Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-07T18:42:41.778771Z
Paper Citation Record · LEDGER
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning
As of 20 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2607.05300.
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 2026-08-20T06:33:59.587034+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
12 of 12 outbound references displayed
- verified exact4
- verified fuzzy6
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation a5380fee-bb6d-4980-8fe7-f818c50df5db · outbound
This paper cites Ainsworth, Jonathan Hayase, and Siddhartha Srinivasa.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Ainsworth, Jonathan Hayase, and Siddhartha Srinivasa
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T18:44:06.155940Z
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 97e9eb81-0733-447a-af4c-f4c312431f36 · outbound
This paper cites Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T18:44:06.116958Z
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 c151dac2-b9c7-4321-af7b-0e02ae39675d · outbound
This paper cites Text-to-LoRA: Instant Transformer Adaption.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Text-to-LoRA: Instant Transformer Adaption
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-07T18:44:06.126221Z
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 2f8bb66f-f356-4a1d-8c8c-4ab33ea2f5e0 · outbound
This paper cites Colluding lora: A compositional vulnerability in llm safety alignment.arXiv preprint arXiv:2603.12681, 2026.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Colluding lora: A compositional vulnerability in llm safety alignment.arXiv preprint arXiv:2603.12681, 2026
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-07-07T18:44:06.100966Z
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 6e61ee56-16c6-4966-8f94-b32ddc5ab07c · outbound
This paper cites Lorahub: Efficient cross-task generalization via dynamic lora composition.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Lorahub: Efficient cross-task generalization via dynamic lora composition
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T18:44:06.143848Z
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 85ae2151-82e5-446e-a9b1-cde13ac8a5fa · outbound
This paper cites Eigenlorax: Recyclingadapters to findprincipalsubspacesforresource-efficientadaptationandinference.arXiv preprint arXiv:2502.04700, 2025.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Eigenlorax: Recyclingadapters to findprincipalsubspacesforresource-efficientadaptationandinference.arXiv preprint arXiv:2502.04700, 2025
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-07-07T18:44:06.112823Z
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 2c128321-9f51-4e83-aece-8f56f0e6371c · outbound
This paper cites Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-07T18:44:06.107673Z
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 bf07104b-9fe9-47e4-aae0-75240c87a341 · outbound
This paper cites Fine- tuning aligned language models compromises safety, even when users do not intend to! InInternational Conference on Learning Representations, 2024.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Fine- tuning aligned language models compromises safety, even when users do not intend to! InInternational Conference on Learning Representations, 2024
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T18:44:06.152817Z
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 2d7f9456-ab32-4708-a5c9-f81a5b20477c · outbound
This paper cites A Study of Backdoors in Instruction Fine-tuned Language Models.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning A Study of Backdoors in Instruction Fine-tuned Language Models
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T18:44:06.121630Z
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 aaf221c9-ed95-499d-a384-74cab0f47f5d · outbound
This paper cites Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, and Raia Hadsell.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, and Raia Hadsell
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T18:44:06.146638Z
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 bb1d5b00-685a-4762-b1ca-af94b940a25c · outbound
This paper cites Model zoos: A dataset of diverse populations of neural network models.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Model zoos: A dataset of diverse populations of neural network models
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T18:44:06.149832Z
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 c6b9b45f-3237-4eca-99b3-7993e09f54ad · outbound
This paper cites Poisoninglanguagemodelsduringinstruction tuning.
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning Poisoninglanguagemodelsduringinstruction tuning
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T18:44:06.141127Z
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.
Pith citing papers
No inbound Pith citation observations are available.