Paper Citation Record · LEDGER

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis

As of 20 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2607.23524.

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

pith.paper-citation-record.v1
2607.23524 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-30T20:14:27.190982Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy0
unresolved43
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 74356a47-79df-45fc-9808-040355014dc4 · outbound

This paper cites Ctrlsynth: Controllable image text synthesis for data-efficient multimodal learning.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Ctrlsynth: Controllable image text synthesis for data-efficient multimodal learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.040146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bfea83a-f191-47b2-aead-ede8009442cf · outbound

This paper cites Humanity's Last Exam.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Humanity's Last Exam

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.044398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a33cfbd1-a450-43ab-8947-935ec7112af6 · outbound

This paper cites xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.048298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b790e828-8dc2-4cfc-b130-19714ae5dddb · outbound

This paper cites Warner, Hugo Aerts, Thomas Hartvigsen, Jack Gallifant, and Danielle Bitterman.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Warner, Hugo Aerts, Thomas Hartvigsen, Jack Gallifant, and Danielle Bitterman

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.052595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6936641e-d34b-41e0-9f5c-8b226dd30646 · outbound

This paper cites BrowseComp-plus: A fair and disentangled evaluation benchmark for deep search agents.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis BrowseComp-plus: A fair and disentangled evaluation benchmark for deep search agents

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.056430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98b8e5dc-b851-431b-9783-2c9b01db877a · outbound

This paper cites Beyond itinerary planning—a real-world benchmark for multi-turn and tool-using travel tasks.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Beyond itinerary planning—a real-world benchmark for multi-turn and tool-using travel tasks

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.059953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9606314-c3e8-4356-8edc-2d8ee7e27a9a · outbound

This paper cites Evoclaw: Evaluating AI agents on continuous software evolution.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Evoclaw: Evaluating AI agents on continuous software evolution

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.063772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7a37de9-1dfb-42c2-8c26-d6a4a70f9052 · outbound

This paper cites CL-bench Life: Can Language Models Learn from Real-Life Context?.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis CL-bench Life: Can Language Models Learn from Real-Life Context?

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.067072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ee2a344-55d7-4232-b908-8944722d97c9 · outbound

This paper cites Cl-bench: A benchmark for context learning, 2026.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Cl-bench: A benchmark for context learning, 2026

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.070575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc6d0e05-82f5-4524-a750-d3622d8d312d · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis GLM-5: from Vibe Coding to Agentic Engineering

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.074405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1309e516-9b38-433c-86f7-73720ee40beb · outbound

This paper cites A Survey on LLM-as-a-Judge.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis A Survey on LLM-as-a-Judge

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.079004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baf45a2c-1b52-4408-b2ec-027554e43bf8 · outbound

This paper cites Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.082575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67809073-b637-4aa3-b4b5-125195e5427e · outbound

This paper cites Step-deepresearch technical report, 2025.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Step-deepresearch technical report, 2025

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.085995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca6fe653-6fae-4c92-86d4-6ba9a965f417 · outbound

This paper cites Building a foundational guardrail for general agentic systems via synthetic data.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Building a foundational guardrail for general agentic systems via synthetic data

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.089428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e599d424-db7a-4996-9d8b-1bad261fb6ad · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Livecodebench: Holistic and contamination free evaluation of large language models for code

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.092653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3865ae89-1c92-4560-9a0b-2c632ba1e514 · outbound

This paper cites DiningBench: A hierarchical multi-view benchmark for perception and reasoning in the dietary domain.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis DiningBench: A hierarchical multi-view benchmark for perception and reasoning in the dietary domain

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.095819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 744e131a-5217-4039-a5e6-956a3d53f02b · outbound

This paper cites Delegation to artificial intelligence can increase dishonest behaviour.Nature, 646(8083):126–134, 2025.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Delegation to artificial intelligence can increase dishonest behaviour.Nature, 646(8083):126–134, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.099086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bb7ab6d-abc3-459a-9c27-175c0721bcae · outbound

This paper cites Fact, fetch, and reason: A unified evaluation of retrieval-augmented generation.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Fact, fetch, and reason: A unified evaluation of retrieval-augmented generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.102492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3808e870-7df5-4940-ba46-6139be23fd5c · outbound

This paper cites Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.105709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca3df9d1-db3e-49a8-9576-8c044217b7b8 · outbound

This paper cites From generation to judgment: Opportunities and challenges of LLM-as-a-judge.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis From generation to judgment: Opportunities and challenges of LLM-as-a-judge

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.109123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bfb1fb4-55e5-4704-af5a-e5a7138abfa0 · outbound

This paper cites ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.112809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c56b9eb-8eae-4590-8a58-22140fdaaa71 · outbound

This paper cites Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.116279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd2aa2ed-b9d8-4a5d-96ba-ba0690f49b31 · outbound

This paper cites Search self-play: Pushing the frontier of agent capa- bility without supervision.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Search self-play: Pushing the frontier of agent capa- bility without supervision

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.119927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8e4598e-cae0-4f5a-af89-a14ed674c11b · outbound

This paper cites Natural emergent misalignment from reward hacking in production rl, 2025.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Natural emergent misalignment from reward hacking in production rl, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.123243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ae49936-7001-433f-9d85-71bd22f07b8f · outbound

This paper cites GAIA: a benchmark for general AI assistants.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis GAIA: a benchmark for general AI assistants

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.126589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89e830b6-80a7-45a9-9a44-be0716141eed · outbound

This paper cites SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.129868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3064de5-6a88-4b96-aed9-425db95ad455 · outbound

This paper cites Measuring and narrowing the compositionality gap in language models.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Measuring and narrowing the compositionality gap in language models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.133812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaf6f6d7-1150-4154-ae16-c678193021d0 · outbound

This paper cites an unresolved cited work.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.137126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de585401-04ad-46ea-8000-307e5d1dd140 · outbound

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

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.140592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6167796a-c09d-4e3a-99f3-c5d93100a9e3 · outbound

This paper cites an unresolved cited work.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.144214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a36df5b4-97eb-41ff-b87e-afe48b942868 · outbound

This paper cites Recent frontier models are reward hacking.https: //metr.org/blog/2025-06-05-recent-reward-hacking/, 06 2025.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Recent frontier models are reward hacking.https: //metr.org/blog/2025-06-05-recent-reward-hacking/, 06 2025

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.147216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36f4b86e-4434-4cf0-8053-b9a87323cca5 · outbound

This paper cites an unresolved cited work.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.150496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68da3a37-6708-4ea7-bb76-b05a72604935 · outbound

This paper cites Intelligent ai delegation, 2026.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Intelligent ai delegation, 2026

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.157756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ec3883-2ef7-445d-9668-fd58be1c164b · outbound

This paper cites Musique: Multihop questions via single-hop question composition.Transactions of the Association for Computational Linguistics, pages 539–554, 2022.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Musique: Multihop questions via single-hop question composition.Transactions of the Association for Computational Linguistics, pages 539–554, 2022

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.160818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8fa1edf-0b88-44c0-bd59-8e1534e64128 · outbound

This paper cites BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.164039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1bb90c3-9922-4f9a-a33e-2e7dbdebb68a · outbound

This paper cites Webwalker: Benchmarking LLMs in web traversal.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Webwalker: Benchmarking LLMs in web traversal

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.167619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 191948fc-b099-4ec8-b5bc-99445aadfcd8 · outbound

This paper cites TRIDENT: Enhancing large language model safety with tri-dimensional diversified red-teaming data synthesis.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis TRIDENT: Enhancing large language model safety with tri-dimensional diversified red-teaming data synthesis

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.170848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9373715-4e0a-4067-8aea-17c199b2000e · outbound

This paper cites HotpotQA:Adatasetfordiverse, explainablemulti-hopquestionanswering.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis HotpotQA:Adatasetfordiverse, explainablemulti-hopquestionanswering

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.173977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 301f922c-38eb-46b0-bdcf-ca1c4aff2778 · outbound

This paper cites {$\tau$}-bench: Abenchmark for \underline{T}ool-\underline{A}gent-\underline{U}ser interaction in real-world domains.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis {$\tau$}-bench: Abenchmark for \underline{T}ool-\underline{A}gent-\underline{U}ser interaction in real-world domains

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.177262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c74660fc-145b-48d1-b8e8-b33706b84d0f · outbound

This paper cites Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.180462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf3e6255-2365-461f-b852-414f44602768 · outbound

This paper cites Browsecomp-zh: Benchmarking web browsing ability of large language models in chinese,.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Browsecomp-zh: Benchmarking web browsing ability of large language models in chinese,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.183833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e145f54-3705-42c4-a43b-1ec0996ef37a · outbound

This paper cites synthetic document.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis synthetic document

Reference 42

Resolution: malformed identifier; no resolver link, observed 2026-07-30T20:14:27.190982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04f7f49f-8adc-4de5-952a-4bb22001ed24 · outbound

This paper cites BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.187351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf6821e1-1a8f-404e-8a09-fec3beaed373 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis Kimi K2: Open Agentic Intelligence

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-07-30T20:14:27.153936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.