Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-19T15:50:01.064709Z
Paper Citation Record · LEDGER
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design
As of 23 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2605.15341.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-12T01:16:50.927415Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
45 of 45 outbound references displayed
- verified exact9
- verified fuzzy24
- unresolved4
- parse uncertain0
- malformed identifier5
- metadata mismatch3
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation b5cf1daf-ba07-4fe6-88c1-0bd3449b9607 · outbound
This paper cites Gonzalez.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Gonzalez
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:39.013931Z
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 e631a623-c8ed-47e4-8268-51ee34bb6aa5 · outbound
This paper cites Autonomous chemical research with large language models.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Autonomous chemical research with large language models
Reference 2
- Resolution
- verified exact
- doi, observed 2026-05-19T15:52:37.969723Z
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 269297ba-250e-419b-8736-9973f737c78f · outbound
This paper cites On the Measure of Intelligence.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design On the Measure of Intelligence
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T15:52:38.080243Z
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 651285ec-1fe0-4e4b-9cc6-6f64dde5da37 · outbound
This paper cites Towards an AI co-scientist.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Towards an AI co-scientist
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T15:52:38.089188Z
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 60020a3d-142f-4cbe-82ff-c3a849976384 · outbound
This paper cites Ideabench: Benchmarking large language models for research idea generation.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Ideabench: Benchmarking large language models for research idea generation
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:39.004715Z
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 77e0de7a-30d0-4f0e-b4b2-233d509d1c14 · outbound
This paper cites BurstGPT: A real-world workload dataset to optimize LLM serving systems.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design BurstGPT: A real-world workload dataset to optimize LLM serving systems
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-19T15:52:37.960886Z
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 f0908c49-759b-44bc-9412-464948262429 · outbound
This paper cites LAB-Bench: Measuring Capabilities of Language Models for Biology Research.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design LAB-Bench: Measuring Capabilities of Language Models for Biology Research
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T15:52:38.083379Z
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 221c4c7c-b92b-4040-b84f-f23b649768d4 · outbound
This paper cites ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T15:52:38.068813Z
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 0a6921a4-010e-4a87-9dec-fba740d5baaa · outbound
This paper cites A framework for evaluating the chemical knowledge and reasoning abilities of large language models against the expertise of chemists.Nature Chemistry.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design A framework for evaluating the chemical knowledge and reasoning abilities of large language models against the expertise of chemists.Nature Chemistry
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.961604Z
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 4455a4df-0ea0-4926-bf7f-f6f2bb1f71fd · outbound
This paper cites Laurent, Alex Andonian, Benjamin Tenmann, Siddharth Narayanan, Geemi P.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Laurent, Alex Andonian, Benjamin Tenmann, Siddharth Narayanan, Geemi P
Reference 10
- Resolution
- malformed identifier
- arxiv_id, observed 2026-05-19T15:52:38.075556Z
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 c3b4dfc1-d676-44b8-9b68-6a027b65d602 · outbound
This paper cites Journal of Open Psychology Data , author =.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Journal of Open Psychology Data , author =
Reference 11
- Resolution
- metadata mismatch
- doi, observed 2026-05-19T15:52:37.962911Z
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 ddd4b8dd-6b70-458c-a819-e05b7575915e · outbound
This paper cites Quantifying language models’ sensitivity to spurious features in prompt design, or: How i learned to start worrying about prompt formatting.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Quantifying language models’ sensitivity to spurious features in prompt design, or: How i learned to start worrying about prompt formatting
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.967808Z
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 7a375841-1d3c-4874-9943-8543ce926562 · outbound
This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T15:52:38.086290Z
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 96707ca3-2673-4e7d-be44-270da38de506 · outbound
This paper cites McConnell Rooney, M.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design McConnell Rooney, M
Reference 14
- Resolution
- malformed identifier
- doi_truncated, observed 2026-05-19T15:52:37.967345Z
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 fb733375-8091-49ae-b246-0ba0c42c5cf7 · outbound
This paper cites Solving math word problems with process- and outcome-based feedback.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Solving math word problems with process- and outcome-based feedback
Reference 15
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-19T15:52:38.071639Z
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 3c590227-1b47-4efa-bf25-fe5d64cd14d9 · outbound
This paper cites Loomba, Shichang Zhang, Yizhou Sun, and Wei Wang.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Loomba, Shichang Zhang, Yizhou Sun, and Wei Wang
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:39.017783Z
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 fd5f72ee-db10-4a12-b720-b7da73af6b89 · outbound
This paper cites Reasoning or reciting? exploring the capabilities and limitations of language models through counterfactual tasks.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Reasoning or reciting? exploring the capabilities and limitations of language models through counterfactual tasks
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:39.008664Z
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 8188bd6c-ad1b-44fd-9b47-fd4cf14f668e · outbound
This paper cites Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin
Reference 18
- Resolution
- verified exact
- doi, observed 2026-05-19T15:52:37.971766Z
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 244412da-2759-48b4-8b3b-deecc4444c45 · outbound
This paper cites rank-2, 50%).
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design rank-2, 50%)
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:39.001109Z
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 568380db-c8d6-437e-a0ea-009232258018 · outbound
This paper cites an unresolved cited work.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Unresolved cited work
Reference 20
- Resolution
- unresolved
- raw_fallback, observed 2026-05-19T15:52:39.002833Z
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 bd4eff59-07d9-4195-80b5-acc2fd6b458a · outbound
This paper cites You are optimizing CRISPR HDR efficiency.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design You are optimizing CRISPR HDR efficiency
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T15:52:37.957631Z
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 10c2a073-92eb-4340-8691-877eeaf00b1e · outbound
This paper cites no model clears 50%.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design no model clears 50%
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:39.006745Z
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 bf6af465-1330-42cc-9510-e96c6c9f4b76 · outbound
This paper cites Task-clustered 95% CIs shown.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Task-clustered 95% CIs shown
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:39.012193Z
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 e8f92d74-ef9c-4fa0-a83c-6c268a324c23 · outbound
This paper cites Error bars are task-clustered bootstrap 95% CIs (𝐵=2000).
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Error bars are task-clustered bootstrap 95% CIs (𝐵=2000)
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:39.010438Z
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 d62e5ed4-d65d-4a05-a940-6132584f5404 · outbound
This paper cites GP-UCB, across horizons.Each model is ranked by the fraction of 45 biology tasks where its median bsf-AUC@𝑘 outperforms GP-UCB.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design GP-UCB, across horizons.Each model is ranked by the fraction of 45 biology tasks where its median bsf-AUC@𝑘 outperforms GP-UCB
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:39.015969Z
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 a02cde04-87ef-4fa5-9f29-fab0766f1a0e · outbound
This paper cites Error bars are task-clustered bootstrap 95% CIs (𝐵= 2000).
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Error bars are task-clustered bootstrap 95% CIs (𝐵= 2000)
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.997609Z
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 68bcc7b3-c85f-4de1-8d33-f843a07bed8d · outbound
This paper cites known-good.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design known-good
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.999342Z
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 e161c94b-b99f-46fb-90df-38db291771b3 · outbound
This paper cites A.15 Robustness of Figure 4: alignment, match definition, and inferential tests This appendix gives the full robustness battery for the oracle-aligned match-rate finding in §4.3.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design A.15 Robustness of Figure 4: alignment, match definition, and inferential tests This appendix gives the full robustness battery for the oracle-aligned match-rate finding in §4.3
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.993657Z
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 493bdb43-fdf3-4258-bb49-ab121992058e · outbound
This paper cites an unresolved cited work.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Unresolved cited work
Reference 29
- Resolution
- unresolved
- raw_fallback, observed 2026-05-19T15:52:38.991676Z
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 21760784-1ab0-492c-9988-38325e2d6c39 · outbound
This paper cites domain-aware’s prior matches the RCT-confirmed mechanism.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design domain-aware’s prior matches the RCT-confirmed mechanism
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.995696Z
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 f8bedd77-a901-4d1c-ba1b-7db44488141b · outbound
This paper cites A.17 Threshold sensitivity of the audit’s main result The audit selects 6 literature-divergent biology tasks using two gap criteria connected by an OR: (R)top-1 vs.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design A.17 Threshold sensitivity of the audit’s main result The audit selects 6 literature-divergent biology tasks using two gap criteria connected by an OR: (R)top-1 vs
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.986533Z
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 27dfe25f-6af0-4c3b-a7f8-63fb2735d900 · outbound
This paper cites literature-typical and best-result diverge by a meaningful margin.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design literature-typical and best-result diverge by a meaningful margin
Reference 32
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-19T15:52:38.984285Z
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 a7040760-9283-4b7d-b45c-54bf6e4ae5c0 · outbound
This paper cites domain-agnostic minus domain-aware.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design domain-agnostic minus domain-aware
Reference 33
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-19T15:52:38.980650Z
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 d41a908a-0de6-4e8c-b05f-e21a9c50be38 · outbound
This paper cites an unresolved cited work.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Unresolved cited work
Reference 34
- Resolution
- unresolved
- raw_fallback, observed 2026-05-19T15:52:38.982469Z
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 f5562413-fe58-412f-af88-0900c28d764c · outbound
This paper cites an unresolved cited work.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Unresolved cited work
Reference 35
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-19T15:52:38.988269Z
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 c52728a9-8f27-4904-9fc3-2dd0e883dc42 · outbound
This paper cites an unresolved cited work.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Unresolved cited work
Reference 36
- Resolution
- unresolved
- raw_fallback, observed 2026-05-19T15:52:38.975338Z
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 dc820085-b111-4363-8a25-63d694055bf3 · outbound
This paper cites Bottom row: domain-agnostic.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Bottom row: domain-agnostic
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.978869Z
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 8ee2c146-d29d-45df-a3a2-c8300bd4833a · outbound
This paper cites GP-UCB on biology under thedomain-agnosticcondition.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design GP-UCB on biology under thedomain-agnosticcondition
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.977127Z
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 b131d0ea-b6cc-451a-b092-266acad0f02c · outbound
This paper cites fall back to common options.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design fall back to common options
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.989983Z
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 76a29c78-051a-4d53-838a-05832fbd1800 · outbound
This paper cites Oracle models are derived predictors trained on these data, released alongside the benchmark for reproducibility.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Oracle models are derived predictors trained on these data, released alongside the benchmark for reproducibility
Reference 40
- Resolution
- verified exact
- doi, observed 2026-05-19T15:52:37.965048Z
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 f8a61c0f-4a65-4baa-96ab-c1ffd58b532d · outbound
This paper cites Offline GRPO with KL penalty 𝛽=0.1, group size 8, learning rate 5 × 10−6, 2 epochs over the fixed trajectory pool.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Offline GRPO with KL penalty 𝛽=0.1, group size 8, learning rate 5 × 10−6, 2 epochs over the fixed trajectory pool
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.965819Z
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 3a152dbc-7de6-42ae-b2d8-4957d8f33a28 · outbound
This paper cites trainable property.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design trainable property
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.973338Z
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 aff0ffc9-b847-40fa-bccd-7977240d7171 · outbound
This paper cites persisting with 47 Pareto.ai LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design May 2026 similar or domain-typical designs despite weak or stagnant outcomes.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design persisting with 47 Pareto.ai LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design May 2026 similar or domain-typical designs despite weak or stagnant outcomes
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.963578Z
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 62dd09dd-052e-48bf-93d9-079de9b7490e · outbound
This paper cites A couple did show quite firm anchoring, persisting with changing one tiny thing that clearly wasn’t working.
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design A couple did show quite firm anchoring, persisting with changing one tiny thing that clearly wasn’t working
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.971581Z
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 dd25b1d5-1d36-4a05-8c0c-2642ef900988 · outbound
This paper cites Fleiss’𝜅= 0.33across the three raters (fair agreement, supporting evidence, not confirmatory).
LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design Fleiss’𝜅= 0.33across the three raters (fair agreement, supporting evidence, not confirmatory)
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-19T15:52:38.969689Z
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 220371d5-9ce2-4ba8-868b-da4c7c863555 · inbound
ArchEval: Measuring AI Agents as Computer Architects cites this paper.
ArchEval: Measuring AI Agents as Computer Architects LEAP: Trajectory-Level Evaluation of LLMs in Iterative Scientific Design
Reference 55
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T01:16:50.927415Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.