row release adds clarification, goal revision, timestamp policy, quality-gated reporting, and evidence attribution while preserving the source computation and split."

The BTS-AgentBench construction is fully reproducible, with two independent builds matching all logical exports and reproducing the exact same train/dev/test artifact

"Two independent raw-to-episode builds match all 11 logical tool-store exports and reproduce the released 356/87/89 train/dev/test artifact exactly."

GPT-5.5 achieves perfect completion on the XAI4HEAT held-out test split when evaluated using the shared construction path

"on its 41-row held-out test split, the controller completes 0 rows and the retained GPT-5.5 execution completes all 41."

Block drafters using all-parallel conditioning hit a fundamental information floor of 28.6% rejection at the final slot on Qwen3-4B, limiting maximum per-slot acceptance to 71%

"the all-parallel floor reaches $0.286$ at the final slot on Qwen3-4B, limiting even the best proposal to $71\%$ per-slot acceptance"

Adding just one realized token removes 86-100% of the information floor in block drafters, demonstrating strong locality in speculative decoding

"one realised token removes $86$--$100\%$ of this floor, a locality also recovered by an independent mutual-information analysis"

Current drafter models are far from optimal, with model gap accounting for 43-64% of DFlash rejection and 85-92% of DSpark's oracle-conditioned rejection at the final slot

"current drafters remain far above their floors: the final-slot model gap accounts for $43$--$64\%$ of DFlash rejection and $85$--$92\%$ of DSpark's oracle-conditioned rejection"

Block drafter rejection stems from two distinct sources that can be separated: missing within-block path information (information floor) and imperfect modeling of observable information (model gap)

"Their rejection mixes two losses: missing within-block path information and imperfect modelling of observable information"

Verbalized eval-awareness in chain-of-thought can be identified as capabilities-flavored or safety-flavored, and these framings predict compliance very differently

"verbalized eval-awareness in chain-of-thought can be identified as capabilities-flavored ("the user is testing my ability to follow instructions"), safety-flavored ("the user is testing my boundaries"), both, or neither: framings that predict compliance very differently"

On Qwen3-32B over the FORTRESS dataset, capabilities-framing predicts compliance with a +24 to +46 percentage-point gap over safety-framing across all tested steering conditions

"On Qwen3-32B over the FORTRESS dataset, capabilities-framing predicts compliance with a +24 to +46 percentage-point gap over safety-framing across all tested steering conditions"

A CoT-prefill intervention demonstrates a causal link between eval-awareness framing and compliance, with 10 of 11 prefills shifting compliance in the predicted direction

"A CoT-prefill intervention on eval-awareness-negative rollouts suggests the link is causal, with 10 of 11 prefills shifting compliance in the predicted direction"

Eval-awareness is not behaviorally uniform - aggregate suppression rates can move while the safety-relevant component does not

"eval-awareness is not behaviorally uniform: aggregate suppression rates can move while the safety-relevant component does not"

The same percentage of eval-awareness suppression can correspond to qualitatively different behavioral outcomes

"the same "X% suppression of eval-awareness" can correspond to qualitatively different behavioral outcomes"