Paper Citation Record · LEDGER

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment

As of 16 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2608.02786.

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

pith.paper-citation-record.v1
2608.02786 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:04:24.060625Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

34 of 34 outbound references displayed

verified exact6
verified fuzzy14
unresolved13
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2f35660b-2527-48d6-a312-425aad65e843 · outbound

This paper cites AI, algorithmic, and automa- tion incidents and controversies (AIAAIC).

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment AI, algorithmic, and automa- tion incidents and controversies (AIAAIC)

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:26.230100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 479a26f6-5d22-4eeb-98b5-ae8f76ca2e57 · outbound

This paper cites Amershi, A.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Amershi, A

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:26.188822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 946d5e6c-6ccd-400c-bf53-f37308b2cd25 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Constitutional AI: Harmlessness from AI Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:23.627074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a3e2fa3-0649-4a46-a5b7-c6696cc4c56e · outbound

This paper cites an unresolved cited work.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:04:26.118990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 30c17db6-ca0f-41bc-9d90-4ac7a3cdd516 · outbound

This paper cites Air canada chatbot liable for misin- formation on bereavement fares.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Air canada chatbot liable for misin- formation on bereavement fares

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:26.088370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 08c7f2d2-ff2d-481a-9a88-a8dba037ecf3 · outbound

This paper cites Reg- ulation (EU) 2022/2554 on digital oper- ational resilience for the financial sector (DORA).

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Reg- ulation (EU) 2022/2554 on digital oper- ational resilience for the financial sector (DORA)

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:26.044760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 73173ad7-777a-4743-b13a-3951cde5be8d · outbound

This paper cites Reg- ulation (EU) 2024/1689 of the european parliament and of the council laying down harmonised rules on artificial intelligence (Artificial Intelligence Act).

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Reg- ulation (EU) 2024/1689 of the european parliament and of the council laying down harmonised rules on artificial intelligence (Artificial Intelligence Act)

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:26.009590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fd5e9466-f582-4561-a164-a36cf9df61c0 · outbound

This paper cites Artificial in- telligence in financial services: Review of firms’ approaches to consumer duty com- pliance.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Artificial in- telligence in financial services: Review of firms’ approaches to consumer duty com- pliance

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:25.931900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3868427a-af40-4d44-b434-ca88c54d0745 · outbound

This paper cites When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:04:25.121819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6e003452-1c2d-4d95-92bf-4921e4227ea0 · outbound

This paper cites Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:23.732184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcce6e00-c871-4bc3-b890-26316eb67ae8 · outbound

This paper cites A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:23.751900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ae260f-227d-4d24-9c09-04f4a1e07920 · outbound

This paper cites Fix GRPO importance sampling ratio: Replace per-token with sequence-mean in KL bias correction (PR #6594).

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Fix GRPO importance sampling ratio: Replace per-token with sequence-mean in KL bias correction (PR #6594)

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:25.890032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8ea11412-17b1-48bb-8b1d-54037b74223c · outbound

This paper cites an unresolved cited work.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:04:25.862065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1e9592bc-eaf7-484e-8a31-af869452f654 · outbound

This paper cites Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:04:24.898299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7e93ba4a-09b0-49f6-8880-cefa28039590 · outbound

This paper cites an unresolved cited work.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:04:25.836662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7188c347-094e-4816-9492-cfde6cdb6ca5 · outbound

This paper cites Holistic Evaluation of Language Models.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Holistic Evaluation of Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:23.826890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bf4dc3b-8337-4205-a0d8-964c4a3ee2fc · outbound

This paper cites From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:04:24.778735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2ad2f21b-f61a-4bfb-89ec-e7bc1e67c88e · outbound

This paper cites McGregor.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment McGregor

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:25.783024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ff4080ba-0505-4e6c-96b2-e36dbdbafa8c · outbound

This paper cites Ouyang, J.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Ouyang, J

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:25.723267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 645fc9e2-ba59-4820-a3fb-d9520b6b5da2 · outbound

This paper cites Paleyes, R.-G.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Paleyes, R.-G

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:25.655400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation abfa905d-fb2e-466a-9b37-5a9e903819d5 · outbound

This paper cites an unresolved cited work.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:04:25.616113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ac80d417-8ba3-4c16-89fc-5543f03d4a0d · outbound

This paper cites Perez and I.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Perez and I

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:25.568302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 49e793f6-9d2d-4c04-8085-3fafaff01997 · outbound

This paper cites Post office Horizon IT inquiry: In- terim report.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Post office Horizon IT inquiry: In- terim report

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:25.514508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 54f32853-4833-4d07-9f12-3a6b47588d45 · outbound

This paper cites an unresolved cited work.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:04:25.471782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a523d257-e314-4f0c-b8b2-406b5a44572c · outbound

This paper cites Sculley, G.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Sculley, G

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:25.437970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bba8414c-267b-4453-ac41-1c5a944201de · outbound

This paper cites Constrained episodic reinforcement learning in concave-convex and knapsack settings.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Constrained episodic reinforcement learning in concave-convex and knapsack settings

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:04:24.633507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1bb434f8-16fd-45bd-9767-ebb0db64103e · outbound

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

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:24.001635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2cf3119-0509-49f2-805a-fd38157d3be4 · outbound

This paper cites an unresolved cited work.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Unresolved cited work

Reference 28

Resolution: verified exact; raw_fallback, observed 2026-08-15T15:04:24.477603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 361f4804-45fd-41c0-8157-5973a6fa9746 · outbound

This paper cites Detecting Pretraining Data from Large Language Models.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Detecting Pretraining Data from Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:24.025493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5b0d093-908d-4481-8ee5-25223d23b81e · outbound

This paper cites Stiennon, L.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Stiennon, L

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:25.339250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 90b12d60-1d60-4933-b82c-24b52976fa39 · outbound

This paper cites an unresolved cited work.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:04:25.290817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4195bbd2-6cf9-4f1b-bd56-248690b08a9e · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Jailbroken: How Does LLM Safety Training Fail?

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:24.049741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ee3447a-3267-438d-8c7c-1682d9e6c6d8 · outbound

This paper cites Zheng, W.-L.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Zheng, W.-L

Reference 33

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T15:04:25.232661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4c9e9614-ac3a-42bb-9f4f-64a6db18cfb9 · outbound

This paper cites Evaluating Agentic AI in the Wild: Failure Modes, Drift Patterns, and a Production Evaluation Framework.

Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment Evaluating Agentic AI in the Wild: Failure Modes, Drift Patterns, and a Production Evaluation Framework

Reference 2026

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:04:24.702289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

No inbound Pith citation observations are available.