Paper Citation Record · LEDGER

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models

As of 7 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2607.26173.

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

pith.paper-citation-record.v1
2607.26173 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T00:38:43.394556Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

33 of 33 outbound references displayed

verified exact0
verified fuzzy0
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fc3a5fa0-2556-45cf-88c1-7c0d305867e2 · outbound

This paper cites We give the generation procedure and matched examples here because the differences between conditions are the intervention.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models We give the generation procedure and matched examples here because the differences between conditions are the intervention

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:43.394556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8676757c-90b4-4c7a-87db-da783520e8fa · outbound

This paper cites Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:40.976925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5dec608-6606-45fc-abbd-a41cec86ab9a · outbound

This paper cites Subliminal Learning: Language models transmit behavioral traits via hidden signals in data.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Subliminal Learning: Language models transmit behavioral traits via hidden signals in data

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.279652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a90eaa7-9c55-4b16-91ab-9fb2cfec81ef · outbound

This paper cites Safety Cases: How to Justify the Safety of Advanced AI Systems.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Safety Cases: How to Justify the Safety of Advanced AI Systems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.415734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0f0fc32-df4b-4612-a852-66ed029f73a3 · outbound

This paper cites Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.498112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 762c5185-b624-4412-b4cc-bb2e2e16200c · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.609361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc22e798-f061-4c96-a7f9-41e756a7a177 · outbound

This paper cites Scaling Laws for Autoregressive Generative Modeling.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Scaling Laws for Autoregressive Generative Modeling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.753884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3f585ea-d940-4e3c-9437-5ebcbc66a8e7 · outbound

This paper cites How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.813074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6087d215-cef2-404e-ab66-eb634ae4b5eb · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.892784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44cd6584-eea2-4f5b-917b-3230b8ee86ba · outbound

This paper cites Jonathan Kutasov, Adam Jermyn, Julius Steen, Minh Le, Samuel R.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Jonathan Kutasov, Adam Jermyn, Julius Steen, Minh Le, Samuel R

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.981034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 887ada73-7ec2-4d97-9977-7a02eb1f5c3a · outbound

This paper cites Andrew K.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Andrew K

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.063468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6fba030-3ade-47a3-9180-9bf59c3326ed · outbound

This paper cites Model Spec Midtraining: Improving How Alignment Training Generalizes.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Model Spec Midtraining: Improving How Alignment Training Generalizes

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.144095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 542765ba-91c8-428e-a96c-5644e3497941 · outbound

This paper cites Gradient Episodic Memory for Continual Learning.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Gradient Episodic Memory for Continual Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.229944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2615bce9-87ad-46dd-918d-5f8bcc90e66d · outbound

This paper cites Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey, Jonathan Marcus, Siddharth Mishra- Sharma, Daniel Ziegler, Emmanuel Ameisen, Joshua Batson, Tim Belonax, Samuel R.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey, Jonathan Marcus, Siddharth Mishra- Sharma, Daniel Ziegler, Emmanuel Ameisen, Joshua Batson, Tim Belonax, Samuel R

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.315454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a667ab4-e74f-4a76-a4b8-86779ba62199 · outbound

This paper cites Negation Neglect: When models fail to learn negations in training.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Negation Neglect: When models fail to learn negations in training

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.400547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ff1159c-a17e-46fc-94a8-645f7070bc08 · outbound

This paper cites Tell, don't show: Declarative facts influence how LLMs generalize.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Tell, don't show: Declarative facts influence how LLMs generalize

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.485504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f178cb15-eca4-4a32-8d2d-4c6a0401807b · outbound

This paper cites Training language models to follow instructions with human feedback.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Training language models to follow instructions with human feedback

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.576238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64369c4d-6cc6-430c-9667-54281e2bdc16 · outbound

This paper cites iCaRL: Incremental Classifier and Representation Learning.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models iCaRL: Incremental Classifier and Representation Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.662240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb5ea07f-7d12-4c48-8ca3-f5cd63365fc3 · outbound

This paper cites School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.908101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1885033-e6ae-4ec6-bb3f-25c27ca3ddaf · outbound

This paper cites Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.989353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e32811c-a2da-43b2-b25f-7939b4e2f58e · outbound

This paper cites Model Organisms for Emergent Misalignment.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Model Organisms for Emergent Misalignment

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:43.069300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bb12c35-1561-450b-84e1-65c60c405e43 · outbound

This paper cites Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:43.150846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab22fa55-c124-4552-8831-a7d159b6952d · outbound

This paper cites LIMA: Less Is More for Alignment.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models LIMA: Less Is More for Alignment

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:43.229927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 901e915a-a79d-4f43-9d52-e7f1fcc9008b · outbound

This paper cites GPQA for the capability side, welfare judge scores for the animal- welfare side, and the same Petri Bloom suite described in Appendix H.2 for the self-preservation side.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models GPQA for the capability side, welfare judge scores for the animal- welfare side, and the same Petri Bloom suite described in Appendix H.2 for the self-preservation side

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:43.314831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d5d0e16-9c26-4354-9ca3-5472c066fb8a · outbound

This paper cites Experience Replay for Continual Learning.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Experience Replay for Continual Learning

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.745057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34e4bc95-2d42-4d3c-8011-73700833c500 · outbound

This paper cites From firewalls to frontiers: AI red-teaming is a domain-specific evolution of cyber red-teaming.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models From firewalls to frontiers: AI red-teaming is a domain-specific evolution of cyber red-teaming

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:42.827149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d06789e2-a277-43d9-bd79-ce7a9ea4405e · outbound

This paper cites On-Policy Replay for Continual Supervised Fine-Tuning.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models On-Policy Replay for Continual Supervised Fine-Tuning

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.160077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d03c9a0-9501-4dad-bfbd-9608a5baab41 · outbound

This paper cites Taken out of context: On measuring situational awareness in LLMs.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Taken out of context: On measuring situational awareness in LLMs

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:40.652237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4adfa29e-c0b9-4ec2-b88d-aeeda5cc8705 · outbound

This paper cites BEiT: BERT Pre-Training of Image Transformers.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models BEiT: BERT Pre-Training of Image Transformers

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:40.500688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dd9b9e6-fdb0-456c-b858-37eaf93e7919 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Constitutional AI: Harmlessness from AI Feedback

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:40.343318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4c5bf99-e663-4e71-8425-5902ed995ed8 · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.667721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18de718f-09dc-42c6-98f9-d936ada2e720 · outbound

This paper cites Looking Inward: Language Models Can Learn About Themselves by Introspection.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Looking Inward: Language Models Can Learn About Themselves by Introspection

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:40.804086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69a7d092-57e3-4cd7-b651-c477d8a447be · outbound

This paper cites Scaling Laws for Generative Mixed-Modal Language Models.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Scaling Laws for Generative Mixed-Modal Language Models

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:40.236591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.