Pith. sign in

Paper Citation Record · LEDGER

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models

As of 18 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2608.07261.

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

pith.paper-citation-record.v1
2608.07261 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T11:38:34.629928Z

measured 14 of 14 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

14 of 14 outbound references displayed

  • verified exact0
  • verified fuzzy2
  • unresolved12
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d14852e5-338b-4469-b7a5-4cfbaa0e91e1 · outbound

This paper cites an unresolved cited work.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Unresolved cited work

Reference 1

Resolution
unresolved
raw_fallback, observed 2026-08-10T11:38:35.273516Z

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.

source=pdf_text observed=2026-08-10T11:38:34.602908Z digest=sha256:e0d1510f520a3241b9eb52aadec63219d5792c9de061e497fb344259243396f1

Observation 8a74c1e8-f475-491f-91bd-e69699878d56 · outbound

This paper cites an unresolved cited work.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-10T11:38:35.256774Z

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.

source=pdf_text observed=2026-08-10T11:38:34.607331Z digest=sha256:a4e8d10f2e1aa2d0e7c94e3cfe06d0eb71b6b8cf973a96f4e1a5baac725ddee5

Observation 1c4de3c1-d959-410e-a4cf-1f0c70d68b88 · outbound

This paper cites an unresolved cited work.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-10T11:38:35.240481Z

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.

source=pdf_text observed=2026-08-10T11:38:34.611998Z digest=sha256:5da064e7696dece75ce31f1a64262c8effca683e28c4f406caf0ad98c71a20ff

Observation bed8637e-3eee-4548-a1e6-d7ada862ea70 · outbound

This paper cites Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-10T11:38:34.581649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T11:38:34.581649Z digest=sha256:7a863a387f9cdb04bf6673b6ec87c8aa785941b47f31e88b3b72702f97f3e791

Observation 16d29be9-f085-44a5-9baa-9fa98128b34d · outbound

This paper cites Improve Mathematical Reasoning in Language Models by Automated Process Supervision.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-10T11:38:34.586747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T11:38:34.586747Z digest=sha256:9946fd1ea39d919a01b97c7ae5459307d48d06ac4874ddb200ae6139747bad46

Observation c38bae10-6769-4b6a-a413-6879d7b57b6e · outbound

This paper cites Jiaran Ye, Zijun Yao, Zhidian Huang, Liangming Pan, Jinxin Liu, Yushi Bai, Amy Xin, Liu Weichuan, Xi- aoyin Che, Lei Hou, and 1 others.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Jiaran Ye, Zijun Yao, Zhidian Huang, Liangming Pan, Jinxin Liu, Yushi Bai, Amy Xin, Liu Weichuan, Xi- aoyin Che, Lei Hou, and 1 others

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-10T11:38:34.592284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T11:38:34.592284Z digest=sha256:60bc73e7b863ea9c1b20f217f5497a6730c2ed45ad8464fd99b9a4fbaa781721

Observation b99b62d8-c2a0-4ceb-89c2-feeaa02169d5 · outbound

This paper cites Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-10T11:38:34.597470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T11:38:34.597470Z digest=sha256:fd946ad61ef9eb77307aadea0987766dfdfcfe684b9664198574f8375f4be64e

Observation b507a87e-3f1d-4272-aa24-dea379873a0b · outbound

This paper cites an unresolved cited work.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Unresolved cited work

Reference 11

Resolution
unresolved
raw_fallback, observed 2026-08-10T11:38:35.225940Z

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.

source=pdf_text observed=2026-08-10T11:38:34.616344Z digest=sha256:ef7c676fe9aab2890afca0975f625e9441b1b9ed261c1506200dd359388ab136

Observation 523e7a16-3abb-4fe7-8128-e2732f6ccfd6 · outbound

This paper cites This experiment enables us to investigate how local graph structure influences the formation of entity representations.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models This experiment enables us to investigate how local graph structure influences the formation of entity representations

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T11:38:35.210262Z

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.

source=pdf_text observed=2026-08-10T11:38:34.620550Z digest=sha256:e0ad784904c9cde4edbb1aa4c00b88cf4393af413ca4aee0a4ca23117b7730c3

Observation 328a3f6f-a6d2-43b2-b216-61d8aabffa8f · outbound

This paper cites For this experiment, we directly use the model after 3,500,000 optimization steps of standard training.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models For this experiment, we directly use the model after 3,500,000 optimization steps of standard training

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T11:38:35.159539Z

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.

source=pdf_text observed=2026-08-10T11:38:34.625375Z digest=sha256:4c646b86be507fedbc2550b024641300da6ee1b24e6bdae2272f22fc7ceaf9a6

Observation 7d24ad1c-349e-4b18-893c-3f786ef1bd4d · outbound

This paper cites an unresolved cited work.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-10T11:38:35.016741Z

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.

source=pdf_text observed=2026-08-10T11:38:34.629928Z digest=sha256:3a9c1a37e57134e408ea4097840de2388dd9b64cc3ad91c62ccc1e76393747de

Observation af87762b-e207-4b10-a110-b2a01b2da9e2 · outbound

This paper cites From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-10T11:38:34.576529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T11:38:34.576529Z digest=sha256:e1b7774a5baa9b4e0b3312881d9a93762a97d48febc38e39be69fa441983e261

Observation eeafa6c4-8bab-43c1-bbb5-84273932774a · outbound

This paper cites Taken out of context: On measuring situational awareness in LLMs.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Taken out of context: On measuring situational awareness in LLMs

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-10T11:38:34.571448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T11:38:34.571448Z digest=sha256:8f5ac690ecd1315f5ee75c5160cd92a4d5ea32ec25135605a87316496ae5a988

Observation da51ac9c-b597-4491-ae83-e152fc80d67b · outbound

This paper cites Evolution of SAE Features Across Layers in LLMs.

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Evolution of SAE Features Across Layers in LLMs

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-10T11:38:34.565960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T11:38:34.565960Z digest=sha256:2947ed65d56deee49bd0105d0eddababca4960c49a8abd0304b8748d47076c85

Pith citing papers

No inbound Pith citation observations are available.