Pith. sign in

Paper Citation Record · LEDGER

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery

As of 4 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 1 inbound Pith citation observation for arXiv:2604.19049.

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

pith.paper-citation-record.v1
2604.19049 v1

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T03:11:26.513954Z

measured 53 of 53 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T03:57:40.779886Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

52 of 52 outbound references displayed

  • verified exact31
  • verified fuzzy16
  • unresolved5
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b1baa61f-bcaa-48dc-9ba7-ccb6507be0fe · outbound

This paper cites Big Sleep: Real-world vulnerability discovery with large language models.Google Security Blog, November 2024.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Big Sleep: Real-world vulnerability discovery with large language models.Google Security Blog, November 2024

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.223321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:8bca3b53f3c5ba6726074119a70b8cf208e70376a793cd9b740598f9b69d2ad6

Observation 09446e36-3cee-413e-a507-706d358156c5 · outbound

This paper cites an unresolved cited work.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Unresolved cited work

Reference 2

Resolution
verified exact
doi, observed 2026-05-10T03:14:07.445517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:f1b686da38c83025871a04b32ef7480f66672872643a887d48cda80112a5fb88

Observation e670b15c-d4c2-4164-a710-578c5b3a773d · outbound

This paper cites an unresolved cited work.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Unresolved cited work

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.009819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:9ed58f2f5a6cce9df20de7c005ed41ebcc9defcb7a885c2cdeef9c68f8c8ff81

Observation 5843eabc-ea71-467b-a2fd-ae9d29310e13 · outbound

This paper cites Ullah, M.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Ullah, M

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.231487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:534813273b229985e173f09f6b56ce2501f1957cfc48d0c2cf38feeebd87d57d

Observation a8b20cd3-dce9-40e0-99bf-7f548bca1b36 · outbound

This paper cites AI-Assisted SAST: False Positive Rates in Production.semgrep.dev/blog.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery AI-Assisted SAST: False Positive Rates in Production.semgrep.dev/blog

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.234347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:329b54def164b9fd82fec200e2d89d20107b14f93ab2176eaa4f72738f7904d8

Observation 4c6a2bbe-dd9a-4b53-b536-124db93eb02c · outbound

This paper cites Stenberg.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Stenberg

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.237124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:4671b9e6ef94ab3165855a75d35ab97cacead522d7dde58dabb01ed15969f27e

Observation 9d1e0777-8649-4c0f-8dcb-f45113fcf1b7 · outbound

This paper cites Stenberg.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Stenberg

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.240244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:0037f370dee6a6ed300a432722b965e6d466c052123b46395d31bf58c011a495

Observation 8919fb46-25d2-45a2-a8cc-bd0c6f69be17 · outbound

This paper cites Improving Factuality and Reasoning in Language Models through Multiagent Debate.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Improving Factuality and Reasoning in Language Models through Multiagent Debate

Reference 8

Resolution
verified exact
arxiv_id, observed 2026-05-12T03:01:45.301651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:d2060652f0805f5d70795054b66747f0967970524ba6545d53dea8f81f2740d1

Observation eec13e0a-ce86-4de2-83b0-09d09b76aaad · outbound

This paper cites Khan et al.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Khan et al

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.243632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:357c2680f8bd511c7aadfddb42acafefbd182ac15864132e2b83ab2105758c4f

Observation a1de0ff6-556f-4627-90eb-c9ca883d7525 · outbound

This paper cites Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao

Reference 10

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:07.993577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:c7ef52c1f774be11e3337e72b79b3ddaa7f0a249d9af7989f0b79325b29155b5

Observation 64cb7e07-a1b7-4ed1-bd55-492193044231 · outbound

This paper cites Cross-context review: Improving LLM output quality by separating production and review sessions, 2026.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Cross-context review: Improving LLM output quality by separating production and review sessions, 2026

Reference 11

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.005338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:80cccda7f29a9ceff8efdc733e26f65ee3e62a190e9ba4743275a3859153dea2

Observation 9d32d695-0ff7-4218-92af-a2e1e3c8b743 · outbound

This paper cites an unresolved cited work.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Unresolved cited work

Reference 12

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:07.990971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:4ceedfb98681819f610a168850dda9b918fb82a6f566ddcd2036fd131f617ae1

Observation 5c91c1f3-35db-4fd0-8e68-5b5dd3052fde · outbound

This paper cites Automated Hypothesis Validation with Agentic Sequential Falsifications.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Automated Hypothesis Validation with Agentic Sequential Falsifications

Reference 13

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.000766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:1a6c278bda6219087fab5376addc11b1806993894b0ea1bf47421108a821a8fa

Observation d528fb9e-e094-487b-9f7a-2425d27b5377 · outbound

This paper cites Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers

Reference 14

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:07.988726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:690c3689382d13c730e951f9682024a6d815375531b30aa3d6cf9e96038af126

Observation 3c388206-18d1-4ea7-ac25-ec42c09af528 · outbound

This paper cites Widyasari, M.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Widyasari, M

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:07.984086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:e14367f40a7d9928e0b3d81e0f515140fe65499edccfe7f6afe41632603fe82a

Observation 9801c6ef-d0e0-4c69-950f-378956fc1684 · outbound

This paper cites Vlcek, J.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Vlcek, J

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.216553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:ec211913c871ead0b785918c9e32084783a0438e93c6b461e03d9f5956503923

Observation 9793672d-02bd-4570-9a12-348fd5a9cb27 · outbound

This paper cites IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities

Reference 17

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.003075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:bcff62de73db5f6aa7eeabf8a9829b66577c5d92413085a252b7fb7a26f53992

Observation 5e20b6e7-bda2-4c96-972d-a737afb1947c · outbound

This paper cites an unresolved cited work.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Unresolved cited work

Reference 18

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:07.996048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:7b42ea7aba852c061c81623dd1c83783d2e0895d48825a11cc5be4ee9544f1c5

Observation d5225054-48c8-43e6-9e1c-5f1123e8da6f · outbound

This paper cites Vulagent: Hypothesis- validation based multi-agent vulnerability detection.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Vulagent: Hypothesis- validation based multi-agent vulnerability detection

Reference 19

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.007620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:3b2a8b78ee80bf6461e9b63da82ed84ff15c582ebdfa86e96c2c222843bb8cb6

Observation 517fd2aa-21db-4743-aecd-5a8c8868ade6 · outbound

This paper cites Zero-Day Vulnerability Discovery with Frontier Models.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Zero-Day Vulnerability Discovery with Frontier Models

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.221029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:20bc93d3a579e360553dffaee50bab51e0a2ff42ea1c3605bcfc5ffe5f433552

Observation df1c2402-b26d-4658-9b15-7f99bad0f165 · outbound

This paper cites Codex Security: Now in Research Preview.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Codex Security: Now in Research Preview

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.226067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:3c8a3cb65085299ab0cb2240f1b9a1e1e6e6ee7b0fe385fa275599ee7bc62eff

Observation c398fa07-069a-4e1a-b9f2-b0b8bac6cabe · outbound

This paper cites Avizienis and J.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Avizienis and J

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.203901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:2518a0732f681b9de242cae102041d2493d5d03d175f02f1df428b1f4fe70898

Observation 1238e175-821e-43d2-9542-dd6a46addfe8 · outbound

This paper cites an unresolved cited work.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Unresolved cited work

Reference 23

Resolution
unresolved
raw_fallback, observed 2026-05-22T17:46:54.206058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:121fc6d63ac08059223fec986daf3de4e241a3ed7aac697e34426ec58c935000

Observation 3bc8d92e-fc6b-49b9-b97d-20a2e2ad9017 · outbound

This paper cites Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering

Reference 24

Resolution
verified exact
arxiv_id, observed 2026-06-30T02:15:37.354612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:d2f50a4d792122e37350d6a43fa2f64af5030bd051582ca06b3be1cf7aeedb8d

Observation 90cd9c72-6888-4f59-bf4c-54ed41a76670 · outbound

This paper cites Du et al.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Du et al

Reference 25

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:07.998386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:d6c74ce16bc19d5a692de5a39b08d6c5d004310719d6bfa090e2a6fa22cf05d4

Observation 06bea090-8291-4f10-a034-9545a84faf54 · outbound

This paper cites Kraidia, I.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Kraidia, I

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.207954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:b79c27d3be375b140549e91ddcc6f9032e03f0ef3ebaa176f783ae5e63fa1e93

Observation bd8ff47d-cc79-498e-8045-bc7e3502bfbc · outbound

This paper cites Claude Mythos Preview.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Claude Mythos Preview

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.246749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:c4edca1717d73607b2e3194d8e76e8a2189f1be67155bb1bc74da15534a3603c

Observation 00c97091-04fa-47c9-8be6-ae69d196e02a · outbound

This paper cites Project Glasswing: Securing Critical Software for the AI Era.anthropic.com, April 2026.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Project Glasswing: Securing Critical Software for the AI Era.anthropic.com, April 2026

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.212257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:193f4197054bd30ce401b5dcf7b7ff709d94731b0a364308debe700ab130809e

Observation 252a2fe1-4f9d-4b29-8eab-57ff90666b06 · outbound

This paper cites Trusted Access for the Next Era of Cyber Defense.openai.com, April 2026.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Trusted Access for the Next Era of Cyber Defense.openai.com, April 2026

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.214766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:4a8a926999e5a1df437b35a4ca9f28b3499c8c7d9c39b46ce54a8c196229cb8d

Observation 79dcebf4-a62d-460d-9652-0f3efaf5dd92 · outbound

This paper cites Correlated Errors in Large Language Models.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Correlated Errors in Large Language Models

Reference 30

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.026843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:5dcbcdd6ef3195fb2275df307a35ed31e6ddeb0458dd74e5e25b21203a0ed0e4

Observation 00d2f911-f47e-4cf8-9190-5b01582649c0 · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 31

Resolution
verified exact
arxiv_id, observed 2026-05-15T06:51:50.894684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:47e15e5ca96213b60d1dfa6fe890a4c2d9e4150088128cd21f4ef26d3efda723

Observation bb565363-ccb2-4e0f-be8f-cf4d6bcbb223 · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 32

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.024390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:0906716ea2f3138907211f409eef44232a328c96e4fb8aee99a6a6f6b8b876ad

Observation c4513758-b235-43f6-a2cc-950dbcb9e776 · outbound

This paper cites Linder, M.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Linder, M

Reference 33

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.029382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:6c1ecfa5628956b0f1c8a5a3858cbb5cbc1eff3faea263caea9a039d3b013595

Observation 482d4da3-b779-44cd-8a82-8cfad2cf71fd · outbound

This paper cites Buildingan AdversarialConsensus Engine: Multi-Agent LLMs for Automated Malware Analysis.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Buildingan AdversarialConsensus Engine: Multi-Agent LLMs for Automated Malware Analysis

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.218620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:74f4d27d9a7dfeb4e62338b22ad4cb9a9c5a0742d0dfdf0bc34f456ea897f581

Observation 7989332e-9ff9-4fc1-89ab-3e340bfed179 · outbound

This paper cites Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?

Reference 35

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.036447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:cb753701496903736e50a659ebc644f3cc30c6bdc7794c8ab076c406fce5ed33

Observation 0467758d-6770-4d80-92d1-43d2df0879ea · outbound

This paper cites Mixture-of-Agents Enhances Large Language Model Capabilities.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Mixture-of-Agents Enhances Large Language Model Capabilities

Reference 36

Resolution
verified exact
arxiv_id, observed 2026-05-16T19:29:34.516338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:686000aa5253d1c1039de06ab692a4c3060e64f8ae7861a834384a91b88e3031

Observation 80c47493-125b-46ff-8a2c-800f737d6ca1 · outbound

This paper cites an unresolved cited work.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Unresolved cited work

Reference 37

Resolution
unresolved
raw_fallback, observed 2026-05-22T17:46:54.198130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:f95c9eee90d6550059ed297f8eb475ad86a1248903523d813f3e02fb464f7db3

Observation 5dbbd930-0f26-4ac1-8ca8-3711afc276c5 · outbound

This paper cites Franceschi-Bicchierai.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Franceschi-Bicchierai

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T17:46:54.200035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:3fdcbfb0f9cf2374d932ba01281d74b12d0bfbcb996e4e349229854264b6de63

Observation b41d30fd-40ed-4be3-a1bf-56d1b87a33a3 · outbound

This paper cites an unresolved cited work.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Unresolved cited work

Reference 39

Resolution
unresolved
raw_fallback, observed 2026-05-22T17:46:54.201932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:1640a514c0957ab612146529098fb777c82dfbd890893c056847e5713562f72b

Observation b8d7666d-edc9-41ba-bb3c-fbf0afc1246a · outbound

This paper cites RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing

Reference 40

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.034118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:7927372a6073661ded7b256709d26604e374d137803b927e91e5411a3ed1b333

Observation 8b01eabc-265d-416e-887e-15fe3990d15f · outbound

This paper cites an unresolved cited work.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Unresolved cited work

Reference 41

Resolution
unresolved
raw_fallback, observed 2026-05-22T17:46:54.228778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:01f3bed4fbefeef83465a56c70b90b6f4f61ec3c283282db93bb1007ba481174

Observation 1250e481-023b-4266-9c7e-c53eb1f79f6a · outbound

This paper cites an unresolved cited work.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-05-22T17:46:54.209757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:94938524baace163c6b528df4b0e7724d08c891f6614d084fecaf910bd5e3f83

Observation bae376ea-731c-4399-bbe5-e3b392e2739d · outbound

This paper cites Reflexion: Language Agents with Verbal Reinforcement Learning.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Reflexion: Language Agents with Verbal Reinforcement Learning

Reference 43

Resolution
verified exact
arxiv_id, observed 2026-05-10T13:51:42.034658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:9e0ef93c31e5d8b2a8464e0cd0a9a420c169f7535c1a28b0c4e5eb5b00321cbd

Observation 0c821c00-45e9-4b80-a819-d81a6335e3d7 · outbound

This paper cites Self-Refine: Iterative Refinement with Self-Feedback.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Self-Refine: Iterative Refinement with Self-Feedback

Reference 44

Resolution
verified exact
arxiv_id, observed 2026-05-10T20:47:39.867132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:7379b4aa33197256deb6d62f9f46a0d583862d8f9b85b40329edeca9218c0574

Observation 026bcc16-14ba-41c5-b2af-34087aeed479 · outbound

This paper cites AI safety via debate.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery AI safety via debate

Reference 45

Resolution
verified exact
arxiv_id, observed 2026-05-13T21:22:01.373606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:a3e42de83eabf91ebf47fbc68be7a77944f169b23631a3c7f3a9d6090603ebaf

Observation 84bf9aa3-f5ea-406d-b873-83d60c67e63e · outbound

This paper cites Denisov-Blanch, J.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Denisov-Blanch, J

Reference 46

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.019578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:b244de5e6bbaf9c98eee035390c700b425dc5c901e75a3633a5cc573fa072a78

Observation 6641cc34-0a4e-4741-a2e9-2e873a1c41bf · outbound

This paper cites an unresolved cited work.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Unresolved cited work

Reference 47

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.051385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:47f251563ab66ff7d860e2c58c312e7aa6c1838f9f8340c6e2296f46eaac2055

Observation bcee126c-3608-4c00-a0ce-91901f1cdc15 · outbound

This paper cites SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

Reference 48

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.021924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:03c61769ff8fc9c267242eee87121b472983233c2e2d7a3929641a9fbc4b3220

Observation 91be2000-4740-47c3-9448-9b6db5d06b26 · outbound

This paper cites Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection

Reference 49

Resolution
verified exact
local_arxiv, observed 2026-05-10T03:14:08.043876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:2c650b1c13034e5bb5269915ac396164a7db8d0dfe28d16aca6e7e292a12a65c

Observation 784fa80c-fd51-43d2-8f4b-49eacd311c95 · outbound

This paper cites arXiv.https://arxiv.org/abs/ 2510.11822.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery arXiv.https://arxiv.org/abs/ 2510.11822

Reference 50

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.041150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:869eb5d09cdcbd3df3daa00b6067e66a0c6159ceabcb899b9e1681ddcc0763d4

Observation 4eefb182-e1bd-4b23-8239-65b4e0d8b261 · outbound

This paper cites D3: Dissecting multi-agent debate for LLM evaluation.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery D3: Dissecting multi-agent debate for LLM evaluation

Reference 51

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:08.038739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:081928d511e576a90e8db2c8e675c9e0c22efe3cd0347c48541b56cc32fbfdce

Observation e611b39a-5903-449f-8b66-2f9824de74d8 · outbound

This paper cites From CVE entries to verifiable exploits: An automated multi- agent framework for reproducing CVEs.CoRR, abs/2509.01835.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery From CVE entries to verifiable exploits: An automated multi- agent framework for reproducing CVEs.CoRR, abs/2509.01835

Reference 52

Resolution
verified exact
arxiv_id, observed 2026-05-10T03:14:07.981854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-10T03:11:26.513954Z digest=sha256:dc6f0ec4978b30e0353bbf1cabf0b07678e0ba7e39e5400c3b45925bd8ff423e

Pith citing papers

Observation e272ef24-f536-4312-a1da-6ec30669cf8b · inbound

Adversarial Test-Hardening for AI-Written Code: An Instrument Autopsy and a Pre-Registered Causal Estimate of the Critic Loop cites this paper.

Adversarial Test-Hardening for AI-Written Code: An Instrument Autopsy and a Pre-Registered Causal Estimate of the Critic Loop Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery

Reference 2026

Resolution
unresolved
no resolver link, observed 2026-08-01T03:57:40.779886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T03:57:40.779886Z digest=sha256:4f91ea3dc3d94f3e176133bc1ba29976cec258ef5a6386962249d1a88584f6ba