Pith. sign in

Paper Citation Record · LEDGER

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT

As of 15 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2607.25063.

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

pith.paper-citation-record.v1
2607.25063 v1

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T02:17:22.722321Z

measured 55 of 55 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+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

55 of 55 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved54
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a017cda5-df0e-40e7-9b51-eda191ef9aba · outbound

This paper cites Scaling Laws for Neural Language Models.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Scaling Laws for Neural Language Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.549469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.549469Z digest=sha256:18c95bd98b30280938fad7eef3373a0c8d32a337758123771b72cd9382f63b0e

Observation 7de6ca48-fc67-445d-8173-cb625a657973 · outbound

This paper cites Advances in neural information processing systems , volume=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Advances in neural information processing systems , volume=

Reference 2

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.555774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.555774Z digest=sha256:aedbd8fe9f971ee7ee289b2f692a4b80eb9c143097ed1a8a014522702903dc8b

Observation 693794e0-756c-4284-a3d8-8c0678bbc84a · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 3

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.559122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.559122Z digest=sha256:5a8d667b1277bf7271ceb4936947304f3f05e05312776ec0154bad8673a12f69

Observation bf9bec91-edea-45d5-9941-18fcb656d76e · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT International conference on machine learning , pages=

Reference 4

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.562609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.562609Z digest=sha256:4e8ad1f2e2fa8c7305943758f6a4882ad77f3f4c23c70e730a9c85a99212ee24

Observation 8b98aae2-1e74-45c2-a202-1237ec16531a · outbound

This paper cites an unresolved cited work.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Unresolved cited work

Reference 5

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.565902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.565902Z digest=sha256:0d26b391d5c2f71d8ca3637a5e034d4117f381a96908b03f95fdcf6728167152

Observation 0663d43e-6a84-438b-b175-2ebe0d253d4d · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT International Conference on Learning Representations , volume=

Reference 6

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.569365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.569365Z digest=sha256:860ee274857e272fdf98befd484b6f8fb9803a5d519d44a3c964e792c8081a3d

Observation ef26de6e-c347-48c1-913b-295a52725e6a · outbound

This paper cites an unresolved cited work.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Unresolved cited work

Reference 7

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.572867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.572867Z digest=sha256:2d5aa54eb18af0251ea2119fa20c1db794575570b4735b65fe9f2d38a04460f5

Observation 4430bee9-30df-4c1b-ab24-b7868f5468b4 · outbound

This paper cites arXiv preprint arXiv:2603.16177 , year=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT arXiv preprint arXiv:2603.16177 , year=

Reference 8

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.576162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.576162Z digest=sha256:ee86abf3b1243138e391bff03345ad4ec206b749dea93f18366e6df7ec92fc74

Observation 2ca4cca7-6143-43b7-9043-b1af18142371 · outbound

This paper cites Early Data Exposure Improves Robustness to Subsequent Fine-Tuning.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Early Data Exposure Improves Robustness to Subsequent Fine-Tuning

Reference 9

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.579554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.579554Z digest=sha256:d2dda0c3e35374757fcacf84da27e7d38930e13346918d241942145aab2ccebb

Observation e6b8d3c7-a61f-4d53-9427-7fc352265f2f · outbound

This paper cites Advances in neural information processing systems , volume=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Advances in neural information processing systems , volume=

Reference 10

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.583253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.583253Z digest=sha256:1e6722e012af50f16f77baaaaded57e61d87d3dacc066e0363d9028396b852c1

Observation a2e854f8-4aab-4a6c-88fe-c2f036d2cc92 · outbound

This paper cites Constitutional.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Constitutional

Reference 11

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.586188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.586188Z digest=sha256:c6b5c5cdc136aeb5f000b4599e43f2dd6b319672138a49fad1b4442f7c1b51ce

Observation 9b783277-afef-4725-b218-edf8447cf661 · outbound

This paper cites Advances in neural information processing systems , volume=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Advances in neural information processing systems , volume=

Reference 12

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.589438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.589438Z digest=sha256:545711ae1d7e691f0e44d67fa457b2fa3d4886ba536ca530abfd5720236e0836

Observation 151eaa9e-4f56-475d-b9ae-e77fbb544cb7 · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Advances in Neural Information Processing Systems , volume=

Reference 13

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.592503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.592503Z digest=sha256:c2c6a927ccd709d9de0a2b0cca54f743b988c45596b08893c00afb84e2e4f05b

Observation 3f1a87db-3639-4d34-bd01-7daba77bc9b0 · outbound

This paper cites Proceedings of the 41st International Conference on Machine Learning , articleno =.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Proceedings of the 41st International Conference on Machine Learning , articleno =

Reference 14

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.595556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.595556Z digest=sha256:5ac699fa3512d5fd98f6798cce45f06450699f6299f259fdf7de2235b760171d

Observation 7ed1b347-8401-4272-bde6-832c6c94af8a · outbound

This paper cites Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning

Reference 15

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.598889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.598889Z digest=sha256:9a508cf4e77f9245c03e3646dcd4e47a41492dcf7413d64aed452b0e5215030d

Observation 08552a79-d83d-4268-a07d-b6482d1147a7 · outbound

This paper cites 2023 , eprint=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT 2023 , eprint=

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.602190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.602190Z digest=sha256:649afd0f2aaba139e47f6980f769d20355cee7d985ae6810c90c6eb525d2cceb

Observation 506ccccb-2154-46e6-8a53-bbd342554085 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 17

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.605460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.605460Z digest=sha256:8a578ce537634e482948cde1e8d6acd6f31e8539af7421c8228d4d557215bc98

Observation b089b126-a29d-491b-a4e4-5b826199a182 · outbound

This paper cites XST est: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT XST est: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 18

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.609047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.609047Z digest=sha256:4241c10763b49db7dedb18b9f6e19fb95163b16eea2c682c51b6ca0b14687c22

Observation d92f9899-399c-4df5-854e-a7bbb54b6da4 · outbound

This paper cites an unresolved cited work.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Unresolved cited work

Reference 19

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.612389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.612389Z digest=sha256:06c3d488b8c032194110b2fd8f00f7e5a0cae856491b542e9dc7a5ccec9bcc55

Observation 043496bb-c4a9-4242-b319-bed7dd58d8e9 · outbound

This paper cites 2025 , url=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT 2025 , url=

Reference 20

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.615441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.615441Z digest=sha256:4d6e80a30cc90061b96567fc6d316641f0f76d0ede638f8cc396fc437d804a3a

Observation 9c4a539c-1d00-47ac-8d88-31973bdf4348 · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Advances in Neural Information Processing Systems , volume=

Reference 21

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.618898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.618898Z digest=sha256:c801b8618bda0cd5612d451ac2538538125d355b14d1fedd4ba8341dbc32f9f6

Observation 7fb46ce0-fd34-4f4c-8e7d-537b2e746372 · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT International Conference on Learning Representations , volume=

Reference 22

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.621818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.621818Z digest=sha256:2b6b0117c0ed7c056ab29324a5c60b176f0d5705fcb7c98a97d67c1efac2b648

Observation 7aae149f-f1dc-4ffe-af76-106006939552 · outbound

This paper cites an unresolved cited work.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Unresolved cited work

Reference 23

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.625044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.625044Z digest=sha256:a4e405a71bc293758bc7dd42519c9c06b964b001b55dcd8e99462fde16e61673

Observation 95425667-b0f4-4911-bd19-de56338d7255 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 24

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.627963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.627963Z digest=sha256:83b459d1e613286519bd2940ca509332153dad872119f25cf027fe27fe1548e5

Observation ed7dc7ad-fc75-4f71-a0d8-2545cce8a2e8 · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT International Conference on Learning Representations , year=

Reference 25

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.630975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.630975Z digest=sha256:2e71b63f1a6db2c5cfb6d8df118b22e74ba6476fc459cf1b463bdd85e305e3a6

Observation 7e1c07db-132b-431a-b4ab-7987881616ab · outbound

This paper cites an unresolved cited work.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Unresolved cited work

Reference 26

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.634113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.634113Z digest=sha256:c530087c0ba7ea30a8df872366e99f61ad00c11e463c43469731e240ad19b954

Observation e6ee6d38-722d-49bf-baec-06890b6e7605 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 27

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.637543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.637543Z digest=sha256:fca17bb73fabe812b9ca4ba861d05a1eed40cd9d5fb63ef73e75dcffa229d809

Observation cd5f8ee0-a79e-4939-9c06-95fbdaebece4 · outbound

This paper cites 2021 , publisher=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT 2021 , publisher=

Reference 28

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.640634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.640634Z digest=sha256:f8c7cac872064eba701fd48ed3a75b4af3e8913dd59a62d254e36454aa1158df

Observation 522c6c56-00a1-4fe6-ae70-4fd13bca52a8 · outbound

This paper cites The Llama 3 Herd of Models.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT The Llama 3 Herd of Models

Reference 29

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.643531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.643531Z digest=sha256:db83775fbcbe2aee7a004b82c6ed7f3be981160bf516879ce771d959af133919

Observation 9e99cc1b-85f8-4ef8-b5a6-0e8738036fc6 · outbound

This paper cites 2 OLMo 2 Furious.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT 2 OLMo 2 Furious

Reference 30

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.646936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.646936Z digest=sha256:fe2c44e6db7481b287b80cd3419cb32e153a85501e6d06e976cbcf801a8d58c6

Observation 1722050a-23af-44be-acb0-af7f87635e53 · outbound

This paper cites Advances in neural information processing systems , volume=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Advances in neural information processing systems , volume=

Reference 31

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.650146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.650146Z digest=sha256:521acec1fc71207157e631712689b73097c430da7c905a698923961763913c1a

Observation eaf029c5-f149-4594-b802-7d02f6fd0cc0 · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Advances in Neural Information Processing Systems , volume=

Reference 32

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.653157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.653157Z digest=sha256:31d13d32df52d9b31500ec07e4dab570a09d092a789278da541a006181d6b491

Observation 96e425a5-5712-4153-99e9-85cf537b3355 · outbound

This paper cites an unresolved cited work.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Unresolved cited work

Reference 33

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.656004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.656004Z digest=sha256:afe4b713a7c4728fba80882f4bf933e6b9bf58e1ae0d17af6502b571b0612fc7

Observation fa6c10c0-0721-4734-9369-c464dd62f674 · outbound

This paper cites an unresolved cited work.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Unresolved cited work

Reference 34

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.659185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.659185Z digest=sha256:6140aca646261cf99275e7b1a6ce1baac8df2086662e07a959b8084de3dad44b

Observation 5871ca10-dbf3-4100-973c-400b5e76cec3 · outbound

This paper cites Researching Alignment Research: Unsupervised Analysis.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Researching Alignment Research: Unsupervised Analysis

Reference 35

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.662103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.662103Z digest=sha256:cacc0ddd572a3e72ee06850bdbeb1c152fb56c24080a74a88f36750fa650a62b

Observation 57aa9629-a0c6-4f71-8db7-aa87d9be263e · outbound

This paper cites an unresolved cited work.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Unresolved cited work

Reference 36

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.665077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.665077Z digest=sha256:ac1ece29b96e3c95acbf45dd6076b36468957833d56aef81ef19153f342b02cd

Observation 225c1992-b2d7-4022-85c7-36b6b4f70fe1 · outbound

This paper cites Findings of the association for computational linguistics: EMNLP 2020 , pages=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Findings of the association for computational linguistics: EMNLP 2020 , pages=

Reference 37

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.667950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.667950Z digest=sha256:752ed580d11a593036725922ca1d9bb870f557320f9379c4d406120f179b751a

Observation bad1bfd2-0b88-489c-91bb-568b3908683e · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2023 , pages=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Findings of the Association for Computational Linguistics: EMNLP 2023 , pages=

Reference 38

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.670820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.670820Z digest=sha256:02670a431737dca5e4dbb6e2e3a712c507a033da9efd3df3a849228becc74738

Observation c777d2ff-4d37-4f8b-b0fb-43a94a315687 · outbound

This paper cites Aligning.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Aligning

Reference 39

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.673604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.673604Z digest=sha256:904288eb21c4297c02562cf7692ac992e109464911758070cc2c2a457c787a8b

Observation 117591e9-ec13-4fb2-8b57-073c21886fcb · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 40

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.676849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.676849Z digest=sha256:757753b66b893fef3ea7acd16b0bf626b6c8497b74f182e199fe41903f7bf86f

Observation 693e832a-5de3-4c13-ae6d-378d262db937 · outbound

This paper cites Model Spec Midtraining: Improving How Alignment Training Generalizes.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Model Spec Midtraining: Improving How Alignment Training Generalizes

Reference 41

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.679919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.679919Z digest=sha256:0aff2d9cede3a04cb787922080a9ec582ca7dcd207f58eb5e68788d42226645a

Observation 8a556665-a590-4f9e-93a8-3f53118fe5f2 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Instruction-Following Evaluation for Large Language Models

Reference 42

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.683124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.683124Z digest=sha256:cccc37ee6b35040db68ae6c7966858dc18e26d2625c75f3f7a29667074bfa39f

Observation 200cdfba-ffe3-4b01-8d78-a89e72cde748 · outbound

This paper cites an unresolved cited work.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Unresolved cited work

Reference 43

Resolution
parse uncertain
no resolver link, observed 2026-07-31T02:17:22.686221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.686221Z digest=sha256:25ae7469120ca3e690a3276d20d68e2fb3932769ac8f769b93dbe6fe44958d3a

Observation 6d26df06-1b48-41ef-8852-0de2fc651fcb · outbound

This paper cites an unresolved cited work.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Unresolved cited work

Reference 44

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.689237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.689237Z digest=sha256:8ee86af01cfef65cd258a20c2eead6318501df1988a078a17c13c940e4ddcf44

Observation 501a62a8-e6f5-4b7f-8ad7-c51fe2427d1c · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT International Conference on Learning Representations , volume=

Reference 45

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.692274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.692274Z digest=sha256:f781d2395030bc5adcf58f41b946e7607249e4d06cbb55e0ad1915b757680fd7

Observation 45550689-fb79-4e38-be1f-4a110e429086 · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Advances in Neural Information Processing Systems , volume=

Reference 46

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.695296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.695296Z digest=sha256:3050943fd3af51aec158dd62e42d2c3d7d2129aec97742890d171fbed61f2a15

Observation 03867213-9911-42d0-9d82-3f73af0687ff · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2023 , pages=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Findings of the Association for Computational Linguistics: ACL 2023 , pages=

Reference 47

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.698120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.698120Z digest=sha256:d735f24c0a7bd5d94a1e6dcec556333a4aba45c1ea8854fc89d69e7b9dd576fd

Observation 1248bad9-b84d-4c77-9942-97b5daa5297c · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT International Conference on Learning Representations , volume=

Reference 48

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.700943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.700943Z digest=sha256:bb59174930667b37c2b0ea62f8cc0aac47811a7bf912cea13cf618f2fa507e53

Observation c053dac0-e414-44d8-a643-860ac74963f8 · outbound

This paper cites Zenodo , year=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Zenodo , year=

Reference 49

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.703918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.703918Z digest=sha256:c37fb62db0aa04b732706ccf2415c7e7a8aee81c3d8cc64a1d1756c3d2e1584c

Observation ecefa553-4193-4a98-8e25-ce9f99e89c1c · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Advances in Neural Information Processing Systems (NeurIPS) , year=

Reference 50

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.707201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.707201Z digest=sha256:ced4d8d2dcaee5c49d44f1ea4c27a546255d6d5ce504a608f496c085ac85c052

Observation 0c4d1232-2bcc-4c12-9b67-adfcfa9ed033 · outbound

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

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT International conference on machine learning , pages=

Reference 51

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.710267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.710267Z digest=sha256:3e7b7d991c3d0d1e7ac87f5e717ec4f4d860a1213d5d27109d08af406dd63203

Observation 08fbf192-c69a-4b56-bfbe-432969869482 · outbound

This paper cites Advances in neural information processing systems , volume=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Advances in neural information processing systems , volume=

Reference 52

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.713408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.713408Z digest=sha256:488d8af4763a10093f92b5fc7eb5b7a624065a64a907db81df724d0e55f89b56

Observation a4faee45-8f7b-48b5-a646-1eb5f3244604 · outbound

This paper cites International Conference on Machine Learning , pages=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT International Conference on Machine Learning , pages=

Reference 53

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.716353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.716353Z digest=sha256:db6149d76b66c6c3baa2b233f63ce29d932f16a4b780f832daa1b0df8ca8adda

Observation 338fe9c2-5404-45a7-9541-5e26eb5e7735 · outbound

This paper cites Nature , volume=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT Nature , volume=

Reference 54

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.719347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.719347Z digest=sha256:944cdfe04b069270d3bbf0e50cd133c5693c858730ec9f319412bc94b7b4a95e

Observation 67494d31-016c-410d-ba14-546bd0c1382d · outbound

This paper cites The Fourteenth International Conference on Learning Representations , year=.

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT The Fourteenth International Conference on Learning Representations , year=

Reference 55

Resolution
unresolved
no resolver link, observed 2026-07-31T02:17:22.722321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T02:17:22.722321Z digest=sha256:a1aaf8c075dbf3a47f294f63a0dbadda243e9706583375aaa9d9021a42ba3840

Pith citing papers

No inbound Pith citation observations are available.