Paper Citation Record · LEDGER

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding

As of 8 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2506.03489.

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

pith.paper-citation-record.v1
2506.03489 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:12:18.786568Z

measured 14 of 14 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 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

14 of 14 outbound references displayed

verified exact1
verified fuzzy3
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6df98904-ac88-4347-8c27-ebb1ae673a76 · outbound

This paper cites In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8503–8526, Miami, Florida, USA.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8503–8526, Miami, Florida, USA

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:12:19.339151Z

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 0cd5697a-653b-403c-bf91-c50201b3414a · outbound

This paper cites HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:18.722627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c2d88b2-495e-4d56-87bf-23ad4db61213 · outbound

This paper cites Contrastive Decoding Improves Reasoning in Large Language Models.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding Contrastive Decoding Improves Reasoning in Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:18.745502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e24b1441-87a3-46fa-abeb-1ad0cb9d892c · outbound

This paper cites The Llama 3 Herd of Models.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:18.751900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c01ff86-873d-47d0-b4b0-372d5cb3453f · outbound

This paper cites Qwen2 Technical Report.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding Qwen2 Technical Report

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:18.757584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 953eeec4-bd06-40a2-bf4d-992683bb46c2 · outbound

This paper cites DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:18.762796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 224f59ec-de88-4d84-9ecb-4429f4118c10 · outbound

This paper cites In ICML 2024 Workshop on Models of Human Feedback for AI Alignment.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding In ICML 2024 Workshop on Models of Human Feedback for AI Alignment

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:12:19.320080Z

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 373afa7c-66b6-4082-ac31-c733fa7398ae · outbound

This paper cites The highest results are madebold, with the second underlined.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding The highest results are madebold, with the second underlined

Reference 13

Resolution: verified exact; raw_fallback, observed 2026-08-07T11:12:19.013279Z

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 2c4eb242-34a0-4108-b1cf-ad73a68aeb6e · outbound

This paper cites For all experiments, we search the optimal hyper- parameters on development sets, and then employ the same hyper-parameters to evaluate models on hold-out test sets.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding For all experiments, we search the optimal hyper- parameters on development sets, and then employ the same hyper-parameters to evaluate models on hold-out test sets

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:12:19.301306Z

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 ae0c752d-3e32-457a-8d62-78ef8c3b689e · outbound

This paper cites JEC-QA: A Legal-Domain Question Answering Dataset.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding JEC-QA: A Legal-Domain Question Answering Dataset

Reference 2019

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T11:12:19.044509Z

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 d8000de7-f1b4-4d29-be6c-215df84ba17c · outbound

This paper cites Fusing finetuned models for better pretraining.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding Fusing finetuned models for better pretraining

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:18.728444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe36b336-7c67-491c-924c-aa5cff7709b0 · outbound

This paper cites Lawyer LLaMA Technical Report.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding Lawyer LLaMA Technical Report

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:18.739695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8500ef1c-c933-457e-a09e-f374ecaf3f3d · outbound

This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:18.691068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcf6cdf2-6387-4f71-9afc-e3607970c6fc · outbound

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

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:18.734093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.