Pith. sign in

Paper Citation Record · LEDGER

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents

As of 18 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2608.08570.

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

pith.paper-citation-record.v1
2608.08570 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:35:18.744747Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

16 of 16 outbound references displayed

  • verified exact0
  • verified fuzzy3
  • unresolved12
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4d1d7f16-743d-4066-af2a-cd91f596d911 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Evaluating Large Language Models Trained on Code

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.235069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.235069Z digest=sha256:b1eb6890b3e069250a7214b340fb7732f095c776121841276a4c14ef4d979926

Observation f22dbb5a-1e5b-4539-a6fa-9c7809aa9d5e · outbound

This paper cites AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.329071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.329071Z digest=sha256:3f67f10e1f3a9745f253efbc8ed1cef2207d3b6687372df2e6f265882a7a82cd

Observation 9c6bb5cd-cc98-40bb-a960-ffb9b589b79d · outbound

This paper cites ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.409597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.409597Z digest=sha256:b9c2bceeee04c52b139ad48b9427084819f79857df00d6938c5de0ed9ec26761

Observation af854849-8964-473a-b613-5f374d05d65d · outbound

This paper cites Training Software Engineering Agents and Verifiers with SWE-Gym.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Training Software Engineering Agents and Verifiers with SWE-Gym

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.445034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.445034Z digest=sha256:1c3d0efd5eb5354748f45ef3084978a27441e9a49dadec2b1616fc815ee68f10

Observation a356471a-ef8a-4e2e-82e8-aab2fc51e78e · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.484752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.484752Z digest=sha256:8eabe3668c120f6c57d9f6c4ba0c8e7a1a0624f6bde10effff1c83a14778c9e9

Observation ef46e9cc-3352-45cd-a2b1-76fb55692f5e · outbound

This paper cites Step Rejection Fine-Tuning: A Practical Distillation Recipe.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Step Rejection Fine-Tuning: A Practical Distillation Recipe

Reference 10

Resolution
metadata mismatch
local_arxiv, observed 2026-08-14T04:35:19.515418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-14T04:35:18.504154Z digest=sha256:e1ef992e16c2d06bf686b064b48c69940e6ee04ef056e7d9d6c46e7818c6f2eb

Observation 09cacc12-62c6-4acf-b07c-4ff79c5c4006 · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.527928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.527928Z digest=sha256:2f856137ef517e78426e244d39e0fb85b8991b69df8ec98c3c32b5fd4eda361a

Observation f0152294-7a94-4411-9220-627b349e0387 · outbound

This paper cites Agentless: Demystifying LLM-based Software Engineering Agents.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Agentless: Demystifying LLM-based Software Engineering Agents

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.611502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.611502Z digest=sha256:8a67348dd0b56888b2e27ff934ea392e20e6eb97e77dae0a7c5b595ccca717e2

Observation eb9fed2f-b065-450e-9b92-9a67a128c79a · outbound

This paper cites InThe Thirty-eighth Annual Conference on Neural In- formation Processing Systems.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents InThe Thirty-eighth Annual Conference on Neural In- formation Processing Systems

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T04:35:20.166634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-14T04:35:18.664753Z digest=sha256:896f14f8685201b8fa2e58f8ab93e4e385c31ae4ee7c8da2d8255ecb92793164

Observation ffd5d77b-22bc-4f8a-ba4b-daa9f3db84a4 · outbound

This paper cites Scaling Relationship on Learning Mathematical Reasoning with Large Language Models.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.706054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.706054Z digest=sha256:55e5886246090080f94c6d01140431a28462a7bb6b877048645660837c7b3e5e

Observation 929e4b31-61c1-478f-8759-3e0f8116d16b · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents GLM-5: from Vibe Coding to Agentic Engineering

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.744747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.744747Z digest=sha256:bb3d2bde63cbca7af34cb623908fccbac5e8a5d190f42986fdd6eb4b4bd86bea

Observation f54916a3-27ea-4420-8596-d6834539b77d · outbound

This paper cites InInternational Conference on Machine Learning, 4940–4950.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents InInternational Conference on Machine Learning, 4940–4950

Reference 2021

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T04:35:20.254752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-14T04:35:18.349104Z digest=sha256:cb8bd6993996502414b2a709b243f8a67e600a9be60046a7f30eabee08123bf9

Observation 30d1c0ad-cfce-4fbe-9cab-4dfb8204f905 · outbound

This paper cites Reinforced Self-Training (ReST) for Language Modeling.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Reinforced Self-Training (ReST) for Language Modeling

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.287222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.287222Z digest=sha256:e5bd09bb9b37e43d5665f1b4c671f29c668208cbf0cacc4dbe57854d944d8fb0

Observation 87cd4cd1-9581-42f6-97d7-1441209e6a48 · outbound

This paper cites InInternationalConference on Learning Representations, volume 2024, 57734–57811.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents InInternationalConference on Learning Representations, volume 2024, 57734–57811

Reference 2024

Resolution
verified fuzzy
raw_fallback, observed 2026-08-14T04:35:20.405464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-14T04:35:18.254931Z digest=sha256:0c3d906467074c6a0e58008fc0b7020e507a59b7b3c8b0123b9272aeb304b493

Observation ac2fa8c3-3207-4f37-aa2d-4f7a74718ad6 · outbound

This paper cites Exploring Expert Failures Improves LLM Agent Tuning.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Exploring Expert Failures Improves LLM Agent Tuning

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.372917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.372917Z digest=sha256:2510cfcdf89e97aea847bd6f3843a9e35c1e16a7d778ba32759ae0eec46bfc5c

Observation dcc81b6a-d705-4067-af07-c98c4c9c2f86 · outbound

This paper cites an unresolved cited work.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Unresolved cited work

Reference 2026

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:18.564768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:18.564768Z digest=sha256:f64c4f6b26d0eb39accef88c40e7da6e85c8e2c562d3c89f64c58ac6df88e93e

Pith citing papers

No inbound Pith citation observations are available.