Pith. sign in

Paper Citation Record · LEDGER

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting

As of 8 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2506.21570.

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

pith.paper-citation-record.v1
2506.21570 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:16:22.385727Z

measured 19 of 19 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 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

19 of 19 outbound references displayed

  • verified exact0
  • verified fuzzy3
  • unresolved16
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 06598154-b1a0-4f5f-bc14-977e4c35f3fe · outbound

This paper cites Chronos: Learning the Language of Time Series.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Chronos: Learning the Language of Time Series

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:20.706920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:20.706920Z digest=sha256:c05d9ddfaea79bf4688300d793e4271f8271150b20e73fb7dce03f1d1a0604c3

Observation ab2a4ad7-06e5-4814-b20d-cbcdb60f91bb · outbound

This paper cites an unresolved cited work.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-07T04:16:23.466494Z

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.

source=arxiv_source observed=2026-08-07T04:16:20.806216Z digest=sha256:405a8da468b5ddf238649b39e8d7d889b3ef29c9c36a6137ae95522f3747361a

Observation 28eea64a-ad28-4eed-b4cf-58543c2f0543 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting On the Opportunities and Risks of Foundation Models

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:20.885318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:20.885318Z digest=sha256:2780433d115439d6f0e00be096c9bf9830b0650d5b66735fd63eb47ad915562e

Observation cc812f25-e325-457b-a8db-bbfe74b790e0 · outbound

This paper cites Scaling Instruction-Finetuned Language Models.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Scaling Instruction-Finetuned Language Models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:20.994738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:20.994738Z digest=sha256:713abf6057e5841b15c7f6e84e8f8e9a408f52491f4dcd2bc5e3d22360bcd0c5

Observation 49559f20-620e-4951-ab56-3f4fedd22644 · outbound

This paper cites Large Language Models Are Zero-Shot Time Series Forecasters.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Large Language Models Are Zero-Shot Time Series Forecasters

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:21.107088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:21.107088Z digest=sha256:72d4e67d0ffd1661131c97700516e204b227a00d07233e4dfc0a2657f9aa3957

Observation 11fcacc2-1117-4cfe-815b-da7c50f91cd5 · outbound

This paper cites Scaling laws for transfer, 2021.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Scaling laws for transfer, 2021

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:16:23.323915Z

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.

source=arxiv_source observed=2026-08-07T04:16:21.201638Z digest=sha256:0273f7947c7150221d2ddf8d67d953056009338cbe6528974751cc806edc51e3

Observation 205753f0-3259-47ba-a391-437f34578e81 · outbound

This paper cites Y., Shi, X., Chen, P.-Y., Liang, Y., Li, Y.-F., Pan, S., and Wen, Q.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Y., Shi, X., Chen, P.-Y., Liang, Y., Li, Y.-F., Pan, S., and Wen, Q

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:16:23.202493Z

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.

source=arxiv_source observed=2026-08-07T04:16:21.286220Z digest=sha256:6002f086f1187a5d2c50d8abb924cb43900f49bf5c781039af1eb2b86e4a696b

Observation daa43046-084e-4e25-993b-abeea03f6ee8 · outbound

This paper cites Scaling Laws for Neural Language Models.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Scaling Laws for Neural Language Models

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:21.360580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:21.360580Z digest=sha256:647bb4b8c536af1942b4b95209f1aa876c6b40bcb096b9afe4614129e93338b7

Observation 38287725-ba8e-4cd7-8c31-d82deb66ca6b · outbound

This paper cites PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:21.458075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:21.458075Z digest=sha256:91f4d193c88a86a252f3ccf5415ebc91d43b3f0694e24a6716a970017adbf2da

Observation 1d57a6a4-cc7d-4532-9c06-d8c3d9dfcc5d · outbound

This paper cites Pretrained Transformers as Universal Computation Engines.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Pretrained Transformers as Universal Computation Engines

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:21.575185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:21.575185Z digest=sha256:5302f27d807b61dd3a025191ef781200375f73b60a5fb3e7c0d59ab457ddb657

Observation 33762d6f-5081-40f4-9daa-680859041d19 · outbound

This paper cites On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:21.672189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:21.672189Z digest=sha256:041704a6f0ae2c26d79374e15c59454719998b2981a8091d466fb6604372fb66

Observation 6c98152a-aeac-4fda-9790-76263581624c · outbound

This paper cites Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:21.754616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:21.754616Z digest=sha256:a468bb140d2391c3d6d346bce4dc0cba5207542b4ade314d5bf4597241e5d872

Observation 758ed7b2-724a-4f94-bba0-bb97d7f5df63 · outbound

This paper cites Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:21.840048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:21.840048Z digest=sha256:4be3cdfb6efac579fe10aec4a87352fc140f65e2d1ebf21e5c7dd206ab9f3d5f

Observation fb853581-8106-46f5-9a92-9a8679e85f04 · outbound

This paper cites an unresolved cited work.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-07T04:16:23.052226Z

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.

source=arxiv_source observed=2026-08-07T04:16:21.922236Z digest=sha256:0accadd368109e64e4bd538943ba18d3d2bead150c4046bfdac3d143251c2725

Observation 7f3d18c2-6685-4b5f-a35a-2ac7f7ab6ca8 · outbound

This paper cites Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:22.020141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:22.020141Z digest=sha256:51d3e084a1804eea87f5f19c0240db335e9ee1206da6c253a6a233966ec38cdb

Observation a695f355-aef3-49e9-8426-859e58cd1c5a · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Finetuned Language Models Are Zero-Shot Learners

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:22.109407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:22.109407Z digest=sha256:98fbfe8ee73746f55a787ce0550dd610a2ed561b8bcd01dff4cd0a7decaade48

Observation eacd3d10-922f-4e55-9c8f-205ebed68ed0 · outbound

This paper cites Context is Key: A Benchmark for Forecasting with Essential Textual Information.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Context is Key: A Benchmark for Forecasting with Essential Textual Information

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:22.191093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:22.191093Z digest=sha256:38c26d31b1fc3641510e6b013985d2e538bb354fa9335789e22d3b66a7be288c

Observation 5ee91e22-2d09-4819-a54d-1c35bd1af9d7 · outbound

This paper cites Unified Training of Universal Time Series Forecasting Transformers.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting Unified Training of Universal Time Series Forecasting Transformers

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T04:16:22.281869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:16:22.281869Z digest=sha256:22ba4ef545f372ac6bbfcd034e2e64ae9d0d870cfa228cf1cbfafac14be069e5

Observation fed88b2e-631f-4349-b2b0-5d41dda4b59c · outbound

This paper cites One fits all:power general time series analysis by pretrained lm, 2023.

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting One fits all:power general time series analysis by pretrained lm, 2023

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T04:16:22.877329Z

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.

source=arxiv_source observed=2026-08-07T04:16:22.385727Z digest=sha256:7f501578b05dc129ac0fc7fb423fd6bfa670586dac8a2c087f97e76bf3506760

Pith citing papers

No inbound Pith citation observations are available.