Paper Citation Record · LEDGER

Predicting Task Difficulty Without Rollouts

As of 17 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2608.05797.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2608.05797 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T23:25:20.526555Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

35 of 35 outbound references displayed

verified exact3
verified fuzzy5
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e0bba2fe-0bb1-491b-834e-ac0d945a7719 · outbound

This paper cites Olmo 3.

Predicting Task Difficulty Without Rollouts Olmo 3

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.458447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a9ab401-4ba1-4e9c-b875-53a64c9060c8 · outbound

This paper cites Mle-bench: Evaluating machine learning agents on machine learning engineering.

Predicting Task Difficulty Without Rollouts Mle-bench: Evaluating machine learning agents on machine learning engineering

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:25:21.893612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 78735c52-245e-4f5a-84b6-7a589b4e3369 · outbound

This paper cites Demystifying prompts in language models via perplexity estimation.

Predicting Task Difficulty Without Rollouts Demystifying prompts in language models via perplexity estimation

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:25:21.868696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a34605f4-7e0a-4eb8-8c5d-973f3a906b82 · outbound

This paper cites The Llama 3 Herd of Models.

Predicting Task Difficulty Without Rollouts The Llama 3 Herd of Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.423485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e95e670e-c795-4c33-a69c-fdad96b649c1 · outbound

This paper cites A rosetta stone for ai benchmarks.arXiv preprint arXiv:2512.00193,.

Predicting Task Difficulty Without Rollouts A rosetta stone for ai benchmarks.arXiv preprint arXiv:2512.00193,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.431316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6404e38-164e-44a2-ad34-aeff77ee642e · outbound

This paper cites Auto-Encoding Variational Bayes.

Predicting Task Difficulty Without Rollouts Auto-Encoding Variational Bayes

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.438878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9a3e6b1-6af2-40f7-8702-d757e1c18d07 · outbound

This paper cites Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation.

Predicting Task Difficulty Without Rollouts Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.442787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d40531c-cc6b-4a43-af1f-56815b822072 · outbound

This paper cites BRIDGE: Predicting Human Task Completion Time From Model Performance.

Predicting Task Difficulty Without Rollouts BRIDGE: Predicting Human Task Completion Time From Model Performance

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-07T23:25:21.501974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 52501f48-9867-4a49-9d26-9ebe4f115ba3 · outbound

This paper cites Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning.

Predicting Task Difficulty Without Rollouts Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.450375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0953aa5-4aa1-4722-8080-8571348054dc · outbound

This paper cites GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks.

Predicting Task Difficulty Without Rollouts GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.466023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96e45a33-36d2-4edf-9b49-4e1945035ed4 · outbound

This paper cites Humanity's Last Exam.

Predicting Task Difficulty Without Rollouts Humanity's Last Exam

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.470081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6b5a2d5-e75f-492d-a705-1f756d3bd4c2 · outbound

This paper cites Automatic Curriculum Learning For Deep RL: A Short Survey.

Predicting Task Difficulty Without Rollouts Automatic Curriculum Learning For Deep RL: A Short Survey

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.474015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 174efcb9-77d6-4e48-86a6-76dfe68948ad · outbound

This paper cites Training Reinforcement Learning Agents and Humans With Difficulty-Conditioned Generators.

Predicting Task Difficulty Without Rollouts Training Reinforcement Learning Agents and Humans With Difficulty-Conditioned Generators

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-07T23:25:20.966619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 16b42bd2-0ff4-4ff3-a43f-fda7207f427b · outbound

This paper cites Reliable and Efficient Amortized Model-based Evaluation.

Predicting Task Difficulty Without Rollouts Reliable and Efficient Amortized Model-based Evaluation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.489045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9d53eba-cd6f-4842-b84f-b86fbc306157 · outbound

This paper cites Benchmark Data Contamination of Large Language Models: A Survey.

Predicting Task Difficulty Without Rollouts Benchmark Data Contamination of Large Language Models: A Survey

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.498536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c8d5afb-8c2e-454f-9cf2-273d3799e70d · outbound

This paper cites An illusion of progress? assessing the current state of web agents.arXiv preprint arXiv:2504.01382,.

Predicting Task Difficulty Without Rollouts An illusion of progress? assessing the current state of web agents.arXiv preprint arXiv:2504.01382,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.503466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 708b96d4-f535-475c-b762-3cec4bfe223d · outbound

This paper cites Qwen3 Technical Report.

Predicting Task Difficulty Without Rollouts Qwen3 Technical Report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.507412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 311b4df5-1aed-4769-ae55-d894cc6527ca · outbound

This paper cites Cybench: A framework for evaluating cybersecurity capabilities and risks of language models.

Predicting Task Difficulty Without Rollouts Cybench: A framework for evaluating cybersecurity capabilities and risks of language models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:25:21.851248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 05eabc8a-2683-4b64-944c-a0883605f3e2 · outbound

This paper cites Edis: Diagnosing llm reasoning via entropy dynamics.arXiv preprint arXiv:2602.01288,.

Predicting Task Difficulty Without Rollouts Edis: Diagnosing llm reasoning via entropy dynamics.arXiv preprint arXiv:2602.01288,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.515298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2911df35-45ae-4891-8e95-dc49273de9e2 · outbound

This paper cites an unresolved cited work.

Predicting Task Difficulty Without Rollouts Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-07T23:25:21.839752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 43ab6abf-30d6-46cc-aa29-6f637b18a21b · outbound

This paper cites A.2 IRT fitting details The IRT model is fit on the observed binary entries of the agent-task response matrix.

Predicting Task Difficulty Without Rollouts A.2 IRT fitting details The IRT model is fit on the observed binary entries of the agent-task response matrix

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:25:21.828224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f09895f7-b821-4cbf-aa18-3855e666cc36 · outbound

This paper cites an unresolved cited work.

Predicting Task Difficulty Without Rollouts Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-07T23:25:21.815890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 448f91d0-4001-4474-ba87-47060b70a1fc · outbound

This paper cites HCAST: Human-Calibrated Autonomy Software Tasks.

Predicting Task Difficulty Without Rollouts HCAST: Human-Calibrated Autonomy Software Tasks

Reference 1960

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.478107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd24008f-7d94-46d1-b45c-723447228ba8 · outbound

This paper cites RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts.

Predicting Task Difficulty Without Rollouts RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts

Reference 1978

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.492888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4287b8ed-1894-4439-9cc8-db77e16e5bd2 · outbound

This paper cites Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces.

Predicting Task Difficulty Without Rollouts Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 2008

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.454221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa97920f-3c40-4c05-9308-fa9bbbfcba3b · outbound

This paper cites Refining Minimax Regret for Unsupervised Environment Design.

Predicting Task Difficulty Without Rollouts Refining Minimax Regret for Unsupervised Environment Design

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.394203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73b60335-e28b-496b-b9b9-fc4add245555 · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code.

Predicting Task Difficulty Without Rollouts Livecodebench: Holistic and contamination free evaluation of large language models for code

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.434930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe6ff6e8-8897-44bf-9a39-46a31b45b999 · outbound

This paper cites LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking.

Predicting Task Difficulty Without Rollouts LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.427524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a2f6e1b-4f0c-4f52-8d32-bb4b8e9c97af · outbound

This paper cites Agent psychometrics: Task-level performance prediction in agentic coding benchmarks.

Predicting Task Difficulty Without Rollouts Agent psychometrics: Task-level performance prediction in agentic coding benchmarks

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.415444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e07f15b2-fd35-44d4-8798-77fedaa9da41 · outbound

This paper cites Gen- eralization or memorization: Data contamination and trustworthy evaluation for large language models.

Predicting Task Difficulty Without Rollouts Gen- eralization or memorization: Data contamination and trustworthy evaluation for large language models

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:25:21.881241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b96fd2cc-786b-4f1f-806b-5527f438c682 · outbound

This paper cites Soft contamination means benchmarks test shallow general- ization.arXiv preprint arXiv:2602.12413,.

Predicting Task Difficulty Without Rollouts Soft contamination means benchmarks test shallow general- ization.arXiv preprint arXiv:2602.12413,

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.481760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1dd55f9-450c-4c5f-9925-693c8860ec52 · outbound

This paper cites SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?.

Predicting Task Difficulty Without Rollouts SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.407209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25939d38-e636-4860-88cd-3a9c09926ee3 · outbound

This paper cites The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?.

Predicting Task Difficulty Without Rollouts The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?

Reference 2024

Resolution: verified exact; local_arxiv, observed 2026-08-07T23:25:21.774648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a2a1c9aa-b064-4145-a9b9-eb1f5ed5b890 · outbound

This paper cites Attention head entropy of llms predicts answer correctness.arXiv preprint arXiv:2602.13699,.

Predicting Task Difficulty Without Rollouts Attention head entropy of llms predicts answer correctness.arXiv preprint arXiv:2602.13699,

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.462141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0bd2f59-d334-4cf0-b7c9-ef94231b0540 · outbound

This paper cites How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks.

Predicting Task Difficulty Without Rollouts How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-07T23:25:20.389296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.