Paper Citation Record · LEDGER

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation

As of 18 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 2 inbound Pith citation observations for arXiv:2504.12637.

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

pith.paper-citation-record.v1
2504.12637 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:30:12.291887Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T14:50:11.769103Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T01:27:30.482602Z

Reference resolution

34 of 34 outbound references displayed

verified exact0
verified fuzzy1
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 40dfbd24-c728-4250-b123-33fab9d6694e · outbound

This paper cites write newline.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.150200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc653956-f292-4a35-96a7-3a852ed1ee62 · outbound

This paper cites @esa (Ref.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation @esa (Ref

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.155450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c5ac33f-72c3-444a-bdaf-d49dbe413880 · outbound

This paper cites an unresolved cited work.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.160119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28b75337-ae1e-4265-87ef-d470219cee63 · outbound

This paper cites ִ|z !|؆l- b)<v kڰ2<WנXy<PG OV< /|4; 'K.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation ִ|z !|؆l- b)<v kڰ2<WנXy<PG OV< /|4; 'K

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:30:12.758054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4be106fb-9499-462d-bd94-45ab909651c8 · outbound

This paper cites PaLM 2 Technical Report.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation PaLM 2 Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.170794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65c20c11-b30d-4110-b654-964d3c0e3bfa · outbound

This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.175136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b770a7ad-3e15-4808-be22-6955ff2d5f5c · outbound

This paper cites Longformer: The Long-Document Transformer.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Longformer: The Long-Document Transformer

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.178847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca2dff60-a409-45d7-ba62-a821d7cceba7 · outbound

This paper cites Extending Context Window of Large Language Models via Positional Interpolation.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Extending Context Window of Large Language Models via Positional Interpolation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.183156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7feb1de-4c17-4800-bcbc-6757c9e7786a · outbound

This paper cites LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.187339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cb6629a-8cdf-435f-a247-355ab967c0d7 · outbound

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

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.192206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55cc07b1-a787-4f99-82f0-3facb73adc7b · outbound

This paper cites LongT5: Efficient Text-To-Text Transformer for Long Sequences.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation LongT5: Efficient Text-To-Text Transformer for Long Sequences

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.196540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3215a79-317e-4d62-8711-c0a4865f0929 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Measuring Massive Multitask Language Understanding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.201018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2700ea7c-64a2-4ed5-bc6f-ff2ddc8af910 · outbound

This paper cites Block Transformer: Global-to-Local Language Modeling for Fast Inference.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Block Transformer: Global-to-Local Language Modeling for Fast Inference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.206076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba4d1b4c-109d-4729-950a-4aee0ad25191 · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.210387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a7dc352-99b1-41b7-b37b-0432fd1dc54a · outbound

This paper cites Mistral 7B.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Mistral 7B

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.214583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95629d72-ec16-4dd7-b1b0-4c5a3effe215 · outbound

This paper cites Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.219021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe453335-108f-427f-b395-34bcb87b5a62 · outbound

This paper cites LooGLE: Can Long-Context Language Models Understand Long Contexts?.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation LooGLE: Can Long-Context Language Models Understand Long Contexts?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.222810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5c416b8-a4a8-4e45-87e7-3c2ce628a7c1 · outbound

This paper cites Lost in the Middle: How Language Models Use Long Contexts.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Lost in the Middle: How Language Models Use Long Contexts

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.226750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0327cd07-774e-4a42-ba42-e2d0b215e45b · outbound

This paper cites Base of RoPE Bounds Context Length.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Base of RoPE Bounds Context Length

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.231091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67bbbb5e-8c53-4759-999c-59beec1d9351 · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Locating and Editing Factual Associations in GPT

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.235253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6e2309f-070b-4a47-b9d4-d94c6d5855d4 · outbound

This paper cites Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.239614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 069dff6d-6bb5-45a7-ba4c-044d64d03f47 · outbound

This paper cites YaRN: Efficient Context Window Extension of Large Language Models.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation YaRN: Efficient Context Window Extension of Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.243291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 465d91b4-4a7c-42e1-a835-ba4d24730da9 · outbound

This paper cites Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.247025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab0f40c1-7985-4cca-890f-c3651e37eddd · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.250564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b77c7d5c-208c-4b9f-b803-9c620c6b5c02 · outbound

This paper cites A Length-Extrapolatable Transformer.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation A Length-Extrapolatable Transformer

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.254689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b093f22-26e6-4919-8281-750cef53fceb · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation LLaMA: Open and Efficient Foundation Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.258310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ec5b2a2-62f5-48e7-beaf-f5a32d6031c0 · outbound

This paper cites Self-Instruct: Aligning Language Models with Self-Generated Instructions.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Self-Instruct: Aligning Language Models with Self-Generated Instructions

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.261784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 822263e8-a98b-474b-8222-f4e7d085b9c7 · outbound

This paper cites Emergent Abilities of Large Language Models.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Emergent Abilities of Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.265736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89e7d83b-9427-42b3-a8b0-b454b915da9b · outbound

This paper cites BloombergGPT: A Large Language Model for Finance.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation BloombergGPT: A Large Language Model for Finance

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.270024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7317f681-6c9b-44a3-bc55-2703162eaa23 · outbound

This paper cites Effective Long-Context Scaling of Foundation Models.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Effective Long-Context Scaling of Foundation Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.274120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9ff6388-87f4-4f68-bdc9-f9231cdb7c3c · outbound

This paper cites WizardLM: Empowering large pre-trained language models to follow complex instructions.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation WizardLM: Empowering large pre-trained language models to follow complex instructions

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.278242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 542447ae-9462-432e-b850-6ff43a07fcf5 · outbound

This paper cites Automatic Instruction Evolving for Large Language Models.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation Automatic Instruction Evolving for Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.282172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea604e59-3892-4460-9c12-06a5e4637459 · outbound

This paper cites $\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation $\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.286706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 741d1b85-0554-466f-87f8-51f6d9194daa · outbound

This paper cites LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models.

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T12:30:12.291887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f6bf2c44-25a1-4e93-a3b0-b714e01912ae · inbound

End-to-End Context Compression at Scale cites this paper.

End-to-End Context Compression at Scale Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-03T01:27:30.484693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e2c9851c-511c-40bc-881c-442b23af3354 · inbound

Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL cites this paper.

Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T14:50:11.769103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.