Paper Citation Record · LEDGER

MemSFT: Mitigating Alignment Tax with an External Parametric Memory

As of 9 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2607.25614.

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

pith.paper-citation-record.v1
2607.25614 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T01:59:49.861333Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

31 of 31 outbound references displayed

verified exact0
verified fuzzy0
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fb559bd6-d0b6-4d0b-8e77-37b2c71a7494 · outbound

This paper cites Nested learning: The illusion of deep learning architectures.arXiv preprint arXiv:2512.24695,.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Nested learning: The illusion of deep learning architectures.arXiv preprint arXiv:2512.24695,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.766270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7c4a55f-1261-4334-80a6-f5a39c1e5400 · outbound

This paper cites an unresolved cited work.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.861333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fd6c1c4-b4ab-4062-a880-e5da167fda06 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory On the Opportunities and Risks of Foundation Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.781202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fba827b-e92a-412a-a116-be7990f3b112 · outbound

This paper cites Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.791419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f12b3f4-e261-4586-acc1-487b1f97f3e1 · outbound

This paper cites Lawbench: Benchmarking legal knowledge of large language models.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Lawbench: Benchmarking legal knowledge of large language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.797566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 172d9212-d55a-4924-88f9-56f814482fd8 · outbound

This paper cites an unresolved cited work.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.800561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0ab5222-c315-4c54-a4f9-91210d12a5c7 · outbound

This paper cites Biology-instructions: A dataset and benchmark for multi-omics sequence understanding capability of large language models.arXiv preprint arXiv:2412.19191,.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Biology-instructions: A dataset and benchmark for multi-omics sequence understanding capability of large language models.arXiv preprint arXiv:2412.19191,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.803728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a4cc0e8-e02f-45d7-8bee-36ab3aa6fa80 · outbound

This paper cites Scaling Laws for Forgetting When Fine-Tuning Large Language Models.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Scaling Laws for Forgetting When Fine-Tuning Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.806815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 644d2c2a-aa12-4b6b-87a3-66500040f953 · outbound

This paper cites Generalization through Memorization: Nearest Neighbor Language Models.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Generalization through Memorization: Nearest Neighbor Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.810007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 078f9086-7e4f-4ea8-a15f-8672ce0f2f59 · outbound

This paper cites Revisiting catastrophic forgetting in large language model tuning.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Revisiting catastrophic forgetting in large language model tuning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.813332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dc97909-ec0a-4c1c-9af4-9cc36405d763 · outbound

This paper cites Let’s verify step by step.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Let’s verify step by step

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.816334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b1ea18c-7af5-4050-8932-3c84e8fec64c · outbound

This paper cites More than catastrophic forgetting: Integrating general capabilities for domain-specific llms.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory More than catastrophic forgetting: Integrating general capabilities for domain-specific llms

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.819376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38b08e56-fabf-47e1-b2dd-1d2cad791960 · outbound

This paper cites Openswi: a massive-scale benchmark dataset for surface wave dispersion curve inversion.Earth System Science Data Discussions, 2025:1–37,.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Openswi: a massive-scale benchmark dataset for surface wave dispersion curve inversion.Earth System Science Data Discussions, 2025:1–37,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.822157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2034f67-ce03-4c4a-be68-73b852813996 · outbound

This paper cites K-adapter: Infusing knowledge into pre-trained models with adapters.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory K-adapter: Infusing knowledge into pre-trained models with adapters

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.831062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fb349ae-8d2e-43c3-9eb7-63d15d154403 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Finetuned Language Models Are Zero-Shot Learners

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.833794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df9d31c1-994e-48a6-85b2-5cb092d4baed · outbound

This paper cites Memorizing Transformers.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Memorizing Transformers

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.839575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8cc3a37-d8c6-4d53-8da7-9208ab44cc40 · outbound

This paper cites Qwen3 Technical Report.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Qwen3 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.842509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bf876c6-f133-4777-9c85-42e6014413b5 · outbound

This paper cites $\text{Memory}^3$: Language Modeling with Explicit Memory.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory $\text{Memory}^3$: Language Modeling with Explicit Memory

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.845780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c35b4678-2a49-4c23-a705-72a5b783ad2e · outbound

This paper cites LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.848706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 302dfb7d-0802-49cc-897f-9237fdd5ed42 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Instruction-Following Evaluation for Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.852324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e835b8c-ccd5-41f1-b29d-9fd9c7925c3f · outbound

This paper cites 2-10 trigger_word_extraction.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory 2-10 trigger_word_extraction

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.855248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12c767ba-d2ba-4282-8ce3-8b47011f72d7 · outbound

This paper cites an unresolved cited work.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Unresolved cited work

Reference 128

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.858569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91ec4bc2-563a-4a3c-88ff-fa7a573dc0ab · outbound

This paper cites In- clude: Evaluating multilingual language understanding with regional knowledge.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory In- clude: Evaluating multilingual language understanding with regional knowledge

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.828263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cad2ed6-b857-4284-aee9-8f1b4fb670f1 · outbound

This paper cites Compressive Transformers for Long-Range Sequence Modelling.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Compressive Transformers for Long-Range Sequence Modelling

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.824935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9c2fd53-3dc8-4f36-93bc-8a52f7067c9a · outbound

This paper cites OpenCompass: A Universal Evaluation Platform for Large Language Models.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory OpenCompass: A Universal Evaluation Platform for Large Language Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.787962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e79e74aa-a955-4716-bc66-d1e25c7eb940 · outbound

This paper cites Mlp mem- ory: A retriever-pretrained memory for large language models.arXiv preprint arXiv:2508.01832,.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Mlp mem- ory: A retriever-pretrained memory for large language models.arXiv preprint arXiv:2508.01832,

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.836797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 746c02d1-d3e0-4969-8468-cc27a48cadca · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.784689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66302a0f-e1f9-48af-8a1f-3809a69c10bb · outbound

This paper cites Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.794527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef603cd2-3f3e-472d-9311-0db57add52cf · outbound

This paper cites LoRA Learns Less and Forgets Less.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory LoRA Learns Less and Forgets Less

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.777615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 434605c4-975c-4aee-81f8-030c3887a850 · outbound

This paper cites Memory Layers at Scale.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Memory Layers at Scale

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.773747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d4e5623-24ae-43bf-86ce-3f5d50e05e2b · outbound

This paper cites Llama-nemotron: Efficient reasoning models.

MemSFT: Mitigating Alignment Tax with an External Parametric Memory Llama-nemotron: Efficient reasoning models

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T01:59:49.770279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.