Pith. sign in

Paper Citation Record · LEDGER

Learning the Signature of Memorization in Autoregressive Language Models

As of 6 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2604.03199.

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

pith.paper-citation-record.v1
2604.03199 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T19:53:10.396785Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

22 of 22 outbound references displayed

  • verified exact15
  • verified fuzzy5
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 71097c6e-cd46-4e68-8128-83900b97c22a · outbound

This paper cites Deep learning with differential privacy.

Learning the Signature of Memorization in Autoregressive Language Models Deep learning with differential privacy

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-05-13T19:53:11.990354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:fead44c9a244457a6dba8cb438f277dcf4e35c33e38a8af89903431e6122ab89

Observation bb76322d-c104-43e8-92a0-591d4375a5e7 · outbound

This paper cites Qwen Technical Report.

Learning the Signature of Memorization in Autoregressive Language Models Qwen Technical Report

Reference 2

Resolution
verified exact
local_arxiv, observed 2026-05-13T19:53:11.457782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:5567740e0452eee089877d009693a16d976e6d0be3aa3e26d0b220cb5aab326c

Observation ff1adcdf-7730-4c02-b1b1-1c0011e20be1 · outbound

This paper cites RecurrentGemma: Moving Past Transformers for Efficient Open Language Models.

Learning the Signature of Memorization in Autoregressive Language Models RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

Reference 3

Resolution
metadata mismatch
arxiv_id, observed 2026-05-13T19:53:11.460881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:1cf4c7aa701dc391272212ccf1003c70d391b8e5473486dc95e9cbd0363d6cdf

Observation 615c0538-ea5e-4b8e-8dfa-d21b2536ed8e · outbound

This paper cites Membership inference attacks from first principles.

Learning the Signature of Memorization in Autoregressive Language Models Membership inference attacks from first principles

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-05-13T19:53:11.988024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:9cf3df0fe7320054402726337e049578743b1eab06eac911d065594fadc3c958

Observation a2219091-bada-401b-b396-bbd2032c0d77 · outbound

This paper cites Window-based membership inference attacks against fine-tuned large language models.

Learning the Signature of Memorization in Autoregressive Language Models Window-based membership inference attacks against fine-tuned large language models

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-05-13T19:53:11.463853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:8eb4d05d376009c2362f4af834c0f286f6c832ecac2513d3062616db2dd6a13f

Observation 3030597b-90d3-49d4-b542-8bcf4d65b7e0 · outbound

This paper cites Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster.

Learning the Signature of Memorization in Autoregressive Language Models Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster

Reference 6

Resolution
metadata mismatch
arxiv_id, observed 2026-05-13T19:53:11.472570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:cb36d01c43fff8259f2b14e684096fa502c2f245ae7511bf094bf293a3bf8dc5

Observation 5707179e-171e-4abf-b374-8dc48447e387 · outbound

This paper cites Do Membership Inference Attacks Work on Large Language Models?.

Learning the Signature of Memorization in Autoregressive Language Models Do Membership Inference Attacks Work on Large Language Models?

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-05-13T19:53:11.488922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:49fd424a5698259b858c3c0c4d4276c093278f1d7c5ff5e682dcc215f8687967

Observation 3ca9c5d3-7b1e-45f0-a0ad-fd487426efcd · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Learning the Signature of Memorization in Autoregressive Language Models Gemma: Open Models Based on Gemini Research and Technology

Reference 8

Resolution
verified exact
local_arxiv, observed 2026-05-13T19:53:11.469482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:f00cb6d4a84256261e98398dfc77f2cc297ce585b7e905aede30ef8104c6a233

Observation b3acad32-6f7e-4bfa-8f58-5aa2f39dc8e7 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Learning the Signature of Memorization in Autoregressive Language Models Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 9

Resolution
verified exact
local_arxiv, observed 2026-05-13T19:53:11.505734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:9bca440a75343be1b72bd0058bdc5b875df19ea1203a63519ea3c9e44441b9f2

Observation e540784e-32ee-4109-8732-7b1df5be7304 · outbound

This paper cites Powerful Training-Free Membership Inference Against Autoregressive Language Models.

Learning the Signature of Memorization in Autoregressive Language Models Powerful Training-Free Membership Inference Against Autoregressive Language Models

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-05-13T19:53:11.503252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:9a6d71195357146ee9e3fb6776e9ac64f7f40b3d6a8253e8f21719478fa27297

Observation 81ffa46e-b802-4912-bb22-810abd055fb0 · outbound

This paper cites Membership inference attacks against language models via neigh- bourhood comparison.

Learning the Signature of Memorization in Autoregressive Language Models Membership inference attacks against language models via neigh- bourhood comparison

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-05-13T19:53:11.996967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:6e70715c5816b9b4a2976da0c35a223fd9af40939941ac8112e0b3b906187c20

Observation c7f2d055-7286-45b0-98f8-5497bab5e5fd · outbound

This paper cites Pointer Sentinel Mixture Models.

Learning the Signature of Memorization in Autoregressive Language Models Pointer Sentinel Mixture Models

Reference 12

Resolution
verified exact
local_arxiv, observed 2026-05-13T19:53:11.480752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:dc1c6b9f4a247556064c60c96fbf9cd3b477beadcc23d221284319ca61453a44

Observation 1bdc74ed-7cc6-4323-a1c8-0a8ff364f69a · outbound

This paper cites News Category Dataset.

Learning the Signature of Memorization in Autoregressive Language Models News Category Dataset

Reference 13

Resolution
verified exact
arxiv_id, observed 2026-05-13T19:53:11.475329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:efc9fbc362fc2e3aefd5d4baafa845e4a57c702ea59cfe63c3c3a23a7b27100f

Observation c11c878c-d4f5-412d-af88-179eb203a0b2 · outbound

This paper cites Don’t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization.

Learning the Signature of Memorization in Autoregressive Language Models Don’t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-05-13T19:53:11.992672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:00db46664be4afb2a6ff8ec3a06b3888739112358805729205ca8826041f14fd

Observation 87c9fc22-7149-4a0f-90b9-b5a3f35097b2 · outbound

This paper cites The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only.

Learning the Signature of Memorization in Autoregressive Language Models The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-05-13T20:43:45.999902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:ca50147621ae9fd510804811bc1ffd0f278842f915d7c10e90eec50837c4a1ea

Observation 978c21b7-fbc5-482d-9a29-50cd64b4af70 · outbound

This paper cites RWKV: Reinventing RNNs for the transformer era.

Learning the Signature of Memorization in Autoregressive Language Models RWKV: Reinventing RNNs for the transformer era

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-05-13T19:53:11.994852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:947f680dce773f34bfa402730fb966c8729685ef7dc2765c99fcd6499e237219

Observation c181ec07-3a77-48f4-8bbe-e4e1709fbbfa · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Learning the Signature of Memorization in Autoregressive Language Models Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 17

Resolution
verified exact
local_arxiv, observed 2026-05-13T19:53:11.486197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:9e7ba5dfa01c0fb7e5278477b3ac0957922dcd5790ce56fb09d44c04527dfc9f

Observation 2e54abf3-93d9-416e-bb5b-ef76d5a5afa4 · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

Learning the Signature of Memorization in Autoregressive Language Models DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 18

Resolution
verified exact
local_arxiv, observed 2026-05-13T19:53:11.499708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:653a5dd865167ee2c7b8366c5f373a6b56a82e68f724a642abb100694ed088cb

Observation e5f13f10-6cd0-45a1-af2d-621e6b817598 · outbound

This paper cites Detecting Pretraining Data from Large Language Models.

Learning the Signature of Memorization in Autoregressive Language Models Detecting Pretraining Data from Large Language Models

Reference 19

Resolution
verified exact
arxiv_id, observed 2026-05-17T18:07:25.061786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:e9a06e3343cd9f29fd8ec4d908497f5c6e2d19437e1d0224e000e8e1f4af99d6

Observation a7adb287-207d-4551-b810-bc240ae08fef · outbound

This paper cites Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models.

Learning the Signature of Memorization in Autoregressive Language Models Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models

Reference 20

Resolution
verified exact
arxiv_id, observed 2026-05-13T19:53:11.478145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:1f33e07e108bd6571449bcce62c03e54854e8f4ee8e61c81ba8265368206effc

Observation 9d7ae684-5f37-4491-aed8-86d02d731f0e · outbound

This paper cites Table 4: Full results on held-out transformers: AUC.

Learning the Signature of Memorization in Autoregressive Language Models Table 4: Full results on held-out transformers: AUC

Reference 21

Resolution
verified exact
arxiv_id, observed 2026-05-13T19:53:11.466678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:c4f19b69433f3a98f7ad5db54c6a026f6f99c4713f45a644b57f8e36f87c44ce

Observation d30daedb-cb05-4dc2-87bd-d58276eacdc6 · outbound

This paper cites D Classifier Architecture Ablation Table 11 presents full results for the classifier architecture comparison.

Learning the Signature of Memorization in Autoregressive Language Models D Classifier Architecture Ablation Table 11 presents full results for the classifier architecture comparison

Reference 22

Resolution
verified exact
arxiv_id, observed 2026-05-13T19:53:11.483651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-05-13T19:53:10.396785Z digest=sha256:f2bce6ca9876b3abb7f236a1432eaa9241f3c32f70514f4f57c43b3feb2c4452

Pith citing papers

No inbound Pith citation observations are available.