Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-16T00:35:15.004333Z
Paper Citation Record · LEDGER
Orientation, not magnitude: the causal structure of task-vector interference in merged language models
As of 18 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2608.11797.
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 2026-08-18T06:34:40.430872+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
13 of 13 outbound references displayed
- verified exact2
- verified fuzzy0
- unresolved10
- parse uncertain0
- malformed identifier1
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 03413ae4-05e4-47dd-a6bf-c515215633e0 · outbound
This paper cites Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-08-16T00:35:15.269180Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation b10ec944-91d5-4a82-a489-8ed759f10874 · outbound
This paper cites Task Singular Vectors: Reducing Task Interference in Model Merging.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models Task Singular Vectors: Reducing Task Interference in Model Merging
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T00:35:14.967167Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f6232d59-162d-4c70-badd-cfb95fb06d8c · outbound
This paper cites Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T00:35:14.984397Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3484d36e-d36e-4cee-bffa-515a895e1059 · outbound
This paper cites SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T00:35:14.992113Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d5aa07fa-24d0-4919-84e5-aae902cc87ac · outbound
This paper cites Zhanpeng Zhou, Zijun Chen, Yilan Chen, Bo Zhang, and Junchi Yan.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models Zhanpeng Zhou, Zijun Chen, Yilan Chen, Bo Zhang, and Junchi Yan
Reference 11
- Resolution
- verified exact
- raw_fallback, observed 2026-08-16T00:35:15.106059Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation aa448aa2-8fbb-42b1-bfb3-d3a977cd18e5 · outbound
This paper cites On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T00:35:15.000254Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 030e9d64-696d-4fbc-b4de-f1516016d142 · outbound
This paper cites stable reversal.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models stable reversal
Reference 13
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-16T00:35:15.281387Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 59d38153-d60c-4634-9da1-ca5cdfbbd642 · outbound
This paper cites The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
Reference 2012
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T00:35:14.988283Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5899902e-bc0b-4015-ad23-17101c5be4ce · outbound
This paper cites To See a World in a Spark of Neuron: Disentangling Multi-task Interference for Training-free Model Merging.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models To See a World in a Spark of Neuron: Disentangling Multi-task Interference for Training-free Model Merging
Reference 2021
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T00:35:14.962572Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 86642dfe-8e5c-417f-a708-d95cbcb5edf8 · outbound
This paper cites PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T00:35:14.975581Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0e4e2153-09e1-4da9-9388-e36accb6bb11 · outbound
This paper cites Activated Parameter Locating via Causal Intervention for Model Merging.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models Activated Parameter Locating via Causal Intervention for Model Merging
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T00:35:14.980490Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 33fd9001-f021-4751-9538-fce6840eddf3 · outbound
This paper cites Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T00:35:14.958333Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7c63f496-3e66-40c4-a956-1714e632361b · outbound
This paper cites Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi.
Orientation, not magnitude: the causal structure of task-vector interference in merged language models Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi
Reference 2026
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T00:35:14.971710Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.