Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378770536> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4378770536 abstract "Much of the recent work developing formal methods techniques to specify or learn the behavior of autonomous systems is predicated on a belief that formal specifications are interpretable and useful for humans when checking systems. Though frequently asserted, this assumption is rarely tested. We performed a human experiment (N = 62) with a mix of people who were and were not familiar with formal methods beforehand, asking them to validate whether a set of signal temporal logic (STL) constraints would keep an agent out of harm and allow it to complete a task in a gridworld capture-the-flag setting. Validation accuracy was $45% pm 20%$ (mean $pm$ standard deviation). The ground-truth validity of a specification, subjects' familiarity with formal methods, and subjects' level of education were found to be significant factors in determining validation correctness. Participants exhibited an affirmation bias, causing significantly increased accuracy on valid specifications, but significantly decreased accuracy on invalid specifications. Additionally, participants, particularly those familiar with formal methods, tended to be overconfident in their answers, and be similarly confident regardless of actual correctness. Our data do not support the belief that formal specifications are inherently human-interpretable to a meaningful degree for system validation. We recommend ergonomic improvements to data presentation and validation training, which should be tested before claims of interpretability make their way back into the formal methods literature." @default.
- W4378770536 created "2023-05-31" @default.
- W4378770536 creator A5005661666 @default.
- W4378770536 creator A5034884039 @default.
- W4378770536 creator A5059144582 @default.
- W4378770536 date "2023-05-26" @default.
- W4378770536 modified "2023-10-16" @default.
- W4378770536 title "STL: Surprisingly Tricky Logic (for System Validation)" @default.
- W4378770536 doi "https://doi.org/10.48550/arxiv.2305.17258" @default.
- W4378770536 hasPublicationYear "2023" @default.
- W4378770536 type Work @default.
- W4378770536 citedByCount "0" @default.
- W4378770536 crossrefType "posted-content" @default.
- W4378770536 hasAuthorship W4378770536A5005661666 @default.
- W4378770536 hasAuthorship W4378770536A5034884039 @default.
- W4378770536 hasAuthorship W4378770536A5059144582 @default.
- W4378770536 hasBestOaLocation W43787705361 @default.
- W4378770536 hasConcept C111498074 @default.
- W4378770536 hasConcept C115903868 @default.
- W4378770536 hasConcept C119857082 @default.
- W4378770536 hasConcept C154945302 @default.
- W4378770536 hasConcept C15744967 @default.
- W4378770536 hasConcept C177264268 @default.
- W4378770536 hasConcept C199360897 @default.
- W4378770536 hasConcept C204321447 @default.
- W4378770536 hasConcept C2777363581 @default.
- W4378770536 hasConcept C2781067378 @default.
- W4378770536 hasConcept C41008148 @default.
- W4378770536 hasConcept C55439883 @default.
- W4378770536 hasConcept C75606506 @default.
- W4378770536 hasConcept C77805123 @default.
- W4378770536 hasConceptScore W4378770536C111498074 @default.
- W4378770536 hasConceptScore W4378770536C115903868 @default.
- W4378770536 hasConceptScore W4378770536C119857082 @default.
- W4378770536 hasConceptScore W4378770536C154945302 @default.
- W4378770536 hasConceptScore W4378770536C15744967 @default.
- W4378770536 hasConceptScore W4378770536C177264268 @default.
- W4378770536 hasConceptScore W4378770536C199360897 @default.
- W4378770536 hasConceptScore W4378770536C204321447 @default.
- W4378770536 hasConceptScore W4378770536C2777363581 @default.
- W4378770536 hasConceptScore W4378770536C2781067378 @default.
- W4378770536 hasConceptScore W4378770536C41008148 @default.
- W4378770536 hasConceptScore W4378770536C55439883 @default.
- W4378770536 hasConceptScore W4378770536C75606506 @default.
- W4378770536 hasConceptScore W4378770536C77805123 @default.
- W4378770536 hasLocation W43787705361 @default.
- W4378770536 hasOpenAccess W4378770536 @default.
- W4378770536 hasPrimaryLocation W43787705361 @default.
- W4378770536 hasRelatedWork W1517743118 @default.
- W4378770536 hasRelatedWork W1614816533 @default.
- W4378770536 hasRelatedWork W2133819580 @default.
- W4378770536 hasRelatedWork W3006943036 @default.
- W4378770536 hasRelatedWork W3012234327 @default.
- W4378770536 hasRelatedWork W3091728393 @default.
- W4378770536 hasRelatedWork W4205364923 @default.
- W4378770536 hasRelatedWork W4206534706 @default.
- W4378770536 hasRelatedWork W4229079080 @default.
- W4378770536 hasRelatedWork W4366769587 @default.
- W4378770536 isParatext "false" @default.
- W4378770536 isRetracted "false" @default.
- W4378770536 workType "article" @default.