Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis | Paper Citation Record

Observation 04221efb-5823-40a6-ac9b-06686a1509a9 · outbound

This paper cites Agentada: Skill-adaptive data analytics for tailored insight discovery,.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Agentada: Skill-adaptive data analytics for tailored insight discovery,

Reference 1

Resolution: malformed identifier; arxiv_id, observed 2026-07-01T09:15:43.472687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a4c258f2-9c22-4818-a4c0-450d4166aa24 · outbound

This paper cites EvoSkill: Automated Skill Discovery for Multi-Agent Systems.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis EvoSkill: Automated Skill Discovery for Multi-Agent Systems

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.534852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ca99bf98-9267-4d83-ba65-92584c4ca17e · outbound

This paper cites Qwen3-VL Technical Report.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Qwen3-VL Technical Report

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T09:15:42.516344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2b300862-21fc-4fb9-8244-2e13b2c5b539 · outbound

This paper cites arXiv preprint arXiv:2505.15277 , year=.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis arXiv preprint arXiv:2505.15277 , year=

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.528914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9e80571b-8446-4f30-83e7-a8d00b871f21 · outbound

This paper cites SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.581077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1e9fc329-0652-49ec-9358-1e5fabf1c507 · outbound

This paper cites Seed-prover 1.5: Mastering undergraduate-level theorem proving via learning from experience.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Seed-prover 1.5: Mastering undergraduate-level theorem proving via learning from experience

Reference 6

Resolution: malformed identifier; arxiv_id, observed 2026-07-01T09:15:43.485910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 632ea8bd-29c8-49ac-97e7-4008e83f0c07 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.061398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 167e743e-6fdf-4bc1-b320-cd0bdc9c06c0 · outbound

This paper cites Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.723416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 88d72abf-3384-404e-b476-96462387ce6c · outbound

This paper cites AI4Research: A Survey of Artificial Intelligence for Scientific Research.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis AI4Research: A Survey of Artificial Intelligence for Scientific Research

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.666393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 58c78b30-5362-4402-aff4-1ed83c6c3da8 · outbound

This paper cites Baker, Benjamin Burns, Daniel Adu-Ampratwum, Xuhui Huang, Xia Ning, Song Gao, Yu Su, and Huan Sun.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Baker, Benjamin Burns, Daniel Adu-Ampratwum, Xuhui Huang, Xia Ning, Song Gao, Yu Su, and Huan Sun

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.043057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation de051dd9-7b10-40aa-a562-6eb6a2dd5cf6 · outbound

This paper cites Process Reinforcement through Implicit Rewards.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Process Reinforcement through Implicit Rewards

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:43.532637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0d6bb89a-1590-4031-bd7a-ef1e53a7fcfa · outbound

This paper cites DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T09:15:42.754077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b4b8a05e-b80a-47b5-808c-bfb78a872248 · outbound

This paper cites Fapo: flawed-aware policy optimization for efficient and reliable reasoning.arXiv preprint arXiv:2510.22543, 2025.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Fapo: flawed-aware policy optimization for efficient and reliable reasoning.arXiv preprint arXiv:2510.22543, 2025

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.512191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cc6d35dd-12d6-43cc-b596-4dbad5863ca8 · outbound

This paper cites ReTool: Reinforcement Learning for Strategic Tool Use in LLMs.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.708792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1db18f53-3398-42d7-af9a-c5717a01dcdc · outbound

This paper cites When agents go astray: Course-correcting swe agents with prms.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis When agents go astray: Course-correcting swe agents with prms

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.572980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5f751d25-fe37-4468-b4c9-1bb9bc2be9d6 · outbound

This paper cites Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering

Reference 17

Resolution: malformed identifier; arxiv_id, observed 2026-07-01T09:15:43.498711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 29b0c001-ade0-4254-b0dc-c1717fdacd20 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.055602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ebed5867-e908-4387-a68c-e93145edd1a7 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.037072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d8847d2e-2332-4d5f-ba21-9f30ce13de62 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.067458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 45978254-4fc1-4529-a623-ee5a6d5ac4d4 · outbound

This paper cites Process reward models that think.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Process reward models that think

Reference 21

Resolution: malformed identifier; arxiv_id, observed 2026-07-01T09:15:43.506903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 536b63fb-9b77-44bf-9326-2554433ed828 · outbound

This paper cites ToolPRMBench: Evaluating and advancing process reward models for tool-using agents.arXiv preprint arXiv:2601.12294, 2026.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis ToolPRMBench: Evaluating and advancing process reward models for tool-using agents.arXiv preprint arXiv:2601.12294, 2026

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:43.479454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation aeb8dd15-f250-4183-812b-446367310ee5 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.053112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8f4f06cf-fbf0-4e17-8c8e-9a6a6844f1da · outbound

This paper cites AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.713304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3cb5b5c3-a91e-459e-829b-6ecfaf4c006b · outbound

This paper cites Pan, Guilin Qi, Haofen Wang, and Huajun Chen.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Pan, Guilin Qi, Haofen Wang, and Huajun Chen

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.057476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 680b7df3-45be-4e58-9520-5e14fc41cbf8 · outbound

This paper cites SkillNet: Create, Evaluate, and Connect AI Skills.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis SkillNet: Create, Evaluate, and Connect AI Skills

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-08-20T02:23:33.197848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 871796f6-94c6-44d5-ba49-41c3e4c5b55c · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.079475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 57300735-99e4-4ec8-b789-8bae6a35cfa7 · outbound

This paper cites ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.750478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3b38060d-072b-466c-b341-4eeb9f518978 · outbound

This paper cites Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:43.492180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5e22b3f6-27c3-4386-bd33-e9534df24371 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.049164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 68e58845-f2b2-4802-98ae-12ea66279c77 · outbound

This paper cites Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:43.537267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 739956c8-f5c8-44c1-82c1-7745c66a4774 · outbound

This paper cites Agentic reinforcement learning with implicit step rewards.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Agentic reinforcement learning with implicit step rewards

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.594739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 406fb051-072e-40bc-9079-5e1e5395904d · outbound

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

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.628606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation be265101-3e63-4e4d-a8e6-64e85a450f32 · outbound

This paper cites Towards Robust Mathematical Reasoning.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Towards Robust Mathematical Reasoning

Reference 35

Resolution: verified exact; doi, observed 2026-07-01T09:15:42.746976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9fbcbca2-acb1-45f1-ba44-037e88ac5006 · outbound

This paper cites Insightpilot: An llm-empowered automated data exploration system,.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Insightpilot: An llm-empowered automated data exploration system,

Reference 36

Resolution: verified exact; doi, observed 2026-07-01T09:15:42.519097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9730ce43-cab5-435d-8815-b11b1e3b32b4 · outbound

This paper cites Ds-star: Data science agent via iterative planning and verification.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Ds-star: Data science agent via iterative planning and verification

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.568946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7d89306a-b730-41bf-b74a-b088bb7d9b09 · outbound

This paper cites Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.739992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 060804ef-25f9-400f-a851-f0d640f71216 · outbound

This paper cites Dsgym: A holistic framework for evaluating and training data science agents.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Dsgym: A holistic framework for evaluating and training data science agents

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:43.543782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 249e9a29-2541-4a6b-b2e7-967ac74005c3 · outbound

This paper cites Datacross: A unified benchmark and agent framework for cross-modal heterogeneous data analysis,.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Datacross: A unified benchmark and agent framework for cross-modal heterogeneous data analysis,

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:43.525540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 36e5f06e-f2b6-4886-a8a2-049aad7307dc · outbound

This paper cites ToolRL: Reward is All Tool Learning Needs.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis ToolRL: Reward is All Tool Learning Needs

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.719608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 57ada28a-5d5e-4664-ba81-170bb5138306 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.047194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ceea8b4b-1f0d-4b28-831f-00fa6f1e2dfa · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.051269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e743c5fc-3b1c-456d-83f0-bd335222f838 · outbound

This paper cites CoRR , volume =.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis CoRR , volume =

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T09:15:42.683723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e4ab68e8-445e-48e5-8ab6-d311e3d6fd40 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:43.512184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1d8e9d55-7fd9-402c-9a5c-20293dec0e12 · outbound

This paper cites DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.678042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e002fea5-d400-4223-8c34-3d839ad5b539 · outbound

This paper cites Agent Laboratory: Using LLM Agents as Research Assistants.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Agent Laboratory: Using LLM Agents as Research Assistants

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.694366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0950b03a-2d39-4017-9f4d-dd953a79c38b · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.059419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a39739d6-d6c2-46cf-bc7b-ddb29ccff3e0 · outbound

This paper cites Deepseekmath-v2: Towards self-verifiable mathematical reasoning.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Deepseekmath-v2: Towards self-verifiable mathematical reasoning

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.701067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 039d2c1e-99e5-4bd4-8dd6-f1ab7fce99ea · outbound

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

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 50

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T09:15:42.757805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 75263ab1-b70c-4e1e-8407-9e3a8f58aca5 · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Hybridflow: A flexible and efficient rlhf framework

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T09:15:42.647142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2e307484-7f7a-40ce-867f-5a78bb24adcf · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 52

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T09:15:42.652362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9821ef54-ff80-4460-93c4-1f828fcd5ba6 · outbound

This paper cites AgenticData: An Agentic Data Analytics System for Heterogeneous Data.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis AgenticData: An Agentic Data Analytics System for Heterogeneous Data

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-07-17T01:20:37.666847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d0bd99ce-3e56-44f7-97ce-d194dc776e5b · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.065794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5756367a-ff06-4a04-a31c-00ae903f635f · outbound

This paper cites Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Reference 56

Resolution: verified exact; doi, observed 2026-07-01T09:15:42.760850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1e16ea8c-ab00-401a-88ba-ba298b405165 · outbound

This paper cites Large language model-based data science agent: A survey.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Large language model-based data science agent: A survey

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.622993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 63a72749-a364-4bd9-b5a4-d38d48ee8436 · outbound

This paper cites Smartsearch: Process reward-guided query refinement for search agents.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Smartsearch: Process reward-guided query refinement for search agents

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:43.549075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0b6cbba3-a225-4523-9ace-65b8c110f1fb · outbound

This paper cites Tablebench: a comprehensive and complex benchmark for table question answering.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Tablebench: a comprehensive and complex benchmark for table question answering

Reference 59

Resolution: verified exact; doi, observed 2026-07-01T09:15:42.575932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5c3ebbb0-3d3f-4a0b-83fb-db82db24e525 · outbound

This paper cites Agentprm: Process reward models for llm agents via step-wise promise and progress.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Agentprm: Process reward models for llm agents via step-wise promise and progress

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.589769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f4bb0a2b-f177-4c3a-8229-8ada4b1d931b · outbound

This paper cites DAgent: A Relational Database-Driven Data Analysis Report Generation Agent.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis DAgent: A Relational Database-Driven Data Analysis Report Generation Agent

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.564141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7fbeaf8b-0a38-4630-b2c9-a4327faffc4e · outbound

This paper cites Qwen3 Technical Report.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Qwen3 Technical Report

Reference 62

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T09:15:42.617087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 40bbb88e-7111-4730-b08b-f608d164b66f · outbound

This paper cites Matplotagent: Method and evaluation for llm-based agentic scientific data visualization.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Matplotagent: Method and evaluation for llm-based agentic scientific data visualization

Reference 63

Resolution: verified exact; doi, observed 2026-07-01T09:15:42.601822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6882a4b0-ab4b-46a4-a60f-584796228353 · outbound

This paper cites Narasimhan, and Yuan Cao.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Narasimhan, and Yuan Cao

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.077646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0346075b-6d70-43fa-a58c-d7813585ebc8 · outbound

This paper cites Datawiseagent: A notebook-centric llm agent framework for adaptive and robust data science automation, 2025.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Datawiseagent: A notebook-centric llm agent framework for adaptive and robust data science automation, 2025

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.640522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d06995e0-ffee-4da7-a255-7bdbecd0835a · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 66

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.545950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 950d63a7-e216-4129-83c7-b56c7987b6c2 · outbound

This paper cites Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment

Reference 67

Resolution: malformed identifier; doi_truncated, observed 2026-07-01T09:15:42.597957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4038613c-561c-4357-8e8e-3ea4ff831abf · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.073560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0c8e829f-d263-459c-8456-1a57f276ee8a · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.069295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6492ac67-5984-4838-b836-64f2a497a177 · outbound

This paper cites Funprm: Function-as-step process reward model with meta reward correction for code generation.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Funprm: Function-as-step process reward model with meta reward correction for code generation

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:43.467126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 97f51736-475a-48c9-9558-14b2f4c07eca · outbound

This paper cites arXiv preprint arXiv:2510.16872 , year=.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis arXiv preprint arXiv:2510.16872 , year=

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.744162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c2118154-7fed-49cf-a0ab-69655148297f · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.038949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ada35c39-b4ec-4ff9-b4b5-ac764dec5d7e · outbound

This paper cites Deep Research: A Survey of Autonomous Research Agents.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Deep Research: A Survey of Autonomous Research Agents

Reference 73

Resolution: malformed identifier; arxiv_id, observed 2026-07-01T09:15:43.520155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a73f2566-3e57-42f3-8903-47580c5522f5 · outbound

This paper cites Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.541013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 368d7af3-b2ff-49d8-a678-26f9c0049933 · outbound

This paper cites Reward- sql: Boosting text-to-sql via stepwise reasoning and process-supervised rewards.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Reward- sql: Boosting text-to-sql via stepwise reasoning and process-supervised rewards

Reference 75

Resolution: malformed identifier; arxiv_id, observed 2026-07-01T09:15:43.459871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7fbca742-558c-42a0-a846-f0446e49ee36 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.071375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 55fb33bd-8353-4aa3-9d71-e11beff6a47a · outbound

This paper cites GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.607003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 83494e52-02e6-4d5a-b191-1887d0b2bf9c · outbound

This paper cites SWIFT: A scalable lightweight infrastructure for fine-tuning.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis SWIFT: A scalable lightweight infrastructure for fine-tuning

Reference 78

Resolution: verified exact; doi, observed 2026-07-01T09:15:42.611300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d58d4ea6-070a-4d41-826e-141868c78f62 · outbound

This paper cites A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models

Reference 79

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.558536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c0b5e993-7455-47ca-96c1-5d52ded1811c · outbound

This paper cites Xing, Hao Zhang, Joseph E.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Xing, Hao Zhang, Joseph E

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.031405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 803ce4e4-ea78-47c6-81d5-ef00bdd8bfa7 · outbound

This paper cites Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

Reference 81

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:15:42.633669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6386e25e-a202-477f-8654-4f1c13e5276f · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 82

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.035161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3b072f25-056b-4621-91a6-8f124766d2f0 · outbound

This paper cites A survey of data agents: Emerging paradigm or overstated hype?CoRR, abs/2510.23587.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis A survey of data agents: Emerging paradigm or overstated hype?CoRR, abs/2510.23587

Reference 83

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T09:15:43.452454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7c0eb2c7-21fa-496f-9192-d12ff07ab845 · outbound

This paper cites Why do open-source llms struggle with data analysis? A systematic empirical study,.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Why do open-source llms struggle with data analysis? A systematic empirical study,

Reference 84

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.733122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2d69ff33-ea00-43ec-8ac5-0fb070562788 · outbound

This paper cites Tattoo: Tool-grounded thinking prm for test-time scaling in tabular reasoning.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Tattoo: Tool-grounded thinking prm for test-time scaling in tabular reasoning

Reference 85

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.552497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c1915613-ff5e-4de7-b937-acd3e5209d56 · outbound

This paper cites Reasonflux-prm: Trajectory-aware prms for long chain-of-thought reasoning in llms.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Reasonflux-prm: Trajectory-aware prms for long chain-of-thought reasoning in llms

Reference 86

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:15:42.671429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ab82c19d-9723-45d5-8922-cedaa43140d1 · outbound

This paper cites We sampled 100 tasks in DABench and TableBench, respectively, and measured the correlation between the model judge and human experts.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis We sampled 100 tasks in DABench and TableBench, respectively, and measured the correlation between the model judge and human experts

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.063725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f28f77b1-89ab-4506-b3fb-f5ad258a9425 · outbound

This paper cites What is the calculation formula for the cost?.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis What is the calculation formula for the cost?

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.029242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6dabe059-e969-40c1-9802-7d13fe60e321 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 90

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.033505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 49477146-1075-4ff2-94c9-416e18f40f4b · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 92

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.044876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ecaf8eb9-cc49-4595-b76d-fc83fff582ab · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 97

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.027264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c130081e-b420-4b27-9930-470c0511d3ae · outbound

This paper cites You should first an- alyze the correctness of the paragraph in ’<reason- ing></reasoning>’ part, then write code to verify your analysis in ’<code></code>’ part.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis You should first an- alyze the correctness of the paragraph in ’<reason- ing></reasoning>’ part, then write code to verify your analysis in ’<code></code>’ part

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.022366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9f6a4332-aeee-4678-a130-472e73b6c858 · outbound

This paper cites Conference acronym ’XX, June 03–05, 2018, Woodstock, NY Qiu et al.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Conference acronym ’XX, June 03–05, 2018, Woodstock, NY Qiu et al

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.040876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 27b9a2dc-342f-4f1a-bcd3-4586c5f048e1 · outbound

This paper cites You can use code to interact with the data files and verify the correctness of the paragraph.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis You can use code to interact with the data files and verify the correctness of the paragraph

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.017970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e0ea7d92-2477-4645-810d-5272d6860e4c · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 101

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.075738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ad80b5a5-aaf6-4aef-a12e-1ed31227b66d · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 102

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.020084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 336ce17f-b708-4b71-b217-6d96702f4b25 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 103

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.009511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ca62a823-b5f0-42e3-a507-d9a2e0ea123e · outbound

This paper cites However, if there is an exception in the code of this paragraph, the variables in this code snippet will not be retained.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis However, if there is an exception in the code of this paragraph, the variables in this code snippet will not be retained

Reference 104

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.015740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8353af1a-8e81-49b8-9d10-feb8a2e98081 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 105

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.011710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4cd6e6a2-c676-48c1-95ca-89b479c25545 · outbound

This paper cites an unresolved cited work.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis Unresolved cited work

Reference 106

Resolution: unresolved; raw_fallback, observed 2026-07-06T11:52:23.013453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4e21b327-995f-4c2b-8ae2-58851f125b37 · outbound

This paper cites # Format Example - Code Format: <reasoning> Your reasoning here, step by step, explaining your thought process and how you will verify the paragraph.

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis # Format Example - Code Format: <reasoning> Your reasoning here, step by step, explaining your thought process and how you will verify the paragraph

Reference 107

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T11:52:23.007449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers