Paper Citation Record · LEDGER

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline

As of 23 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 1 inbound Pith citation observation for arXiv:2605.27440.

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

pith.paper-citation-record.v1
2605.27440 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T14:44:45.353335Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T15:31:55.519115Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-10T15:31:55.849223Z

Reference resolution

16 of 16 outbound references displayed

verified exact9
verified fuzzy6
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4b4237ce-0691-446e-be4c-4b315bb201b7 · outbound

This paper cites Prominence-Stratified Failure Modes in Retrieval-Augmented Commercial Recom- mendation: A 37,000-Run Audit.Unusual.ai Research Series, 2026a.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline Prominence-Stratified Failure Modes in Retrieval-Augmented Commercial Recom- mendation: A 37,000-Run Audit.Unusual.ai Research Series, 2026a

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T22:05:43.331470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8d1d5652-1137-4532-a7bd-6215935ada2c · outbound

This paper cites Divergent Recommendations, Convergent Diagnoses: Cross-Provider Failure-Mode Convergence in AI Commercial Recommendation.Unusual.ai Research Series, 2026b.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline Divergent Recommendations, Convergent Diagnoses: Cross-Provider Failure-Mode Convergence in AI Commercial Recommendation.Unusual.ai Research Series, 2026b

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T22:05:43.337571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6f7d0fe8-5162-4ac9-9c5e-1155cd7ddbe2 · outbound

This paper cites Persona Conditioning of Brand Recommendations in Retrieval-Augmented Com- mercial Chat: A Prominence-Stratified Cross-Provider Audit.Unusual.ai Research Series, 2026c.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline Persona Conditioning of Brand Recommendations in Retrieval-Augmented Com- mercial Chat: A Prominence-Stratified Cross-Provider Audit.Unusual.ai Research Series, 2026c

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T22:05:43.335456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cc5a8a63-c3be-46bc-a3f7-d7300817962e · outbound

This paper cites GEO: Generative Engine Optimization.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline GEO: Generative Engine Optimization

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:54:45.701123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bb372c13-286a-4994-8deb-64fb72784d94 · outbound

This paper cites Non-Determinism of "Deterministic" LLM Settings.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline Non-Determinism of "Deterministic" LLM Settings

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:54:45.696788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5d8f05b4-e5c7-465a-bc3e-7b8a0993a6da · outbound

This paper cites C., Ng, H.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline C., Ng, H

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T22:05:43.329397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 73cbd5dd-14d2-461e-ad39-54a0e86fdcb5 · outbound

This paper cites POSIX: A Prompt Sensitivity Index For Large Language Models.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline POSIX: A Prompt Sensitivity Index For Large Language Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:54:45.702142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation beaacf80-11aa-4226-ab62-7c82c0a45038 · outbound

This paper cites Investigating the Robustness of Retrieval-Augmented Generation at the Query Level.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline Investigating the Robustness of Retrieval-Augmented Generation at the Query Level

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:54:45.695242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0ee95957-15ce-4216-855b-d189f07e2900 · outbound

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

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-06-30T14:54:45.692449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a4938e5c-59f4-487c-9a97-5ef6c421c2cf · outbound

This paper cites InProceedings of the Fif- teenth ACM International Conference on Web Search and Data Mining, WSDM ’22, pages 1256–1265, New York, NY , USA.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline InProceedings of the Fif- teenth ACM International Conference on Web Search and Data Mining, WSDM ’22, pages 1256–1265, New York, NY , USA

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T14:54:45.703840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9a8dac22-793a-4bce-b61d-e5cb87d9b119 · outbound

This paper cites Query Rewriting for Retrieval-Augmented Large Language Models.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline Query Rewriting for Retrieval-Augmented Large Language Models

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:54:45.691504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5c523056-ccb3-4e61-b900-0a37fa955b40 · outbound

This paper cites Prompting Science Report 2: The Decreasing Value of Chain of Thought in Prompting.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline Prompting Science Report 2: The Decreasing Value of Chain of Thought in Prompting

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:54:45.690079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7b50aff4-ea21-453b-bffe-e656b00af517 · outbound

This paper cites State of What Art? A Call for Multi-Prompt LLM Evaluation.TACL, 2024.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline State of What Art? A Call for Multi-Prompt LLM Evaluation.TACL, 2024

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T22:05:43.333342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 32e7b45b-c48b-4dd2-a165-551ae0d4f7fd · outbound

This paper cites M., Xu, R., Weber, L., Silva, M., Bhardwaj, O., Choshen, L., de Oliveira, A.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline M., Xu, R., Weber, L., Silva, M., Bhardwaj, O., Choshen, L., de Oliveira, A

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T22:05:43.327495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2a250451-02d6-4609-8150-551b576494b5 · outbound

This paper cites Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-30T14:54:45.706466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2f670708-04fe-4947-8e00-a3bb446419b9 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-30T14:54:45.699010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 496d2d9d-2fa6-4c5e-90a5-0775bd35992e · inbound

Invisible to the Machine: Auditing AI Restaurant, Cafe, and Bar Recommendation Against a Complete Market Census cites this paper.

Invisible to the Machine: Auditing AI Restaurant, Cafe, and Bar Recommendation Against a Complete Market Census Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline

Reference 2000

Resolution: metadata mismatch; local_arxiv, observed 2026-08-10T15:31:55.853143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.