Paper Citation Record · LEDGER

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance

As of 17 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2608.08139.

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

pith.paper-citation-record.v1
2608.08139 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:29:50.411022Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

33 of 33 outbound references displayed

verified exact1
verified fuzzy9
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 12711156-0980-4ad3-9b80-99d96efda96d · outbound

This paper cites PhyloLM: Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks , url =.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance PhyloLM: Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks , url =

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:29:50.829977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 11c270e4-854c-4bb9-8184-e8d1ba8ffe99 · outbound

This paper cites International Conference on Learning Representations , volume=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance International Conference on Learning Representations , volume=

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:29:50.818486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2be0de21-e20e-4901-a2a8-84a34b2088ab · outbound

This paper cites International Conference on Learning Representations , volume=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance International Conference on Learning Representations , volume=

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:29:50.807482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a209c394-4bb6-424c-9058-70271d9e757e · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Advances in Neural Information Processing Systems , volume=

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.303907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89fa1def-2f1a-44ac-a5e9-eaf874e961aa · outbound

This paper cites International conference on machine learning , pages=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance International conference on machine learning , pages=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.307735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ae77b63-3ef3-41b2-8d75-1819b8e99144 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.311696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0867a3b9-a937-4ebe-818f-23f9e88b1f96 · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.315595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c57d6c6-245e-423b-84e2-acbfed8c671e · outbound

This paper cites Interpreting.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Interpreting

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:29:50.783229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 551c0cfb-1ca7-48b1-8c80-0ab24adc46b8 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.323208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 725cc3e5-7ead-45ef-bead-e95f52028387 · outbound

This paper cites International Conference on Learning Representations , volume=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance International Conference on Learning Representations , volume=

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:29:50.771962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 48025ecc-0fb6-4272-a2a7-cad62e16f851 · outbound

This paper cites International conference on machine learning , pages=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance International conference on machine learning , pages=

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.330754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24650858-04ed-43fa-91a4-0fd6ac5e63a0 · outbound

This paper cites Qwen2.5 Technical Report.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Qwen2.5 Technical Report

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.334397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83498c0a-c862-4d85-b825-90a19e402ed1 · outbound

This paper cites Qwen3 Technical Report.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Qwen3 Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.338273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91b625f3-b308-47e0-b6ed-1d9d787598f0 · outbound

This paper cites The Llama 3 Herd of Models.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance The Llama 3 Herd of Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.341908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b33954bd-1df3-4589-8f6c-a22d2be26b11 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Gemma 2: Improving Open Language Models at a Practical Size

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.345128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b1d203f-e1e0-432a-8048-1a2201744371 · outbound

This paper cites an unresolved cited work.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:29:50.755470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 928761c2-9212-49e5-b311-271ddef032a4 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.352622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71302a89-f90f-48aa-b433-c7bb8a705670 · outbound

This paper cites Phi-4 Technical Report.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Phi-4 Technical Report

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.356769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37a720de-178d-4eaa-885d-859edda6e10e · outbound

This paper cites an unresolved cited work.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:29:50.744113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 76bbd211-92dc-4c63-87b6-5bb96846c971 · outbound

This paper cites Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classification.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classification

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.365025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43075341-ff8e-479c-882c-aef3763a43aa · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Advances in Neural Information Processing Systems , volume=

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:29:50.732590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 09f77ece-294e-4712-b58d-f1373af1e719 · outbound

This paper cites Detecting Distillation Data from Reasoning Models.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Detecting Distillation Data from Reasoning Models

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-08-12T00:29:50.551962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9a2d08cf-06f5-4f57-a16e-6c3d7a2c54ad · outbound

This paper cites an unresolved cited work.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:29:50.722120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 901354a8-423f-4dc2-88a9-902c6f37eed0 · outbound

This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:29:50.711945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c30f8f44-1b7d-4b41-bca7-d3a13eb00462 · outbound

This paper cites Feder and Lee, Katherine and Jagielski, Matthew and Nasr, Milad and Conmy, Arthur and Wallace, Eric and Rolnick, David and Tram\`.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Feder and Lee, Katherine and Jagielski, Matthew and Nasr, Milad and Conmy, Arthur and Wallace, Eric and Rolnick, David and Tram\`

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:29:50.701887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d8876eb8-bc27-4c5f-afa5-320e2f66d09b · outbound

This paper cites arXiv preprint arXiv:2602.09434 , year=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance arXiv preprint arXiv:2602.09434 , year=

Reference 26

Resolution: verified exact; raw_fallback, observed 2026-08-12T00:29:50.534010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0ee704ac-225f-4f29-afcf-2e57641d0978 · outbound

This paper cites an unresolved cited work.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:29:50.689649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 808077a7-92a4-45dc-8f0c-3d8d0ecb90ff · outbound

This paper cites OpenAI blog , volume=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance OpenAI blog , volume=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.393764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35f11fd0-70a8-4e0b-a83c-52b566213a8d · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance OPT: Open Pre-trained Transformer Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.397109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f0dd71-b2b3-463e-9a5e-a240751bdd97 · outbound

This paper cites 2 OLMo 2 Furious.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance 2 OLMo 2 Furious

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.400922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 454b17be-7946-4a0d-8b32-1848e781c172 · outbound

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

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.404637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f621303-fb15-4733-824b-2d58c76fe784 · outbound

This paper cites Proceedings of BigScience Episode\# 5--Workshop on Challenges & Perspectives in Creating Large Language Models , pages=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Proceedings of BigScience Episode\# 5--Workshop on Challenges & Perspectives in Creating Large Language Models , pages=

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:29:50.671924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a0a16dee-09e8-4237-9d2a-ad972d6c1960 · outbound

This paper cites Findings of the association for computational linguistics: EMNLP 2023 , pages=.

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance Findings of the association for computational linguistics: EMNLP 2023 , pages=

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T00:29:50.411022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.