Paper Citation Record · LEDGER

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks

As of 5 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2604.05912.

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

pith.paper-citation-record.v1
2604.05912 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T19:49:32.983778Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-31T16:17:41.453945Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

39 of 39 outbound references displayed

verified exact20
verified fuzzy8
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch9

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 27b8ec59-7268-40d3-bbbd-319a1c00ef7a · outbound

This paper cites Inspect AI: Framework for Large Language Model Evaluations.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Inspect AI: Framework for Large Language Model Evaluations

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T03:50:35.199194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0ad29743-2058-41f9-8555-8b08a60abace · outbound

This paper cites Labor market impacts of AI : A new measure and early evidence.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Labor market impacts of AI : A new measure and early evidence

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T03:50:35.204067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cb6530a0-b053-4a8b-b3d5-3e4d2d0650e7 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL) , year=.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL) , year=

Reference 3

Resolution: metadata mismatch; doi, observed 2026-05-10T19:50:45.998340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1485e507-b83d-48cb-9c8d-5c7be3e37f64 · outbound

This paper cites MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:30:49.944041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2f741ddf-e515-408f-8461-e1bac4c90a6d · outbound

This paper cites FinQA: A dataset of numerical reasoning over financial data.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks FinQA: A dataset of numerical reasoning over financial data

Reference 5

Resolution: verified exact; doi, observed 2026-05-10T19:50:46.066587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9f3e3588-bfc7-42c5-9c5e-76958fc665ff · outbound

This paper cites C onv F in QA : Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks C onv F in QA : Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering

Reference 6

Resolution: verified exact; doi, observed 2026-05-10T19:50:46.078163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 20bd82eb-43f9-4303-a8c1-eb40cf2202ab · outbound

This paper cites Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T15:13:25.541930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e789e319-f3bf-4e93-a9e5-8834b792ae40 · outbound

This paper cites Davenport and Laks Srinivasan.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Davenport and Laks Srinivasan

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T03:50:35.176667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3430b22c-9387-4d1b-aa2f-9ea15ede2e09 · outbound

This paper cites Longcli-bench: A preliminary benchmark and study for long-horizon agentic programming in command-line interfaces.arXiv preprint.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Longcli-bench: A preliminary benchmark and study for long-horizon agentic programming in command-line interfaces.arXiv preprint

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:30:49.838273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7cf33c2a-85d3-4425-b035-6ae2ad1773dc · outbound

This paper cites Gao et al.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Gao et al

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T22:30:49.883880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 66a2d92c-6900-4054-89cf-49cf3a1d69bc · outbound

This paper cites Evaluating the impact of AI on the labor market: Current state of affairs.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Evaluating the impact of AI on the labor market: Current state of affairs

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T03:50:35.185405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bc688bc4-21f7-4dc8-bbcb-ff24fe0e4315 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Measuring Massive Multitask Language Understanding

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-10T22:30:49.963676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0b2d9507-f9a0-4288-a45a-dc4cd819dd41 · outbound

This paper cites FinanceBench: A New Benchmark for Financial Question Answering.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks FinanceBench: A New Benchmark for Financial Question Answering

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:01:13.018607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation eaaa449e-6481-4511-96a6-2c852df92fd2 · outbound

This paper cites SWE-bench: Can Language Models Resolve Real-World GitHub Issues?.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T22:30:49.746099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f7a18eae-e580-4111-8959-740dc9f57aaa · outbound

This paper cites Prometheus: Inducing Fine-grained Evaluation Capability in Language Models.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Prometheus: Inducing Fine-grained Evaluation Capability in Language Models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:30:49.695358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f62ff757-110d-4836-a8a1-923f24786878 · outbound

This paper cites B iz B ench: A quantitative reasoning benchmark for business and finance.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks B iz B ench: A quantitative reasoning benchmark for business and finance

Reference 16

Resolution: verified exact; doi, observed 2026-05-10T19:50:46.042984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8d4a7442-5fed-4f0d-a760-7d378bf246a3 · outbound

This paper cites Measuring ai ability to complete long tasks.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Measuring ai ability to complete long tasks

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T03:50:35.193946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6a8bcd1c-e5cf-4a8f-97ae-055f578ab94e · outbound

This paper cites Meta-Harness: End-to-End Optimization of Model Harnesses.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Meta-Harness: End-to-End Optimization of Model Harnesses

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-13T16:15:58.398964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 28406ea9-95b2-4866-a5fe-18a370fa7e5e · outbound

This paper cites AgentBench: Evaluating LLMs as Agents.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks AgentBench: Evaluating LLMs as Agents

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:40:05.312349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b9e1f01f-d84a-4e52-9043-b3e0f21deeeb · outbound

This paper cites Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Reference 20

Resolution: metadata mismatch; doi, observed 2026-05-10T19:50:46.060035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 660a3ea2-b219-4467-9689-70a487698a14 · outbound

This paper cites SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:30:49.708132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fffe4da9-315c-47f5-86d5-9226be4a06de · outbound

This paper cites GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T11:11:04.750341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 147781df-7136-458e-a332-644f9f4fa9da · outbound

This paper cites D oc F in QA : A long-context financial reasoning dataset.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks D oc F in QA : A long-context financial reasoning dataset

Reference 23

Resolution: verified exact; doi, observed 2026-05-10T19:50:46.024354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bc8f48b7-e655-4f58-a981-4d46c9f41b8b · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:00:34.729655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 08464753-0b72-43a9-ad68-c6b1d4f6c4b3 · outbound

This paper cites HCAST: Human-Calibrated Autonomy Software Tasks.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks HCAST: Human-Calibrated Autonomy Software Tasks

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:30:49.847820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 583d29b3-6e87-4952-8985-4c95fad2f806 · outbound

This paper cites How will AI affect the US labor market? Technical report, Goldman Sachs Research, March 2026.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks How will AI affect the US labor market? Technical report, Goldman Sachs Research, March 2026

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T03:50:35.167911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0c175797-94bc-4917-bc83-75eac0c795d4 · outbound

This paper cites Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:26:25.883762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1844847c-4cc4-4058-874a-042bf0a9fb6a · outbound

This paper cites Large Language Models for Spreadsheets: Benchmarking Progress and Evaluating Performance with FLARE.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Large Language Models for Spreadsheets: Benchmarking Progress and Evaluating Performance with FLARE

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:30:49.923397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f2df77a9-3bb1-4135-9856-74ceba69deca · outbound

This paper cites 2601.14242 , archivePrefix =.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks 2601.14242 , archivePrefix =

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:30:49.874302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 40057c14-2a2d-40d2-ba8a-dc9ed847dd4d · outbound

This paper cites OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:19:32.642608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 31a9ab78-dfc9-4a91-90a1-43dad97f5aa7 · outbound

This paper cites ISBN 979-8-89176-256-5.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks ISBN 979-8-89176-256-5

Reference 31

Resolution: metadata mismatch; doi, observed 2026-05-10T19:50:46.055062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a63aff80-9c14-4983-bfb8-3f64c7b6f84e · outbound

This paper cites Financemath: Knowledge-intensive math reasoning in finance domains.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Financemath: Knowledge-intensive math reasoning in finance domains

Reference 32

Resolution: verified exact; doi, observed 2026-05-10T19:50:46.028819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a7b1fbe7-ac2d-4b73-bffe-f2b14702a5e6 · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T22:30:49.950901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c504a3ef-0f9a-4533-98ac-6437d2fee2a2 · outbound

This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T22:30:49.734825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8654a1c6-8b0b-4b3d-b993-1216f0162ad3 · outbound

This paper cites TAT-QA: A question answering benchmark on a hybrid of tabular and textual content in finance.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks TAT-QA: A question answering benchmark on a hybrid of tabular and textual content in finance

Reference 35

Resolution: verified exact; doi, observed 2026-05-10T19:50:46.072915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9e0ddc88-f8ca-467d-beac-16b30e74a51f · outbound

This paper cites write newline.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks write newline

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T03:50:35.189648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0a3638ba-55d5-492f-9219-40fe51d8186a · outbound

This paper cites @esa (Ref.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks @esa (Ref

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T03:50:35.180903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 80cae2f5-28f6-4edf-bd67-738b7add3335 · outbound

This paper cites an unresolved cited work.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-05-16T03:50:35.172424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f186c566-34da-4e9d-89d2-dc0e0bdbd54e · outbound

This paper cites (QGT+  o/߸ ;fQ Zt鐒gvZxG*J Y ȮY! dZs (HE E 2 n=#R.

FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks (QGT+  o/߸ ;fQ Zt鐒gvZxG*J Y ȮY! dZs (HE E 2 n=#R

Reference 39

Resolution: malformed identifier; arxiv_id, observed 2026-05-10T22:30:49.818607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation 68c04a99-83a5-4c0c-9c13-019ee500a61b · inbound

GAUGE: Grading Agent-Built Financial Models Without a Golden Answer cites this paper.

GAUGE: Grading Agent-Built Financial Models Without a Golden Answer FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T16:17:41.453945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.