Paper Citation Record · LEDGER

LLMs Can Teach Themselves to Better Predict the Future

As of 9 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 6 inbound Pith citation observations for arXiv:2502.05253.

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

pith.paper-citation-record.v1
2502.05253 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T20:20:35.406397Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:42:38.315838Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

27 of 27 outbound references displayed

verified exact1
verified fuzzy3
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation a3a53c92-9084-487d-83ff-e3cc00420273 · outbound

This paper cites ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities.

LLMs Can Teach Themselves to Better Predict the Future ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.292300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8487ca6-fca4-4229-a746-54746aebe939 · outbound

This paper cites an unresolved cited work.

LLMs Can Teach Themselves to Better Predict the Future Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-08T20:20:35.952754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f29330a6-4356-4b76-9a77-1ee323f64205 · outbound

This paper cites Financial Statement Analysis with Large Language Models.

LLMs Can Teach Themselves to Better Predict the Future Financial Statement Analysis with Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.302779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d3d1685-dc45-4ada-9112-dbb1e3889689 · outbound

This paper cites From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection.

LLMs Can Teach Themselves to Better Predict the Future From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.307549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41a90620-8ce0-442d-a6b9-5b44a2305747 · outbound

This paper cites an unresolved cited work.

LLMs Can Teach Themselves to Better Predict the Future Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-08T20:20:35.939951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a02b49ae-f3f8-48f0-a000-2b37738fd02b · outbound

This paper cites Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy.

LLMs Can Teach Themselves to Better Predict the Future Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.316355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6782c929-e13d-452c-ac4f-a1ff51d0e974 · outbound

This paper cites Approaching Human-Level Forecasting with Language Models.

LLMs Can Teach Themselves to Better Predict the Future Approaching Human-Level Forecasting with Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.321292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a9a7ad5-a868-4a72-9bc8-0a004e9512ea · outbound

This paper cites AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval.

LLMs Can Teach Themselves to Better Predict the Future AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-08T20:20:35.779167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f832ecc3-f8c4-4a12-a289-2e8725cc0fae · outbound

This paper cites an unresolved cited work.

LLMs Can Teach Themselves to Better Predict the Future Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.330583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ac05b3c-09a7-4cc2-8855-cce582f6580b · outbound

This paper cites Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm.

LLMs Can Teach Themselves to Better Predict the Future Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.334579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8769e92e-8130-477d-94dc-a3d54efb6253 · outbound

This paper cites Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models.

LLMs Can Teach Themselves to Better Predict the Future Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.339159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf206664-e78b-4ca7-a5b1-5476c21d94e7 · outbound

This paper cites Rafailov, A.

LLMs Can Teach Themselves to Better Predict the Future Rafailov, A

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.343657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ecb541a-324e-4c8f-99df-e662dc73fdba · outbound

This paper cites Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study.

LLMs Can Teach Themselves to Better Predict the Future Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.347604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcf4f610-34d9-4e75-854c-7b6e0c5a9168 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

LLMs Can Teach Themselves to Better Predict the Future DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.351927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e8ab1f4-1cda-424d-862e-545a548161a9 · outbound

This paper cites Abdin, J.

LLMs Can Teach Themselves to Better Predict the Future Abdin, J

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:20:35.917043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b1e6cc14-ddbf-4373-8cd7-44ed5e5b784e · outbound

This paper cites GPT-4o System Card.

LLMs Can Teach Themselves to Better Predict the Future GPT-4o System Card

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.364455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e18513-bf9d-4919-b1b9-d841f5e64942 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

LLMs Can Teach Themselves to Better Predict the Future GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.368660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dde0ec0-afa9-44ab-9896-ded730f04694 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

LLMs Can Teach Themselves to Better Predict the Future Measuring Mathematical Problem Solving With the MATH Dataset

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.372856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecdcafbd-c60f-4938-b87f-6aa2b9f026f6 · outbound

This paper cites Qwen2.5 Technical Report.

LLMs Can Teach Themselves to Better Predict the Future Qwen2.5 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.377324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4c579bf-b7a1-455d-806e-4a85ac3e8252 · outbound

This paper cites Show Your Work: Scratchpads for Intermediate Computation with Language Models.

LLMs Can Teach Themselves to Better Predict the Future Show Your Work: Scratchpads for Intermediate Computation with Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.381457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfde8a6b-4b43-494f-8354-adbd61df2d46 · outbound

This paper cites Nash Learning from Human Feedback.

LLMs Can Teach Themselves to Better Predict the Future Nash Learning from Human Feedback

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.385689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e481466-5886-4187-9bb8-399eadc7eee4 · outbound

This paper cites ExpertPrompting: Instructing Large Language Models to be Distinguished Experts.

LLMs Can Teach Themselves to Better Predict the Future ExpertPrompting: Instructing Large Language Models to be Distinguished Experts

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.389730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1b6f11d-6fec-4f46-b00a-8a5f13a55bb7 · outbound

This paper cites an unresolved cited work.

LLMs Can Teach Themselves to Better Predict the Future Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-08T20:20:35.903486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7cec682e-ab67-4df4-968a-a7aa20c38df3 · outbound

This paper cites Benjamini and Y.

LLMs Can Teach Themselves to Better Predict the Future Benjamini and Y

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:20:35.889328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7cf5c46a-3cb3-4b61-8567-6ad78eed7246 · outbound

This paper cites an unresolved cited work.

LLMs Can Teach Themselves to Better Predict the Future Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-08T20:20:35.875767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 05eeb110-3ffc-4272-a3c2-9219e29d77fa · outbound

This paper cites Huang, X.

LLMs Can Teach Themselves to Better Predict the Future Huang, X

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:20:35.862125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f8d93a3e-89e0-4b4b-950f-f75fb9295a40 · outbound

This paper cites Phi-4 Technical Report.

LLMs Can Teach Themselves to Better Predict the Future Phi-4 Technical Report

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T20:20:35.360201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e80675f6-8f4c-4e8a-bd3f-5b246f79b6d7 · inbound

Prompt Engineering Large Language Models' Forecasting Capabilities cites this paper.

Prompt Engineering Large Language Models' Forecasting Capabilities LLMs Can Teach Themselves to Better Predict the Future

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:42:38.315838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b890b0b9-bdee-45fe-8b8f-a21e56b3cacc · inbound

Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts cites this paper.

Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts LLMs Can Teach Themselves to Better Predict the Future

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T14:22:31.315943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c7ddbb0-5645-4eea-a73c-510a6c9fb2bc · inbound

ClinQueryAgent: A Conversational Agent for Population Health Management cites this paper.

ClinQueryAgent: A Conversational Agent for Population Health Management LLMs Can Teach Themselves to Better Predict the Future

Reference 177

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:33:55.595457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0323c331-cb35-4e73-a3a4-caffdb86b8ec · inbound

StakeBench: Evaluating Language Understanding Grounded in Market Commitment cites this paper.

StakeBench: Evaluating Language Understanding Grounded in Market Commitment LLMs Can Teach Themselves to Better Predict the Future

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T21:43:58.617527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2feff8c3-9c75-4290-829a-6eab0d18db06 · inbound

Verifiable Rewards for Calibrated Probabilistic Forecasting cites this paper.

Verifiable Rewards for Calibrated Probabilistic Forecasting LLMs Can Teach Themselves to Better Predict the Future

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T19:47:18.739986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e73e150f-594b-4f83-ad2e-ac9d6f02ec42 · inbound

Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry cites this paper.

Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry LLMs Can Teach Themselves to Better Predict the Future

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-07-03T14:48:32.592091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.