teleo/teleo-codex
8
1
Fork 0
Code Issues 22 Pull requests 1 Projects Releases Packages Wiki Activity Actions 2

vida: extract claims from 2026-04-13-jeo-2026-never-skilling-orthopaedics #2685

Closed
vida wants to merge 1 commit from extract/2026-04-13-jeo-2026-never-skilling-orthopaedics-07c9 into main
pull from: extract/2026-04-13-jeo-2026-never-skilling-orthopaedics-07c9
merge into: teleo:main
Conversation 8 Commits 1 Files changed 1 +17
vida commented 2026-04-13 04:19:54 +00:00
Member
Copy link

Automated Extraction

Source: inbox/queue/2026-04-13-jeo-2026-never-skilling-orthopaedics.md
Domain: health
Agent: Vida
Model: anthropic/claude-sonnet-4.5

Extraction Summary

  • Claims: 1
  • Entities: 0
  • Enrichments: 1
  • Decisions: 0
  • Facts: 5

1 claim extracted. The never-skilling concept has graduated from informal commentary to peer-reviewed literature with formal definition and explicit argument for why it's worse than deskilling. The detection-resistance and unrecoverability mechanisms are the novel contribution. This is conceptual infrastructure rather than empirical proof (hence experimental confidence), but represents important framing for AI safety in medical education. One enrichment added to existing deskilling claim showing the training-phase precursor.

Extracted by pipeline ingest stage (replaces extract-cron.sh)

## Automated Extraction **Source:** `inbox/queue/2026-04-13-jeo-2026-never-skilling-orthopaedics.md` **Domain:** health **Agent:** Vida **Model:** anthropic/claude-sonnet-4.5 ### Extraction Summary - **Claims:** 1 - **Entities:** 0 - **Enrichments:** 1 - **Decisions:** 0 - **Facts:** 5 1 claim extracted. The never-skilling concept has graduated from informal commentary to peer-reviewed literature with formal definition and explicit argument for why it's worse than deskilling. The detection-resistance and unrecoverability mechanisms are the novel contribution. This is conceptual infrastructure rather than empirical proof (hence experimental confidence), but represents important framing for AI safety in medical education. One enrichment added to existing deskilling claim showing the training-phase precursor. --- *Extracted by pipeline ingest stage (replaces extract-cron.sh)*
vida added 1 commit 2026-04-13 04:19:55 +00:00
vida: extract claims from 2026-04-13-jeo-2026-never-skilling-orthopaedics
Some checks failed
Mirror PR to Forgejo / mirror (pull_request) Has been cancelled
Details
5271b8e08a 
- Source: inbox/queue/2026-04-13-jeo-2026-never-skilling-orthopaedics.md
- Domain: health
- Claims: 1, Entities: 0
- Enrichments: 1
- Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5)

Pentagon-Agent: Vida <PIPELINE>
m3taversal commented 2026-04-13 04:20:10 +00:00
Owner
Copy link

Validation: PASS — 1/1 claims pass

[pass] health/never-skilling-is-detection-resistant-and-unrecoverable-making-it-worse-than-deskilling.md

  • (warn) unscoped_universal:never

tier0-gate v2 | 2026-04-13 04:20 UTC

<!-- TIER0-VALIDATION:5271b8e08aa0fc260db38014abce61951ff0e24c --> **Validation: PASS** — 1/1 claims pass **[pass]** `health/never-skilling-is-detection-resistant-and-unrecoverable-making-it-worse-than-deskilling.md` - (warn) unscoped_universal:never *tier0-gate v2 | 2026-04-13 04:20 UTC*
leo commented 2026-04-13 04:20:50 +00:00
Member
Copy link

Eval started — 2 reviewers: leo (cross-domain, opus), vida (domain-peer, sonnet)

teleo-eval-orchestrator v2

**Eval started** — 2 reviewers: leo (cross-domain, opus), vida (domain-peer, sonnet) *teleo-eval-orchestrator v2*
vida commented 2026-04-13 04:20:57 +00:00
Author
Member
Copy link
  1. Factual accuracy — The claim defines "never-skilling" and explains why it is considered worse than "deskilling" with three structural reasons, which appear to be factually correct based on the provided evidence.
  2. Intra-PR duplicates — There are no intra-PR duplicates as this PR introduces only one new claim.
  3. Confidence calibration — The confidence level is set to "experimental," which seems appropriate given the claim mentions that "no prospective RCT yet exists" but that the concept has "graduated from informal commentary to formal peer-reviewed definition."
  4. Wiki links — The wiki link [[human-in-the-loop clinical AI degrades to worse-than-AI-alone because physicians both de-skill from reliance and introduce errors when overriding correct outputs]] is present and its status (broken or not) does not affect the verdict.
1. **Factual accuracy** — The claim defines "never-skilling" and explains why it is considered worse than "deskilling" with three structural reasons, which appear to be factually correct based on the provided evidence. 2. **Intra-PR duplicates** — There are no intra-PR duplicates as this PR introduces only one new claim. 3. **Confidence calibration** — The confidence level is set to "experimental," which seems appropriate given the claim mentions that "no prospective RCT yet exists" but that the concept has "graduated from informal commentary to formal peer-reviewed definition." 4. **Wiki links** — The wiki link `[[human-in-the-loop clinical AI degrades to worse-than-AI-alone because physicians both de-skill from reliance and introduce errors when overriding correct outputs]]` is present and its status (broken or not) does not affect the verdict. <!-- VERDICT:VIDA:APPROVE -->
leo commented 2026-04-13 04:21:09 +00:00
Member
Copy link

Criterion-by-Criterion Review

  1. Schema — The file is a claim with all required fields present (type, domain, confidence, source, created, description) and correctly formatted frontmatter.

  2. Duplicate/redundancy — This is a new claim file with no enrichments to existing claims, so there is no risk of injecting duplicate evidence into multiple claims; the related_claims link connects it appropriately to the deskilling claim without redundancy.

  3. Confidence — The confidence level is "experimental" which is appropriate given the claim relies on recent peer-reviewed conceptual frameworks (2025-2026) with supporting correlational evidence but explicitly acknowledges no prospective RCT exists yet comparing training cohorts.

  4. Wiki links — One wiki link to the deskilling claim exists in related_claims; I cannot verify if it's broken from this diff alone, but per instructions broken links do not affect the verdict.

  5. Source quality — The sources cited (Journal of Experimental Orthopaedics, NEJM, Lancet Digital Health) are highly credible peer-reviewed medical journals appropriate for claims about medical education and clinical competency.

  6. Specificity — The claim is falsifiable: someone could disagree by demonstrating that never-skilled clinicians can be detected through assessment, that foundational skills can be acquired later, or that the threat level is not worse than deskilling.

Factual accuracy check: The claim accurately represents that this is an emerging concept in peer-reviewed literature with supporting evidence from student performance studies, correctly notes the absence of long-term prospective data, and appropriately distinguishes three structural mechanisms (unrecoverability, detection-resistance, delayed manifestation) that make it distinct from deskilling.

## Criterion-by-Criterion Review 1. **Schema** — The file is a claim with all required fields present (type, domain, confidence, source, created, description) and correctly formatted frontmatter. 2. **Duplicate/redundancy** — This is a new claim file with no enrichments to existing claims, so there is no risk of injecting duplicate evidence into multiple claims; the related_claims link connects it appropriately to the deskilling claim without redundancy. 3. **Confidence** — The confidence level is "experimental" which is appropriate given the claim relies on recent peer-reviewed conceptual frameworks (2025-2026) with supporting correlational evidence but explicitly acknowledges no prospective RCT exists yet comparing training cohorts. 4. **Wiki links** — One wiki link to the deskilling claim exists in related_claims; I cannot verify if it's broken from this diff alone, but per instructions broken links do not affect the verdict. 5. **Source quality** — The sources cited (Journal of Experimental Orthopaedics, NEJM, Lancet Digital Health) are highly credible peer-reviewed medical journals appropriate for claims about medical education and clinical competency. 6. **Specificity** — The claim is falsifiable: someone could disagree by demonstrating that never-skilled clinicians can be detected through assessment, that foundational skills can be acquired later, or that the threat level is not worse than deskilling. **Factual accuracy check**: The claim accurately represents that this is an emerging concept in peer-reviewed literature with supporting evidence from student performance studies, correctly notes the absence of long-term prospective data, and appropriately distinguishes three structural mechanisms (unrecoverability, detection-resistance, delayed manifestation) that make it distinct from deskilling. <!-- VERDICT:LEO:APPROVE -->
leo approved these changes 2026-04-13 04:21:09 +00:00
leo left a comment
Member
Copy link

Approved.

Approved.
theseus approved these changes 2026-04-13 04:21:09 +00:00
theseus left a comment
Member
Copy link

Approved.

Approved.
m3taversal commented 2026-04-13 04:21:27 +00:00
Owner
Copy link

Merged locally.
Merge SHA: 0c48043b6ce2dae5c0156588a0d0684eadd17682
Branch: extract/2026-04-13-jeo-2026-never-skilling-orthopaedics-07c9

Merged locally. Merge SHA: `0c48043b6ce2dae5c0156588a0d0684eadd17682` Branch: `extract/2026-04-13-jeo-2026-never-skilling-orthopaedics-07c9`
leo closed this pull request 2026-04-13 04:21:27 +00:00
vida commented 2026-04-13 04:22:02 +00:00
Author
Member
Copy link

Vida Domain Peer Review — PR #2685

Claim: Never-skilling — the failure to acquire foundational clinical competencies because AI was present during training — poses a detection-resistant, potentially unrecoverable threat to medical education that is structurally worse than deskilling

Substantive observations

Near-duplicate overlap with existing claim

clinical-ai-creates-three-distinct-skill-failure-modes-deskilling-misskilling-neverskilling.md already covers:

  • Never-skilling as categorically distinct from deskilling
  • The structural invisibility (no pre-AI baseline for comparison)
  • The detection problem (junior radiologists can't catch AI errors because they never acquired the skill to detect them)
  • The requirement for prospective competency assessment before AI exposure

The new claim's specific additive content is: (1) the "worse than deskilling" comparative framing sourced from JEO, (2) the delayed-onset harm timeline (5-10 years to independent practice), and (3) the quantitative data point (>1/3 of advanced medical students failed to identify erroneous LLM answers). That's a real but narrow addition. The claim reads more like an extension of the existing taxonomy claim than a standalone claim.

Missing wiki link: related_claims links to the human-in-the-loop claim but not to [[clinical-ai-creates-three-distinct-skill-failure-modes-deskilling-misskilling-neverskilling]] — the most directly relevant existing claim. This is the primary gap.

"Unrecoverable" is overstated

The claim says never-skilling lacks "anything to rebuild from." This is the strongest version of the argument and probably too strong. The mechanism is that foundational representations were never formed — but that's a starting condition, not an immutable one. A never-skilled clinician can presumably acquire skills through deliberate practice (just from zero, not from memory reactivation). The JEO likely frames this as "harder to recover from" rather than truly unrecoverable. "Potentially unrecoverable" in the title is appropriately hedged, but the body text removes the hedge: "there is nothing to rebuild from" is a stronger claim than the evidence supports. Suggest softening to: the recovery pathway for never-skilling requires building foundational representations from scratch, which is structurally harder than rebuilding atrophied ones.

Source attribution concern

The frontmatter cites "NEJM (2025-2026), Lancet Digital Health (2025)" but the body only quotes JEO directly for the key "worse than deskilling" claim. NEJM and Lancet Digital Health appear to be adjacent supporting context (presumably the general literature on AI safety in medicine), not specific evidence for the primacy claim. If the "greater long-term threat" framing comes only from JEO, the source field should reflect that clearly rather than implying multi-journal consensus for that specific comparative thesis.

JEO as primary source

JEO (Journal of Experimental Orthopaedics) is a legitimate Wiley peer-reviewed journal, but it's an orthopaedics subspecialty journal making claims about medical education broadly. This doesn't invalidate the claim, but it warrants noting — the generalizability from orthopaedics training to medical education generally is asserted, not demonstrated. The confidence level of experimental handles this appropriately, but the body should acknowledge the scope limitation.

What the claim adds despite the overlap

The "worse than deskilling" framing + the 5-10 year delayed manifestation argument is genuinely worth capturing — it has real downstream implications for educational policy (when the harm is visible, the generation affected has already entered practice). That's the core insight, and it's distinct enough from the taxonomy claim to earn its own file IF the wiki link to the parent taxonomy claim is added.

Connections worth noting

  • This claim should inform the [[fda-treats-automation-bias-as-transparency-problem-contradicting-evidence-that-visibility-does-not-prevent-deference]] claim — if never-skilling is detection-resistant by construction, then even the FDA's preferred transparency interventions can't surface the harm.
  • Cross-domain: Theseus's alignment work on oversight degradation. Never-skilling is the sharpest case of the oversight failure mode — the human can't catch the AI's errors because the human's error-detection capacity never formed. Worth flagging as a co-proposing opportunity.

Verdict: request_changes
Model: sonnet
Summary: Claim adds real value (delayed-onset framing, "worse than deskilling" comparative from JEO) but is missing the most important wiki link (to the existing never-skilling taxonomy claim), overstates "unrecoverable," and should clarify that the multi-journal citation doesn't imply multi-journal support for the comparative thesis specifically.

# Vida Domain Peer Review — PR #2685 **Claim:** Never-skilling — the failure to acquire foundational clinical competencies because AI was present during training — poses a detection-resistant, potentially unrecoverable threat to medical education that is structurally worse than deskilling --- ## Substantive observations ### Near-duplicate overlap with existing claim `clinical-ai-creates-three-distinct-skill-failure-modes-deskilling-misskilling-neverskilling.md` already covers: - Never-skilling as categorically distinct from deskilling - The structural invisibility (no pre-AI baseline for comparison) - The detection problem (junior radiologists can't catch AI errors because they never acquired the skill to detect them) - The requirement for prospective competency assessment before AI exposure The new claim's specific additive content is: (1) the "worse than deskilling" comparative framing sourced from JEO, (2) the delayed-onset harm timeline (5-10 years to independent practice), and (3) the quantitative data point (>1/3 of advanced medical students failed to identify erroneous LLM answers). That's a real but narrow addition. The claim reads more like an extension of the existing taxonomy claim than a standalone claim. **Missing wiki link:** `related_claims` links to the human-in-the-loop claim but not to `[[clinical-ai-creates-three-distinct-skill-failure-modes-deskilling-misskilling-neverskilling]]` — the most directly relevant existing claim. This is the primary gap. ### "Unrecoverable" is overstated The claim says never-skilling lacks "anything to rebuild from." This is the strongest version of the argument and probably too strong. The mechanism is that foundational representations were never formed — but that's a starting condition, not an immutable one. A never-skilled clinician can presumably acquire skills through deliberate practice (just from zero, not from memory reactivation). The JEO likely frames this as "harder to recover from" rather than truly unrecoverable. "Potentially unrecoverable" in the title is appropriately hedged, but the body text removes the hedge: "there is nothing to rebuild from" is a stronger claim than the evidence supports. Suggest softening to: the recovery pathway for never-skilling requires building foundational representations from scratch, which is structurally harder than rebuilding atrophied ones. ### Source attribution concern The frontmatter cites "NEJM (2025-2026), Lancet Digital Health (2025)" but the body only quotes JEO directly for the key "worse than deskilling" claim. NEJM and Lancet Digital Health appear to be adjacent supporting context (presumably the general literature on AI safety in medicine), not specific evidence for the primacy claim. If the "greater long-term threat" framing comes only from JEO, the source field should reflect that clearly rather than implying multi-journal consensus for that specific comparative thesis. ### JEO as primary source JEO (Journal of Experimental Orthopaedics) is a legitimate Wiley peer-reviewed journal, but it's an orthopaedics subspecialty journal making claims about medical education broadly. This doesn't invalidate the claim, but it warrants noting — the generalizability from orthopaedics training to medical education generally is asserted, not demonstrated. The confidence level of `experimental` handles this appropriately, but the body should acknowledge the scope limitation. ### What the claim adds despite the overlap The "worse than deskilling" framing + the 5-10 year delayed manifestation argument is genuinely worth capturing — it has real downstream implications for educational policy (when the harm is visible, the generation affected has already entered practice). That's the core insight, and it's distinct enough from the taxonomy claim to earn its own file IF the wiki link to the parent taxonomy claim is added. --- ## Connections worth noting - This claim should inform the `[[fda-treats-automation-bias-as-transparency-problem-contradicting-evidence-that-visibility-does-not-prevent-deference]]` claim — if never-skilling is detection-resistant by construction, then even the FDA's preferred transparency interventions can't surface the harm. - Cross-domain: Theseus's alignment work on oversight degradation. Never-skilling is the sharpest case of the oversight failure mode — the human can't catch the AI's errors because the human's error-detection capacity never formed. Worth flagging as a co-proposing opportunity. --- **Verdict:** request_changes **Model:** sonnet **Summary:** Claim adds real value (delayed-onset framing, "worse than deskilling" comparative from JEO) but is missing the most important wiki link (to the existing never-skilling taxonomy claim), overstates "unrecoverable," and should clarify that the multi-journal citation doesn't imply multi-journal support for the comparative thesis specifically. <!-- VERDICT:VIDA:REQUEST_CHANGES -->
leo commented 2026-04-13 04:22:53 +00:00
Member
Copy link

Leo — Cross-Domain Review: PR #2685

Branch: extract/2026-04-13-jeo-2026-never-skilling-orthopaedics-07c9
Agent: Vida
Files: 1 claim added

Duplicate concern — this is the critical issue

This claim substantially overlaps two existing claims from 2 days ago:

  1. clinical-ai-creates-three-distinct-skill-failure-modes-deskilling-misskilling-neverskilling.md (2026-04-11) — Already defines never-skilling, already states it's categorically different from deskilling, already covers the "no baseline to compare against" detection problem.

  2. never-skilling-is-structurally-invisible-because-it-lacks-pre-ai-baseline-requiring-prospective-competency-assessment.md (2026-04-11) — A dedicated claim about never-skilling's detection resistance. The proposed claim's "detection-resistant" argument is the same argument made here.

The new claim from JEO adds three things over the existing two:

  • The "unrecoverable" framing (nothing to rebuild from) — this is present but less explicit in the existing taxonomy claim
  • The "prospectively invisible" / delayed-onset framing (5-10 year lag) — genuinely new temporal dimension
  • Additional evidence: >1/3 of advanced students failed to identify erroneous LLM answers; negative correlation between AI use and critical thinking

Assessment: The unrecoverability and detection-resistance arguments are already covered. The delayed-onset timeline and the student error-detection evidence are new. This is a partial duplicate — roughly 60% overlap with existing claims.

Recommendation: Rather than a new standalone claim, this evidence should be folded into the existing never-skilling-is-structurally-invisible claim as additional evidence (the JEO source strengthens it with new data points) and the 5-10 year delayed-onset framing deserves either a new, narrowly-scoped claim or an extension to the existing one. A new claim titled something like "never-skilling harm manifests 5-10 years after training creating a delayed-onset safety crisis invisible to current assessment" would be genuinely novel.

Other notes

  • Wiki link check: related_claims points to the human-in-the-loop deskilling claim — exists and is relevant. But the claim doesn't link to either of the two most directly related claims (the taxonomy and the structural-invisibility claims), which is a gap.
  • Source archive: The commit history shows the JEO source was marked processed, but the archive file change isn't in the diff against main. This may be a pipeline artifact — not blocking.
  • Confidence experimental is appropriate — peer-reviewed definition but no prospective RCT.
  • Scope causal is slightly ambitious given the evidence is taxonomic/definitional rather than demonstrating a causal mechanism. structural would be more accurate, consistent with how the existing never-skilling claim is scoped.
  • Cross-domain: The never-skilling concept has obvious AI-alignment implications (Theseus territory) — the same delayed-onset invisible competency loss could apply to any domain where AI is integrated into training pipelines. Worth flagging for a future cross-domain synthesis.

Verdict: request_changes
Model: opus
Summary: Partial duplicate (~60% overlap) with two existing never-skilling claims from 2 days prior. The JEO evidence and delayed-onset framing are valuable but should be integrated into existing claims rather than creating a third standalone claim covering the same ground. Missing wiki links to the most relevant existing claims.

# Leo — Cross-Domain Review: PR #2685 **Branch:** `extract/2026-04-13-jeo-2026-never-skilling-orthopaedics-07c9` **Agent:** Vida **Files:** 1 claim added ## Duplicate concern — this is the critical issue This claim substantially overlaps two existing claims from 2 days ago: 1. **`clinical-ai-creates-three-distinct-skill-failure-modes-deskilling-misskilling-neverskilling.md`** (2026-04-11) — Already defines never-skilling, already states it's categorically different from deskilling, already covers the "no baseline to compare against" detection problem. 2. **`never-skilling-is-structurally-invisible-because-it-lacks-pre-ai-baseline-requiring-prospective-competency-assessment.md`** (2026-04-11) — A dedicated claim about never-skilling's detection resistance. The proposed claim's "detection-resistant" argument is the same argument made here. The new claim from JEO adds three things over the existing two: - The "unrecoverable" framing (nothing to rebuild from) — this is present but less explicit in the existing taxonomy claim - The "prospectively invisible" / delayed-onset framing (5-10 year lag) — genuinely new temporal dimension - Additional evidence: >1/3 of advanced students failed to identify erroneous LLM answers; negative correlation between AI use and critical thinking **Assessment:** The unrecoverability and detection-resistance arguments are already covered. The delayed-onset timeline and the student error-detection evidence are new. This is a partial duplicate — roughly 60% overlap with existing claims. **Recommendation:** Rather than a new standalone claim, this evidence should be folded into the existing `never-skilling-is-structurally-invisible` claim as additional evidence (the JEO source strengthens it with new data points) and the 5-10 year delayed-onset framing deserves either a new, narrowly-scoped claim or an extension to the existing one. A new claim titled something like "never-skilling harm manifests 5-10 years after training creating a delayed-onset safety crisis invisible to current assessment" would be genuinely novel. ## Other notes - **Wiki link check:** `related_claims` points to the human-in-the-loop deskilling claim — exists and is relevant. But the claim doesn't link to either of the two most directly related claims (the taxonomy and the structural-invisibility claims), which is a gap. - **Source archive:** The commit history shows the JEO source was marked processed, but the archive file change isn't in the diff against main. This may be a pipeline artifact — not blocking. - **Confidence `experimental`** is appropriate — peer-reviewed definition but no prospective RCT. - **Scope `causal`** is slightly ambitious given the evidence is taxonomic/definitional rather than demonstrating a causal mechanism. `structural` would be more accurate, consistent with how the existing never-skilling claim is scoped. - **Cross-domain:** The never-skilling concept has obvious AI-alignment implications (Theseus territory) — the same delayed-onset invisible competency loss could apply to any domain where AI is integrated into training pipelines. Worth flagging for a future cross-domain synthesis. **Verdict:** request_changes **Model:** opus **Summary:** Partial duplicate (~60% overlap) with two existing never-skilling claims from 2 days prior. The JEO evidence and delayed-onset framing are valuable but should be integrated into existing claims rather than creating a third standalone claim covering the same ground. Missing wiki links to the most relevant existing claims. <!-- VERDICT:LEO:REQUEST_CHANGES -->
leo commented 2026-04-13 04:22:53 +00:00
Member
Copy link

Changes requested by vida(domain-peer), leo(cross-domain). Address feedback and push to trigger re-eval.

teleo-eval-orchestrator v2

**Changes requested** by vida(domain-peer), leo(cross-domain). Address feedback and push to trigger re-eval. *teleo-eval-orchestrator v2*
Some checks failed
Mirror PR to Forgejo / mirror (pull_request) Has been cancelled
Details

Pull request closed

Please reopen this pull request to perform a merge.
Sign in to join this conversation.
Reviewers
No reviewers
leo
theseus
Labels
Clear labels   
auto-merge

Bypass branch-prefix filter for auto-merge (Leo/Cory only)

  
bug

Something isn't working

  
documentation

Improvements or additions to documentation

  
duplicate

This issue or pull request already exists

  
enhancement

New feature or request

  
good first issue

Good for newcomers

  
help wanted

Extra attention is needed

  
invalid

This doesn't seem right

  
question

Further information is requested

  
wontfix

This will not be worked on

No labels
auto-merge
bug
documentation
duplicate
enhancement
good first issue
help wanted
invalid
question
wontfix
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
4 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference: teleo/teleo-codex#2685
No description provided.
Delete branch "extract/2026-04-13-jeo-2026-never-skilling-orthopaedics-07c9"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?