Paper Citation Record · LEDGER

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs

As of 23 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 1 inbound Pith citation observation for arXiv:2602.03554.

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

pith.paper-citation-record.v1
2602.03554 v2

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T04:59:00.889111Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-11T15:07:55.363793Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

26 of 26 outbound references displayed

verified exact3
verified fuzzy0
unresolved21
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 02e46857-7a7c-4b5c-90c0-0217c827830d · outbound

This paper cites an unresolved cited work.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:58.856218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 511ef837-b7a3-4dd2-a514-b229493d7fc2 · outbound

This paper cites an unresolved cited work.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Unresolved cited work

Reference 2

Resolution: verified exact; doi, observed 2026-08-03T05:03:27.650972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c46dbbd4-c107-4927-9128-afc743b178cc · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:58.354736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e684e095-658a-4bc6-9974-b6f2d629aa23 · outbound

This paper cites Nature Language Model: Deciphering the Language of Nature for Scientific Discovery.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Nature Language Model: Deciphering the Language of Nature for Scientific Discovery

Reference 9

Resolution: malformed identifier; no resolver link, observed 2026-08-03T04:58:58.455595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b9ec24d-c33f-440d-bed2-0472cddaa29f · outbound

This paper cites The URSA-expert-2026 was used as a holdout set.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs The URSA-expert-2026 was used as a holdout set

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:59.054852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde41ac0-18c6-4984-879c-ab2d02044c8d · outbound

This paper cites Left Arm (N-aryl-oxadiazole- heterocycle): ‘Nc2noc(-c3cnn4ccccc34)n2‘ 3.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs **Left Arm (N-aryl-oxadiazole- heterocycle):** ‘Nc2noc(-c3cnn4ccccc34)n2‘ 3

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:59.224783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99eb9ad4-9be4-4d7b-aea9-4c58eba81b12 · outbound

This paper cites an unresolved cited work.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:59.471910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2b821b2-8b4d-4f4c-bb7e-e5d280fa02e5 · outbound

This paper cites This would yield ‘<smiles>Cc1ccc(Nc2noc(-c3cnn4ccccc34)n2)c(CO)c1</smiles >‘.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs This would yield ‘<smiles>Cc1ccc(Nc2noc(-c3cnn4ccccc34)n2)c(CO)c1</smiles >‘

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:59.696710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36fe11a2-3adf-4a00-b602-7a73b5dbb769 · outbound

This paper cites The CH2O ether linkage could be formed via Williamson ether synthesis 3.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs The CH2O ether linkage could be formed via Williamson ether synthesis 3

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:59.884580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83e4511e-9bef-4524-b256-66c8234127d1 · outbound

This paper cites an unresolved cited work.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T04:59:00.041836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57abb5e2-9d56-473d-a767-3f548dd8b8ca · outbound

This paper cites an unresolved cited work.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T04:59:00.210387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c485157-8f45-427e-97b6-c28d769b8f53 · outbound

This paper cites Jin, W., Coley, C., Barzilay, R., and Jaakkola, T.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Jin, W., Coley, C., Barzilay, R., and Jaakkola, T

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:57.824703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8d37a4e-b461-4ae1-af10-d17eb71b0c34 · outbound

This paper cites an unresolved cited work.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T04:59:00.338851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21b56a4a-d85a-41ed-927a-14ccef5d8358 · outbound

This paper cites The ether bond (C-O-C) between the benzyl and pyridazinone 2.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs The ether bond (C-O-C) between the benzyl and pyridazinone 2

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T04:59:00.405807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8e0672f-f177-4768-8aab-7bce083c8c13 · outbound

This paper cites Atom-anchored LLMs speak Chemistry: A Retrosynthesis Demonstration.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Atom-anchored LLMs speak Chemistry: A Retrosynthesis Demonstration

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:57.579172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd1a3af8-f562-4748-8a83-0b91086b6bba · outbound

This paper cites an unresolved cited work.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T04:59:00.590114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f970777b-9f85-4a89-9494-6af00b578732 · outbound

This paper cites A nucleophilic aromatic substitution or Williamson ether synthesis could couple these fragments together.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs A nucleophilic aromatic substitution or Williamson ether synthesis could couple these fragments together

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T04:59:00.697446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c30477b-c80d-4271-92d1-8633a227b8f2 · outbound

This paper cites - Multiple electron-withdrawing groups activate the ring and allow substitution.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs - Multiple electron-withdrawing groups activate the ring and allow substitution

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T04:59:00.765668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a00ea60-4001-4379-ba87-ddf398754d5b · outbound

This paper cites - Perhaps a Buchwald–Hartwig amination? Possible precursors: The first part is the source molecule, and the second component is the amine.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs - Perhaps a Buchwald–Hartwig amination? Possible precursors: The first part is the source molecule, and the second component is the amine

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T04:59:00.889111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee7a1531-8dcc-4833-8b56-f1675107c40d · outbound

This paper cites emnlp-main.70.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs emnlp-main.70

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:58.252151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1e44f48-cd44-48b6-b672-aec04fe9e30f · outbound

This paper cites ChemLLM: A Chemical Large Language Model.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs ChemLLM: A Chemical Large Language Model

Reference 827

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:58.631253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c57d4c3b-a768-4145-9ba6-9ab5d5a5cf3d · outbound

This paper cites 2025/840.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs 2025/840

Reference 840

Resolution: malformed identifier; no resolver link, observed 2026-08-03T04:58:57.962122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae1aad04-74d4-44dc-924d-98d267ab6449 · outbound

This paper cites wiley.com/doi/abs/10.1002/wcms.1694.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs wiley.com/doi/abs/10.1002/wcms.1694

Reference 1694

Resolution: verified exact; doi, observed 2026-08-03T05:03:27.835791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 62e816ae-e4b1-4bec-bece-2a325d52a207 · outbound

This paper cites cc/paper_files/paper/2017/file/ ced556cd9f9c0c8315cfbe0744a3baf0-Paper.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs cc/paper_files/paper/2017/file/ ced556cd9f9c0c8315cfbe0744a3baf0-Paper

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:57.920781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41c911ae-cc9d-4cf0-b3a4-99f21de657e3 · outbound

This paper cites Livne, M., Miftahutdinov, Z., Tutubalina, E., Kuznetsov, M., Polykovskiy, D., Brundyn, A., Jhunjhunwala, A., Costa, A., Aliper, A., Aspuru-Guzik, A., and Zhavoronkov, A.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Livne, M., Miftahutdinov, Z., Tutubalina, E., Kuznetsov, M., Polykovskiy, D., Brundyn, A., Jhunjhunwala, A., Costa, A., Aliper, A., Aspuru-Guzik, A., and Zhavoronkov, A

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T04:58:58.111955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd12049b-2f17-4570-b60c-88301c99cffe · outbound

This paper cites an unresolved cited work.

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs Unresolved cited work

Reference 9294

Resolution: verified exact; doi, observed 2026-08-03T05:03:28.942807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 136694bf-fbc2-4772-8e85-758e027704d7 · inbound

URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment cites this paper.

URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-11T15:07:55.363793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.