Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-30T23:59:10.797762Z
Paper Citation Record · LEDGER
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
As of 15 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 1 inbound Pith citation observation for arXiv:2605.03217.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-12T06:23:49.752475Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
12 of 12 outbound references displayed
- verified exact6
- verified fuzzy1
- unresolved3
- parse uncertain0
- malformed identifier0
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation ddfe04df-5058-4e9f-af23-17d4f1abb550 · outbound
This paper cites Constitutional AI: Harmlessness from AI Feedback.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability Constitutional AI: Harmlessness from AI Feedback
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T00:25:10.316448Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 43afc6c4-41a1-4eed-81a8-7ec856d3dceb · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T00:25:10.313490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a19b7205-130e-4674-9cc6-f64ec74858fc · outbound
This paper cites The Capacity for Moral Self-Correction in Large Language Models.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability The Capacity for Moral Self-Correction in Large Language Models
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T00:25:10.319507Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation dd8a28f2-da1c-40cd-97aa-e824a3b6d3c9 · outbound
This paper cites Unboxing Occupational Bias: Grounded Debiasing of LLMs with U.S. Labor Data.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability Unboxing Occupational Bias: Grounded Debiasing of LLMs with U.S. Labor Data
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T00:25:10.322823Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 104a090f-2ae9-4b21-8b56-6c87f5d29f43 · outbound
This paper cites Distilling the Knowledge in a Neural Network.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability Distilling the Knowledge in a Neural Network
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T00:25:10.325625Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation b8ab3419-7e5e-4d04-b8e3-c8148b5bc134 · outbound
This paper cites Language Model Alignment in Multilingual Trolley Problems.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability Language Model Alignment in Multilingual Trolley Problems
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T00:25:10.302945Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 02e50204-3f55-461d-b8e3-f7c50349e26d · outbound
This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T00:25:10.306973Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation dd831664-28de-433e-8fe1-996f2e523a09 · outbound
This paper cites Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T00:25:10.310274Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 17083016-82b3-424d-b2e6-7ecc06495f03 · outbound
This paper cites Our tiered evaluation framework and mechanistic analysis are designed to make model biases more transparent and auditable.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability Our tiered evaluation framework and mechanistic analysis are designed to make model biases more transparent and auditable
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T09:43:36.276708Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation c094d000-1a1b-410e-b937-565caa20ff37 · outbound
This paper cites an unresolved cited work.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T09:43:36.278564Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 36010f41-fcf6-4a89-9d8c-c8d877e88884 · outbound
This paper cites an unresolved cited work.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability Unresolved cited work
Reference 11
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T09:43:36.280634Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 9a7aad71-2208-4a5f-8ad4-cdbae4830215 · outbound
This paper cites an unresolved cited work.
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability Unresolved cited work
Reference 12
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T09:43:36.280308Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Pith citing papers
Observation 744e89d5-6068-46e3-ac0f-0634cc296711 · inbound
Where do LLMs Fall Short in CBT-Guided Affective Reasoning? cites this paper.
Where do LLMs Fall Short in CBT-Guided Affective Reasoning? Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T06:23:49.752475Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.