Paper Citation Record · LEDGER

The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 28 inbound Pith citation observations for arXiv:2312.01552.

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

pith.paper-citation-record.v1
2312.01552 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 28 of 28 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:15:15.263799Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

10
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 56962391-eaa0-4ea2-9a87-3765dc60ad49 · inbound

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing cites this paper.

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 125

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:58:36.871379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7be68382-b3b8-4608-8f41-42053f3e9440 · inbound

CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation cites this paper.

CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T12:09:42.956749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c97be210-02c5-4308-8bd5-5cabcec9f12c · inbound

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models cites this paper.

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T05:55:12.992368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceef9326-51bc-4f94-bee1-53e504c68cf3 · inbound

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense cites this paper.

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T22:11:59.790507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e313cce4-0ca2-4cdd-b0d0-a77d6893b51d · inbound

Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes cites this paper.

Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T15:18:19.096405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 081e9339-f6f7-42ea-9357-433d651db1c7 · inbound

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models cites this paper.

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:02.007476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3469f3d8-c65e-4e37-bb2e-5e0afe358758 · inbound

Beyond the Surface: Measuring Self-Preference in LLM Judgments cites this paper.

Beyond the Surface: Measuring Self-Preference in LLM Judgments The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:26:04.503845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d13333a-89f9-4752-a905-4f0fee3be0f9 · inbound

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding cites this paper.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.466703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1475df43-82da-4f8b-9304-f9a3c3bb1e9e · inbound

SoK: Machine Unlearning for Large Language Models cites this paper.

SoK: Machine Unlearning for Large Language Models The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 121

Resolution: unresolved; no resolver link, observed 2026-08-07T04:59:00.471223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a299b3ba-ca64-428c-a5f5-87a036e037af · inbound

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems cites this paper.

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:36.587266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9689af8-987e-4d55-883f-e9c6b49995e2 · inbound

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning cites this paper.

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T23:59:56.327320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46a2c479-7b49-459a-9d34-26c01c9bd92c · inbound

Computational Approaches to Understanding Large Language Model Impact on Writing and Information Ecosystems cites this paper.

Computational Approaches to Understanding Large Language Model Impact on Writing and Information Ecosystems The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 130

Resolution: unresolved; no resolver link, observed 2026-08-15T19:15:15.263799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 698c6424-b278-4fc8-b9ff-f1a83b345b72 · inbound

Optimising Language Models for Downstream Tasks: A Post-Training Perspective cites this paper.

Optimising Language Models for Downstream Tasks: A Post-Training Perspective The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 133

Resolution: unresolved; no resolver link, observed 2026-08-06T22:44:44.229878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71654ec6-2cf7-433a-b873-6c7e850fe347 · inbound

GeLaCo: An Evolutionary Approach to Layer Compression cites this paper.

GeLaCo: An Evolutionary Approach to Layer Compression The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T17:45:20.814657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4f16710-d197-41d0-9f06-c86237e9b564 · inbound

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models cites this paper.

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-18T05:25:54.623202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f9182871-7f57-4cfb-97eb-88421208f1cb · inbound

Learning to Diagnose and Correct Moral Errors: Beyond Shallow Heuristics in Moral Alignment cites this paper.

Learning to Diagnose and Correct Moral Errors: Beyond Shallow Heuristics in Moral Alignment The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T12:26:06.707114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e86963c9-174d-43c2-a462-f5d69aa54f8f · inbound

Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds cites this paper.

Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:11:02.880386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 00b851cf-e9b1-4399-8a27-25a66ae8d5ac · inbound

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control cites this paper.

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:01:04.089213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bf9702aa-962e-4c46-8bc6-12fe7b4b1018 · inbound

Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation cites this paper.

Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T13:25:45.180208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2220709a-344f-435d-9dd1-56ef77fe2b76 · inbound

Belief or Circuitry? Causal Evidence for In-Context Graph Learning cites this paper.

Belief or Circuitry? Causal Evidence for In-Context Graph Learning The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T08:41:23.937292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c6365ba4-d8ef-4c63-bba5-d703d3a4a2c4 · inbound

Convex Optimization for Alignment and Preference Learning on a Single GPU cites this paper.

Convex Optimization for Alignment and Preference Learning on a Single GPU The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:05:23.032520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 853101b0-42f7-4cb1-b239-3e0c27be9d29 · inbound

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs cites this paper.

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-06-30T16:04:52.574280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c7654052-acc3-4581-85a3-40585353818d · inbound

Prompt Governance? On Governing Technologies Governed by Natural Language cites this paper.

Prompt Governance? On Governing Technologies Governed by Natural Language The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 206

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:25:32.709201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation aba39c14-f94b-4cad-9b46-39bde2893120 · inbound

LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction cites this paper.

LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:34:21.314009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 06c19d1b-72b1-4719-bb25-a11346df64d2 · inbound

Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness Crystallization cites this paper.

Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness Crystallization The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-30T06:44:19.123688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 484d093f-569b-42af-9ef2-4527e87187f0 · inbound

Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization cites this paper.

Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:17:08.606884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 539033ca-0071-45fd-843c-b7b847d3bfde · inbound

Normalized Rewards for Preference Optimization cites this paper.

Normalized Rewards for Preference Optimization The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T10:01:58.330858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce1219f5-b9c5-42ea-a92b-cc9b6c2a17d2 · inbound

Training Skills Like Parameters via Self-Supervised Semantic Diffusion cites this paper.

Training Skills Like Parameters via Self-Supervised Semantic Diffusion The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T05:47:42.153415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.