Paper Citation Record · LEDGER

Next-token pretraining implies in-context learning

As of 8 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 4 inbound Pith citation observations for arXiv:2505.18373.

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

pith.paper-citation-record.v1
2505.18373 v2

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:39:14.475409Z

measured 36 of 36 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:48:04.570803Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-03T20:38:55.894248Z

Reference resolution

32 of 32 outbound references displayed

verified exact2
verified fuzzy13
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 23ae4b3f-7573-43f4-9194-b2a19cb84ae8 · outbound

This paper cites Language models are unsupervised multitask learners.

Next-token pretraining implies in-context learning Language models are unsupervised multitask learners

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:39:10.522624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba9a3316-9c80-450b-a6d0-83c35c5623aa · outbound

This paper cites Language models are few-shot learners.

Next-token pretraining implies in-context learning Language models are few-shot learners

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:39:10.659096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9d83373-353a-458a-9940-3d3bcfddc0bd · outbound

This paper cites Sparks of Artificial General Intelligence: Early experiments with GPT-4.

Next-token pretraining implies in-context learning Sparks of Artificial General Intelligence: Early experiments with GPT-4

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:39:10.779063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c507153a-c542-4234-ac4e-f98ee1bd41c2 · outbound

This paper cites An explanation of in-context learning as implicit Bayesian inference.

Next-token pretraining implies in-context learning An explanation of in-context learning as implicit Bayesian inference

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:19.577650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fbc26298-df18-4ff3-b6dd-cae2b8c3e7ad · outbound

This paper cites Bayesian scaling laws for in-context learning.

Next-token pretraining implies in-context learning Bayesian scaling laws for in-context learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:39:11.096101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a26ff039-52aa-4efb-9412-1b4c3e7297ce · outbound

This paper cites Transformers learn in-context by gradient descent.

Next-token pretraining implies in-context learning Transformers learn in-context by gradient descent

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:19.353203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 028fc5f7-63e8-4405-855a-2e1e1add81a0 · outbound

This paper cites Transformers learn to implement preconditioned gradient descent for in-context learning.

Next-token pretraining implies in-context learning Transformers learn to implement preconditioned gradient descent for in-context learning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:19.124364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5d07d308-4d84-4c26-a5f0-a56514518e23 · outbound

This paper cites The broader spectrum of in-context learning.

Next-token pretraining implies in-context learning The broader spectrum of in-context learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:39:11.525634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c10f9de-1942-4986-aa0e-002c0df277b7 · outbound

This paper cites Transformers represent belief state geometry in their residual stream.

Next-token pretraining implies in-context learning Transformers represent belief state geometry in their residual stream

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:18.880580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 94e3ab11-b2b9-4ac3-90d2-d155b3a412d3 · outbound

This paper cites Constrained belief updates explain geometric structures in transformer representations.

Next-token pretraining implies in-context learning Constrained belief updates explain geometric structures in transformer representations

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:18.624548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f9a097d9-0a92-4919-a464-b9ddca1120c1 · outbound

This paper cites RNNs represent belief state geometry in their hidden states.

Next-token pretraining implies in-context learning RNNs represent belief state geometry in their hidden states

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:18.434866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation eebf4abf-4b44-4e28-b6ed-320a478b4e62 · outbound

This paper cites an unresolved cited work.

Next-token pretraining implies in-context learning Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:39:18.181859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 67abdc84-aad6-4dbc-8d3b-1aa29589e4c6 · outbound

This paper cites A mathematical framework for transformer circuits.

Next-token pretraining implies in-context learning A mathematical framework for transformer circuits

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:39:12.219137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79ede063-cb47-4393-91b7-5192c1752cc5 · outbound

This paper cites In-context learning and induction heads.

Next-token pretraining implies in-context learning In-context learning and induction heads

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:17.925148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4c187814-8b65-4432-a3c0-0ded963ec18e · outbound

This paper cites an unresolved cited work.

Next-token pretraining implies in-context learning Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:39:17.687571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 98b9499e-0972-488e-a67c-74c62ef303bd · outbound

This paper cites an unresolved cited work.

Next-token pretraining implies in-context learning Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:39:17.461471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 44bccc95-5339-4f4c-8909-79aaabaac208 · outbound

This paper cites an unresolved cited work.

Next-token pretraining implies in-context learning Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:39:17.270392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 00ef0ebd-df95-42aa-a817-2c2852e8e144 · outbound

This paper cites an unresolved cited work.

Next-token pretraining implies in-context learning Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:39:17.033210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c18aefdb-5d3e-4161-9e6f-9eaca7ef037e · outbound

This paper cites an unresolved cited work.

Next-token pretraining implies in-context learning Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:39:16.846055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 71ed24ca-59f9-4d66-9227-bf3f509cb586 · outbound

This paper cites Shannon entropy rate of hidden markov processes.

Next-token pretraining implies in-context learning Shannon entropy rate of hidden markov processes

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:16.623887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ce99a68f-39ac-40c2-a131-2b9680199ca9 · outbound

This paper cites Critical behavior in physics and probabilistic formal languages.

Next-token pretraining implies in-context learning Critical behavior in physics and probabilistic formal languages

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:16.438303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3e6274c1-974a-41bc-a5cc-dd49782f8ca3 · outbound

This paper cites Signatures of Infinity: Nonergodicity and Resource Scaling in Prediction, Complexity, and Learning.

Next-token pretraining implies in-context learning Signatures of Infinity: Nonergodicity and Resource Scaling in Prediction, Complexity, and Learning

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:39:15.006118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation faca23d7-3995-42b3-83ed-3e9d6087a9e3 · outbound

This paper cites Language models model us.

Next-token pretraining implies in-context learning Language models model us

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:16.289298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c6d3af4b-f423-487c-9ed5-275f884cd1fe · outbound

This paper cites Predictability, complexity, and learning.

Next-token pretraining implies in-context learning Predictability, complexity, and learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:16.060360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 17d4ec45-227b-4e82-b4db-11e613628f6c · outbound

This paper cites Scaling Laws for Neural Language Models.

Next-token pretraining implies in-context learning Scaling Laws for Neural Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:39:13.843128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75612168-e09b-498c-9425-9c5decff3d6c · outbound

This paper cites Meta-learning of Sequential Strategies.

Next-token pretraining implies in-context learning Meta-learning of Sequential Strategies

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:39:13.913343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a8004f4-9cca-4b52-8a91-942848a9d1ce · outbound

This paper cites Data distributional properties drive emer- gent in-context learning in transformers.

Next-token pretraining implies in-context learning Data distributional properties drive emer- gent in-context learning in transformers

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:15.838207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9d842ca5-de7e-4687-af69-6d32106a1f45 · outbound

This paper cites Predictive Information.

Next-token pretraining implies in-context learning Predictive Information

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:39:14.717646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3d6be4e3-f7d6-441b-8e7d-3783d4740593 · outbound

This paper cites an unresolved cited work.

Next-token pretraining implies in-context learning Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:39:15.636570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation edfaebd0-8a9c-4ee6-b832-e898203a04a5 · outbound

This paper cites Grassberger.

Next-token pretraining implies in-context learning Grassberger

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:39:15.447962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 246e4b65-000e-4f5b-ac02-5b18fac886bc · outbound

This paper cites Attention Is All You Need.

Next-token pretraining implies in-context learning Attention Is All You Need

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:39:14.475409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc8af376-9683-4c47-aaeb-21e9d0e95bf8 · outbound

This paper cites an unresolved cited work.

Next-token pretraining implies in-context learning Unresolved cited work

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T14:39:12.353085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 0dd0ea06-82f7-4f61-83ad-f01dbb981ebb · inbound

Neural networks leverage nominally quantum and post-quantum representations cites this paper.

Neural networks leverage nominally quantum and post-quantum representations Next-token pretraining implies in-context learning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T18:48:04.570803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0f54fa9-dd2f-4e5f-a778-3ee3d1e27498 · inbound

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs cites this paper.

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs Next-token pretraining implies in-context learning

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:34:02.835390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 83c8668e-eafe-4dd7-8012-f1781be88702 · inbound

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs cites this paper.

Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs Next-token pretraining implies in-context learning

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-06-30T18:04:58.158650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4e4983ec-6615-4d8c-bcf8-36c90a25873a · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning Next-token pretraining implies in-context learning

Reference 70

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:38:55.895992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.