Paper Citation Record · LEDGER

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning

As of 10 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2607.08393.

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

pith.paper-citation-record.v1
2607.08393 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-10T08:11:11.566370Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

36 of 36 outbound references displayed

verified exact3
verified fuzzy25
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch6

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 41d3cf17-19a8-4434-ab71-04c903c78707 · outbound

This paper cites an unresolved cited work.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-07-10T08:16:59.362636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fff37db9-4bde-4924-88be-5b4230fb18f3 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.366561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0922f8d9-5744-454f-afbe-ab9f58d7ae37 · outbound

This paper cites Physics of language models: Part 3.3, knowledge capacity scaling laws.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Physics of language models: Part 3.3, knowledge capacity scaling laws

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.375760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3b9f4fc1-9cbc-4588-98ed-a333de0a1669 · outbound

This paper cites Cocarascu, F.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Cocarascu, F

Reference 4

Resolution: malformed identifier; doi_truncated, observed 2026-07-10T08:16:58.534665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c0dbd0c1-0629-49b8-95a9-619bfa9dd793 · outbound

This paper cites a is b” fail to learn “b is a.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning a is b” fail to learn “b is a

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.351180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4c7aabc0-32fe-47af-9944-ee28fcff9154 · outbound

This paper cites Hopping too late: Exploring the limitations of large language models on multi-hop queries.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Hopping too late: Exploring the limitations of large language models on multi-hop queries

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.368429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cf46e937-ead8-4d10-9590-cbcc9e7aff1e · outbound

This paper cites Evaluating the ripple effects of knowledge editing in language models.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Evaluating the ripple effects of knowledge editing in language models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.379209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8e1868b6-e4c8-42c2-9af0-9bdc298fa66c · outbound

This paper cites doi: 10.18653/v1/2022.acl-long.581.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning doi: 10.18653/v1/2022.acl-long.581

Reference 8

Resolution: metadata mismatch; doi, observed 2026-07-10T08:16:58.521192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 35980cfc-7680-44dd-ba60-3c823b59802e · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Scaling and evaluating sparse autoencoders

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.372094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ff7a7c0f-2342-4446-8fce-b5f3a6304966 · outbound

This paper cites Key-value memory in the brain.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Key-value memory in the brain

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T08:16:58.541359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 321608e5-9b84-4e40-a544-2ab2565c6454 · outbound

This paper cites Dissecting recall of factual associations in auto-regressive language models.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Dissecting recall of factual associations in auto-regressive language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.393521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6e67a8b4-9c0e-47aa-90f1-425f48988141 · outbound

This paper cites Patchscopes: A unifying framework for inspecting hidden representations of language models.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Patchscopes: A unifying framework for inspecting hidden representations of language models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.395388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1862aa5d-2902-49b2-9a8e-538a223591c3 · outbound

This paper cites Model editing at scale leads to gradual and catastrophic forgetting.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Model editing at scale leads to gradual and catastrophic forgetting

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.391591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0bfee5fe-cf15-43da-bac3-f45fda8aaeeb · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Sparse autoencoders find highly interpretable features in language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.389609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e8b1ce0f-bdfb-4212-90e2-029a15c5bc11 · outbound

This paper cites Where to find grokking in llm pretraining? monitor memorization-to-generalization without test.arXiv preprint arXiv:2506.21551, 2025k.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Where to find grokking in llm pretraining? monitor memorization-to-generalization without test.arXiv preprint arXiv:2506.21551, 2025k

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-10T08:16:58.525175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 19395955-3524-4b73-953a-373ff4516a65 · outbound

This paper cites Michaud, Max Tegmark, and Mike Williams.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Michaud, Max Tegmark, and Mike Williams

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.397085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 23dc7490-8bd7-4e9c-a2ec-1fa6198d392e · outbound

This paper cites Mass-editing memory in a transformer.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Mass-editing memory in a transformer

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.387522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c19347d2-f0ff-43d8-878a-eb1f3bf34b6d · outbound

This paper cites Locating and editing factual associations in GPT.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Locating and editing factual associations in GPT

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.383143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 996e8311-1e2e-4906-bc61-b1a41a5ca82e · outbound

This paper cites How much do language models memorize?.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning How much do language models memorize?

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T08:16:58.784744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation de209e04-5640-4cdb-9367-bb3ce7211807 · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Progress measures for grokking via mechanistic interpretability

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.385015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ffa22f44-a852-4937-bbef-d94487c349c6 · outbound

This paper cites interpreting GPT : the logit lens, August 2020.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning interpreting GPT : the logit lens, August 2020

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.398759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0986e177-7118-4831-addd-39a99b2d85c6 · outbound

This paper cites In-context Learning and Induction Heads.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning In-context Learning and Induction Heads

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T08:16:58.532280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7975282f-011f-40af-91ba-f1f09a2aa38c · outbound

This paper cites Fine-tuning or retrieval? comparing knowledge injection in llms.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Fine-tuning or retrieval? comparing knowledge injection in llms

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.381236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8f6d7fd8-3025-484e-bc32-c7128b553e60 · outbound

This paper cites Burbi, A.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Burbi, A

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-07-10T08:16:58.538181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 39597c06-0e70-4d01-9d07-b368ea8226fa · outbound

This paper cites The linear representation hypothesis and the geometry of large language models.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning The linear representation hypothesis and the geometry of large language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.370107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 83343dee-8a08-4884-bf0a-d32f54f852fd · outbound

This paper cites Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-07-10T08:16:58.779339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16beef6b-5832-4a96-9f52-d4534bf35362 · outbound

This paper cites Fine-tuning enhances existing mechanisms: A case study on entity tracking.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Fine-tuning enhances existing mechanisms: A case study on entity tracking

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.374083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 411fbf06-46bd-433e-b510-574d87d26c55 · outbound

This paper cites Fine tuning vs.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Fine tuning vs

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.377339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fd9aeb94-0d09-4060-aa1e-3312f206b030 · outbound

This paper cites Grokking of implicit reasoning in transformers: A mechanistic journey to the edge of generalization.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Grokking of implicit reasoning in transformers: A mechanistic journey to the edge of generalization

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.360841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b08b8d1d-48da-4d85-be31-711c1973ec25 · outbound

This paper cites Interpretability in the wild: a circuit for indirect object identification in GPT-2 small.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Interpretability in the wild: a circuit for indirect object identification in GPT-2 small

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.364504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 592092ef-e7b6-4bbb-aeba-64c1e2568c39 · outbound

This paper cites doi: 10.18653/v1/2024.acl-long.820.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning doi: 10.18653/v1/2024.acl-long.820

Reference 31

Resolution: metadata mismatch; doi, observed 2026-07-10T08:16:58.528926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 338ffd4c-10eb-4fd2-9082-5d73c3db0274 · outbound

This paper cites Ioannidis, Karthik Subbian, James Y.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Ioannidis, Karthik Subbian, James Y

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.356928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 00a225be-897a-462d-baaf-9213f07ba4d2 · outbound

This paper cites Knowledge circuits in pretrained transformers.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Knowledge circuits in pretrained transformers

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.358871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d0ccca99-2165-4800-9a68-a6c009df59fb · outbound

This paper cites Cake: Circuit-aware editing enables generalizable knowledge learners.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Cake: Circuit-aware editing enables generalizable knowledge learners

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-07-10T08:16:58.782324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5fc7136f-9f42-45b7-bc50-037e2d72611d · outbound

This paper cites Towards best practices of activation patching in language models: Metrics and methods.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Towards best practices of activation patching in language models: Metrics and methods

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.353133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4169bc55-a310-4e20-9b64-9bfca67edadb · outbound

This paper cites Mquake: Assessing knowledge editing in language models via multi-hop questions.

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Mquake: Assessing knowledge editing in language models via multi-hop questions

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T08:16:59.354999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

No inbound Pith citation observations are available.