Paper Citation Record · LEDGER

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis

As of 8 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2505.17636.

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

pith.paper-citation-record.v1
2505.17636 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:47:18.940629Z

measured 41 of 41 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

41 of 41 outbound references displayed

verified exact0
verified fuzzy23
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9a4940c3-fa52-4212-b2e1-57535383a302 · outbound

This paper cites Ethical and social risks of harm from Language Models.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Ethical and social risks of harm from Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:15.146003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f677f231-34e7-4f25-add8-0cc703fb144f · outbound

This paper cites An Overview of Catastrophic AI Risks.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis An Overview of Catastrophic AI Risks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:15.195620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce9d0c70-3b33-4e86-a02f-362175bf25a3 · outbound

This paper cites (2021) ”On the dangers of stochastic parrots: Can languagemodels be too big?”, Proceedings of the 2021 ACM conference on fairness, accountability, and transparency.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2021) ”On the dangers of stochastic parrots: Can languagemodels be too big?”, Proceedings of the 2021 ACM conference on fairness, accountability, and transparency

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:26.809492Z

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 21b96249-913d-4112-89c4-a794bb68a231 · outbound

This paper cites SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:15.353466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c96f53e1-b9e5-4818-8895-f6a3316ab16c · outbound

This paper cites BAN: Detecting Backdoors Activated by Adversarial Neuron Noise.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis BAN: Detecting Backdoors Activated by Adversarial Neuron Noise

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:15.428425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63fec357-a027-483a-804a-377e6c460578 · outbound

This paper cites (2025) ”Evaluating the Consistency of LLM Evaluators”, Proceedings of the 31st International Conference on Computational Linguistics, pp.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2025) ”Evaluating the Consistency of LLM Evaluators”, Proceedings of the 31st International Conference on Computational Linguistics, pp

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:26.504916Z

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 a9d6bb60-6e4a-463a-80c1-2a578f029ffa · outbound

This paper cites &Gurevych, I.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis &Gurevych, I

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:26.194856Z

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 4685f60a-b766-4133-b6e0-255802bd124b · outbound

This paper cites (1967) ”So me methods for classification and analysis of multivariate observations”, Proceedings of the fifthBerkeley symposium on mathematical statistics and probability, V ol.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (1967) ”So me methods for classification and analysis of multivariate observations”, Proceedings of the fifthBerkeley symposium on mathematical statistics and probability, V ol

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:26.030685Z

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 b4ba2c0c-e9fd-4450-9a50-6b8ef6942f77 · outbound

This paper cites Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:15.798129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0e0df1f-ec45-4c9a-8439-a63939c10e9e · outbound

This paper cites WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:15.887083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff04302f-8f41-4dab-9efe-6481ea1961c8 · outbound

This paper cites an unresolved cited work.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:47:25.796687Z

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 71395c66-c24d-44c3-a1bb-e711f714e7f4 · outbound

This paper cites (2024) ”Building Datasets to Enable Safer AI Responses”, Gretel.aiBlog.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2024) ”Building Datasets to Enable Safer AI Responses”, Gretel.aiBlog

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:25.555138Z

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 cfacede2-6633-4002-a242-d428cb0a9f32 · outbound

This paper cites an unresolved cited work.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:47:25.255064Z

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 2020cf8a-8cea-4447-afd5-95989282d4e7 · outbound

This paper cites H., & Dang, S.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis H., & Dang, S

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:24.987833Z

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 13658da2-f85a-4b32-b2f0-9390f4bf826b · outbound

This paper cites (2021) ”Pitfalls in clustering”, Scientific reports, V ol.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2021) ”Pitfalls in clustering”, Scientific reports, V ol

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:24.738531Z

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 e2989c02-2a63-45d9-bb39-27366b2eeb4c · outbound

This paper cites (1988) ”Statistical power analysis for the behavioral sciences”, Routledge.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (1988) ”Statistical power analysis for the behavioral sciences”, Routledge

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:24.445457Z

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 6a7dae3b-ebc9-4918-b7ab-f8e3ca925da4 · outbound

This paper cites & Shukla, D.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis & Shukla, D

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:24.138371Z

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 43d9db66-4908-45fb-bdec-83d87b8bf082 · outbound

This paper cites an unresolved cited work.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:47:23.852000Z

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 93e7b47a-9a89-4751-aa8d-1b27ee0d3ca1 · outbound

This paper cites (2013) ”Detecting outliers: Do not use standard deviation aroun d themean, use absolute deviation around the median”, Journal of Experimental Social Psychology, V ol.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2013) ”Detecting outliers: Do not use standard deviation aroun d themean, use absolute deviation around the median”, Journal of Experimental Social Psychology, V ol

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:23.657678Z

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 f80ce694-9893-40b2-af71-891ff7b334ee · outbound

This paper cites (2012) ”Modern statistics for the social and behavioral sciences: A practical introduction”, CRC press.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2012) ”Modern statistics for the social and behavioral sciences: A practical introduction”, CRC press

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:23.425097Z

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 bd7f2bb8-e239-4f84-b49b-dddb32a65a31 · outbound

This paper cites MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:16.786525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e82aa5fc-e21f-45dc-b4cf-b01cb5c4bb0b · outbound

This paper cites MPNet: Masked and Permuted Pre-training for Language Understanding.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis MPNet: Masked and Permuted Pre-training for Language Understanding

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:16.887424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd6a052-5e19-40b5-adc0-9904e8739759 · outbound

This paper cites & Hinton, G.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis & Hinton, G

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:23.205940Z

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 464f1e1c-a9ab-49eb-80cb-97542e08a485 · outbound

This paper cites UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:17.010927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 121361b7-1d34-4566-bc48-6b010fec03cc · outbound

This paper cites & Berens, P.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis & Berens, P

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:22.963430Z

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 2aaa5fad-fc37-474b-8fea-5a6035a2cfaf · outbound

This paper cites an unresolved cited work.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:47:22.742044Z

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 e20895ac-2ab6-445b-92ea-b169f92f67c9 · outbound

This paper cites an unresolved cited work.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:47:22.524555Z

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 8356972a-221f-42c0-9e10-45cdef92c03b · outbound

This paper cites (2019) ”Automated optimizedparamet ers for t -distributed stochastic neighbor embedding improve visualization and analysis of large datasets”, Nature Communications, V ol.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2019) ”Automated optimizedparamet ers for t -distributed stochastic neighbor embedding improve visualization and analysis of large datasets”, Nature Communications, V ol

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:22.372700Z

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 78a69feb-c41f-4a10-b545-8be957251132 · outbound

This paper cites (2001) ”On the surprising behavior of distance metrics in high-dimensionalspace”, Proceedings of the 8th International Conference on Database Theory (ICDT), pp.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2001) ”On the surprising behavior of distance metrics in high-dimensionalspace”, Proceedings of the 8th International Conference on Database Theory (ICDT), pp

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:22.191361Z

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 6bc784da-2455-4d11-a942-a2641eec32f5 · outbound

This paper cites (2000) ”TheMahalanobis distance”, Chemometrics and Intelligent Laboratory Systems, V ol.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2000) ”TheMahalanobis distance”, Chemometrics and Intelligent Laboratory Systems, V ol

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:21.984032Z

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 d49a1e0f-9e5f-44ad-87d3-603f72058f6e · outbound

This paper cites (1999) ”Mahalanobis distance”, Research Letters in Information and Mathematical Sciences, V ol.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (1999) ”Mahalanobis distance”, Research Letters in Information and Mathematical Sciences, V ol

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:21.795517Z

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 da08703c-d299-4fd9-92d0-03d150e129f4 · outbound

This paper cites an unresolved cited work.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:47:21.565579Z

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 f0f711a2-eef2-4762-b14a-462b145a75cb · outbound

This paper cites an unresolved cited work.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:47:21.351726Z

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 87bec25f-6022-4649-8c55-feb422a8972f · outbound

This paper cites A., Albrecht, J., Irwin, D., & Raghavan, B.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis A., Albrecht, J., Irwin, D., & Raghavan, B

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:21.109366Z

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 641d81ce-fbc7-406f-a331-f9eefb809a1a · outbound

This paper cites (1987) ”Silhouettes: a graphical aid to the interpretation and validation of cluster analysis”, Journal ofComputational and Applied Mathematics, V ol.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (1987) ”Silhouettes: a graphical aid to the interpretation and validation of cluster analysis”, Journal ofComputational and Applied Mathematics, V ol

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:20.894898Z

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 c12f2307-fea5-4590-a8a4-25234a833a8e · outbound

This paper cites (2001) ”Estimating the number of clusters in a data set via the gap statistic”,Journal of the Royal Statistical Society B, V ol.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2001) ”Estimating the number of clusters in a data set via the gap statistic”,Journal of the Royal Statistical Society B, V ol

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:20.659823Z

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 3c70b773-3bdb-4544-a98c-dd51ee4b70b5 · outbound

This paper cites (2024) ”Examinin g the robustness of LLM evaluation to the distributional assumptions of benchmarks”, Annual Meeting of the Association for Computational Linguistics.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2024) ”Examinin g the robustness of LLM evaluation to the distributional assumptions of benchmarks”, Annual Meeting of the Association for Computational Linguistics

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:20.283192Z

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 c9add1d2-6c1a-40fb-8c88-f7cbd2ada6ca · outbound

This paper cites & Luccioni, A.S.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis & Luccioni, A.S

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:19.895922Z

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 f48cfb87-27b5-46d7-bc5e-6decbaf76a86 · outbound

This paper cites (2007) ”G* power 3: A flexible statistical power analysis program for the social, behavioral, and biomedical sciences”, Behavior research methods, V ol.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis (2007) ”G* power 3: A flexible statistical power analysis program for the social, behavioral, and biomedical sciences”, Behavior research methods, V ol

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:47:19.619504Z

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 0be717b6-d51e-4efb-8c3d-dd0fc51e6ff5 · outbound

This paper cites Semantics derived automatically from language corpora contain human-like biases.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Semantics derived automatically from language corpora contain human-like biases

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:18.808787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c8f4342-0248-448b-b82e-fc2ec76933ef · outbound

This paper cites Interpretable Deep Learning-Based Forensic Iris Segmentation and Recognition.

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis Interpretable Deep Learning-Based Forensic Iris Segmentation and Recognition

Reference 41

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T14:47:19.242745Z

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.

Pith citing papers

No inbound Pith citation observations are available.