Paper Citation Record · LEDGER

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning

As of 9 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2607.23394.

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

pith.paper-citation-record.v1
2607.23394 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-30T23:28:39.374084Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

25 of 25 outbound references displayed

verified exact1
verified fuzzy0
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 40a662bf-b9b9-4a3d-ae46-230c68fbbe31 · outbound

This paper cites Subliminal effects in your data: A general mechanism via log-linearity.arXiv preprint arXiv:2602.04863,.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Subliminal effects in your data: A general mechanism via log-linearity.arXiv preprint arXiv:2602.04863,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.270586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99d73c39-da88-49af-bda4-aae84707919a · outbound

This paper cites F Extended Related Work This appendix expands on the related work discussed in Section 2, giving per-reference detail that the main text compresses into citation clusters.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning F Extended Related Work This appendix expands on the related work discussed in Section 2, giving per-reference detail that the main text compresses into citation clusters

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.370114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5a971e3-6720-48fa-a07a-8bf66a695094 · outbound

This paper cites Weird generalization and inductive backdoors: New ways to corrupt LLMs.arXiv preprint arXiv:2512.09742,.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Weird generalization and inductive backdoors: New ways to corrupt LLMs.arXiv preprint arXiv:2512.09742,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.280326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ddcc00c-beba-4eb2-a907-5480828dd1f1 · outbound

This paper cites Federico Bianchi, Mirac Suzgun, Giuseppe Attanasio, Paul R¨ ottger, Dan Jurafsky, Tatsunori Hashimoto, and James Zou.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Federico Bianchi, Mirac Suzgun, Giuseppe Attanasio, Paul R¨ ottger, Dan Jurafsky, Tatsunori Hashimoto, and James Zou

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.284630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf1efbe1-41e8-4cb7-a1c9-41c8b97edbea · outbound

This paper cites James Flemings, Meisam Razaviyayn, and Murali Annavaram.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning James Flemings, Meisam Razaviyayn, and Murali Annavaram

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.293641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b83816-93ec-4c7b-aff3-61853b442d9c · outbound

This paper cites Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daum´ e III, and Kate Crawford.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daum´ e III, and Kate Crawford

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.297970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9103acd-4e18-4397-836f-4bcaf3d3e247 · outbound

This paper cites CharED: Character-wise Ensemble Decoding for Large Language Models.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning CharED: Character-wise Ensemble Decoding for Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.306715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0009b72d-be7b-485f-80c6-7371802ebe9e · outbound

This paper cites M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.311232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e4f79b5-0d2b-4b20-993a-983f86dcd430 · outbound

This paper cites Consensus Sampling for Safer Generative AI.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Consensus Sampling for Safer Generative AI

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.315542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbb4fde2-dc8b-4dae-aeb9-ca22c48f2f61 · outbound

This paper cites The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.328282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b3c2cee-17d0-4942-b4b4-5aba44ca460c · outbound

This paper cites Semantic label smoothing for sequence to sequence problems.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Semantic label smoothing for sequence to sequence problems

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.332376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f5ed6ba-307c-428b-9da2-3a8a46942fbe · outbound

This paper cites Poisoning attacks on LLMs require a near-constant number of poison samples.arXiv preprint arXiv:2510.07192,.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Poisoning attacks on LLMs require a near-constant number of poison samples.arXiv preprint arXiv:2510.07192,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.344727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dad4ce71-68cf-4c83-b0c2-644a829f3cdb · outbound

This paper cites Semantic consensus decoding: Backdoor defense for verilog code generation.arXiv preprint arXiv:2602.04195,.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Semantic consensus decoding: Backdoor defense for verilog code generation.arXiv preprint arXiv:2602.04195,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.353058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ed48157-b4e9-46da-b865-dd81b7fd75b7 · outbound

This paper cites PECAN: A Deterministic Certified Defense Against Backdoor Attacks.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning PECAN: A Deterministic Certified Defense Against Backdoor Attacks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.357218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d3abc7f-cea7-4948-aa25-1ea00011a28e · outbound

This paper cites Nguyen, Yanhao Jia, Meihuizi Jia, Feng Yichao, and Anh Tuan Luu.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Nguyen, Yanhao Jia, Meihuizi Jia, Feng Yichao, and Anh Tuan Luu

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.361809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff484a4c-a556-4161-a0fa-24b6eacd34b8 · outbound

This paper cites 14 A Illustrative Examples: Two Disagreement Policies The following examples isolate the rules’ different responses to disputed mass.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning 14 A Illustrative Examples: Two Disagreement Policies The following examples isolate the rules’ different responses to disputed mass

Reference 23

Resolution: verified exact; doi, observed 2026-07-30T23:30:55.386353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fe76ceb9-1007-404e-a215-1e462f555e24 · outbound

This paper cites These methods assign the models known roles.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning These methods assign the models known roles

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.374084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0edff86b-d0fd-4f43-b954-97d849ed9dd5 · outbound

This paper cites Learning to Decode Collaboratively with Multiple Language Models.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Learning to Decode Collaboratively with Multiple Language Models

Reference 1948

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.340462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e502ea8b-3b7d-4534-8f56-3502437509cc · outbound

This paper cites Mihnea Ghitu and Matthew Wicker.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Mihnea Ghitu and Matthew Wicker

Reference 1986

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.302112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9a58e69-f170-4373-9637-686a56d9c287 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.319846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a04499f1-3eab-45ee-bb9f-9bbb0259f998 · outbound

This paper cites Abhishek Mishra, Mugilan Arulvanan, Reshma Ashok, Polina Petrova, Deepesh Suranjandass, and Donnie Winkelmann.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Abhishek Mishra, Mugilan Arulvanan, Reshma Ashok, Polina Petrova, Deepesh Suranjandass, and Donnie Winkelmann

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.336574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f16eef63-1eca-495d-9cf8-cd172afb7a08 · outbound

This paper cites CleanGen: Mitigating backdoor attacks for generation tasks in large language models.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning CleanGen: Mitigating backdoor attacks for generation tasks in large language models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.324305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 724b73b5-7036-412f-ba9a-4594e92db310 · outbound

This paper cites Steering out-of-distribution generalization with concept ablation fine-tuning.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Steering out-of-distribution generalization with concept ablation fine-tuning

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.289273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e71a4cfe-6c42-4eb0-8fb4-8d8f4227f606 · outbound

This paper cites Certifiably robust RAG against retrieval corruption.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Certifiably robust RAG against retrieval corruption

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.348678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5c74ff8-21ea-43dc-ab00-e4736b340e36 · outbound

This paper cites Semantic Smoothing for Language Models via Distribution Estimation and Embeddings.

Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning Semantic Smoothing for Language Models via Distribution Estimation and Embeddings

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-07-30T23:28:39.275525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.