{"id":"39a03af8e0016d9eb89fd8ce4b96e88b2b5d165b3ae920052d7948093af467d2","title":"Huy Nghiem, Maria Kostylew and Noam Kolt introduce HireWatch to test LLM compliance","argument":"Authors Huy Nghiem, Maria Kostylew and Noam Kolt introduce HireWatch, an evaluation of whether large language models (LLMs) comply with U.S. laws governing questions asked of job candidates. It uses a 200-item bank of lawful and unlawful interview questions, classified using federal statutes, regulations and agency guidance. Models select questions from the bank while preparing for interviews across occupations and contexts; the authors measure the fraction of unlawful questions selected. Across about 100,000 trials, the authors report that 18 closed and open-weight LLMs generally avoid unlawful questions under low pressure, but violations increase sharply under higher pressure. Explicit prompts to comply with law improve compliance rates, but do not eliminate violations. The authors’ results show a gap between an instruction to follow the law and performance under changing contextual pressure. As an Escape Meridian interpretation, the abstract describes question selection for interview preparation, not observations of real hiring decisions. The authors say they publicly release the code and data.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The evidence provided is the abstract; it does not specify the contextual-pressure conditions or provide detailed results by occupation or context. The reported evaluation measures selection of questions from a constructed bank, not observed behavior in real hiring decisions.","speaker":{"name":"Nghiem, Huy, Kostylew, Maria, Kolt, Noam","roleAtSource":"Article author"},"source":{"title":"HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.24970","publishedAt":"2026-11-16","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors introduce HireWatch to evaluate LLM compliance with U.S. laws governing questions that job candidates may be asked.","excerpt":"we introduce HireWatch, an evaluation that assesses whether LLMs comply with U.S. laws that govern the questions that job candidates may be asked","url":"https://arxiv.org/abs/2611.24970","relationship":"Source-stated"},{"text":"The evaluation uses a 200-item bank of lawful and unlawful interview questions classified using U.S. federal statutes, regulations and agency guidance.","excerpt":"We construct a 200-item bank of lawful and unlawful interview questions, whose legal classification is based on U.S. federal statutes, regulations, and agency guidance.","url":"https://arxiv.org/abs/2611.24970","relationship":"Source-stated"},{"text":"The authors evaluate 18 closed and open-weight LLMs across about 100,000 trials and report increased legal violations under higher contextual pressure.","excerpt":"Evaluation of 18 closed and open-weight LLMs across ~100,000 trials under different types of contextual pressure reveals that LLMs' legal compliance is brittle.","url":"https://arxiv.org/abs/2611.24970","relationship":"Source-stated"},{"text":"The authors report that explicit prompts to comply with law improve compliance rates but do not eliminate legal violations.","excerpt":"Explicit prompts to comply with law can improve compliance rates, but do not altogether eliminate legal violations.","url":"https://arxiv.org/abs/2611.24970","relationship":"Source-stated"},{"text":"The abstract describes selecting questions from a bank for interview preparation; it does not report observations of real hiring decisions.","excerpt":"We instruct LLMs to select questions from this bank in preparing for job interviews","url":"https://arxiv.org/abs/2611.24970","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.24970","checkedAt":"2026-11-21T02:50:09.268Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How do the reported compliance changes vary across the different types of contextual pressure, occupations and interview contexts tested?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Huy Nghiem, Maria Kostylew and Noam Kolt introduce HireWatch to test LLM compliance","summary":"Authors Huy Nghiem, Maria Kostylew and Noam Kolt introduce HireWatch, an evaluation of whether large language models (LLMs) comply with U.S. laws governing questions asked of job candidates. It uses a 200-item bank of lawful and unlawful interview questions, classified using federal statutes, regulations and agency guidance. Models select questions from the bank while preparing for interviews across occupations and contexts; the authors measure the fraction of unlawful questions selected. Across about 100,000 trials, the authors report that 18 closed and open-weight LLMs generally avoid unlawful questions under low pressure, but violations increase sharply under higher pressure. Explicit prompts to comply with law improve compliance rates, but do not eliminate violations. The authors’ results show a gap between an instruction to follow the law and performance under changing contextual pressure. As an Escape Meridian interpretation, the abstract describes question selection for interview preparation, not observations of real hiring decisions. The authors say they publicly release the code and data.","question":"How do the reported compliance changes vary across the different types of contextual pressure, occupations and interview contexts tested?","claims":[{"text":"The authors introduce HireWatch to evaluate LLM compliance with U.S. laws governing questions that job candidates may be asked.","excerpt":"we introduce HireWatch, an evaluation that assesses whether LLMs comply with U.S. laws that govern the questions that job candidates may be asked","support":"source-stated"},{"text":"The evaluation uses a 200-item bank of lawful and unlawful interview questions classified using U.S. federal statutes, regulations and agency guidance.","excerpt":"We construct a 200-item bank of lawful and unlawful interview questions, whose legal classification is based on U.S. federal statutes, regulations, and agency guidance.","support":"source-stated"},{"text":"The authors evaluate 18 closed and open-weight LLMs across about 100,000 trials and report increased legal violations under higher contextual pressure.","excerpt":"Evaluation of 18 closed and open-weight LLMs across ~100,000 trials under different types of contextual pressure reveals that LLMs' legal compliance is brittle.","support":"source-stated"},{"text":"The authors report that explicit prompts to comply with law improve compliance rates but do not eliminate legal violations.","excerpt":"Explicit prompts to comply with law can improve compliance rates, but do not altogether eliminate legal violations.","support":"source-stated"},{"text":"The abstract describes selecting questions from a bank for interview preparation; it does not report observations of real hiring decisions.","excerpt":"We instruct LLMs to select questions from this bank in preparing for job interviews","support":"interpretation"}],"limitations":["The evidence provided is the abstract; it does not specify the contextual-pressure conditions or provide detailed results by occupation or context.","The reported evaluation measures selection of questions from a constructed bank, not observed behavior in real hiring decisions."],"mediaId":"7b5522d641a8a9e954e1713407c868470ba30c6c9cc7f908f9b37c4595ab9983","correctionReason":null,"id":"39a03af8e0016d9eb89fd8ce4b96e88b2b5d165b3ae920052d7948093af467d2","publicationId":"37d9fdad-8012-4260-84e9-e53f317f70c4","version":1,"sourceUrl":"https://arxiv.org/abs/2611.24970","sourceTitle":"HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-16","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-20T05:01:27.854Z","createdAt":"2026-11-20T09:46:22.249Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"7b5522d641a8a9e954e1713407c868470ba30c6c9cc7f908f9b37c4595ab9983","kind":"article","url":"https://arxiv.org/abs/2611.24970","sourceUrl":"https://arxiv.org/abs/2611.24970","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-20T09:33:25.040Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.24970","checkedAt":"2026-11-21T02:50:09.268Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v9","mediaId":"7b5522d641a8a9e954e1713407c868470ba30c6c9cc7f908f9b37c4595ab9983","confidence":0.77,"provider":"typesafe","model":"jev-1.13.0","inputHash":"963fa8c1a480b1338ebb42769da2940de5fe4831fd74aaba2052a5b690f27e0d","decidedAt":"2026-11-20T09:33:26.969Z"},"provenance":{"textHash":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","observationId":"259055a23e97321af5fb25d52985b2affe45b1ab45708d171950c04b9b464224","retrievedAt":"2026-11-20T09:33:24.757Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"77e20c5c-de16-47d6-87ee-008af3d292c4"},"reviewer":{"model":"gpt-6-luna","runId":"e23cf6e4-104d-4471-8a16-e4b96c91cc97"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-20T09:46:22.249Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Nghiem, Huy","url":null,"kind":"unknown"},{"name":"Kostylew, Maria","url":null,"kind":"unknown"},{"name":"Kolt, Noam","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Nghiem, Huy","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Nghiem, Huy","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.24970","locator":"head/meta[name=author|citation_author]"},"assertionId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-21T02:50:09.268Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b","sourceUrl":"https://arxiv.org/abs/2611.24970","contentSha256":"a66413857eb73294dab24661a6e8b2cbca4c90d7698ab8e6d2caf8d0be14bb9c","textHash":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","observedAt":"2026-11-21T02:50:09.268Z"}},{"actor":{"name":"Kostylew, Maria","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kostylew, Maria","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.24970","locator":"head/meta[name=author|citation_author]"},"assertionId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-21T02:50:09.268Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b","sourceUrl":"https://arxiv.org/abs/2611.24970","contentSha256":"a66413857eb73294dab24661a6e8b2cbca4c90d7698ab8e6d2caf8d0be14bb9c","textHash":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","observedAt":"2026-11-21T02:50:09.268Z"}},{"actor":{"name":"Kolt, Noam","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kolt, Noam","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.24970","locator":"head/meta[name=author|citation_author]"},"assertionId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-21T02:50:09.268Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b","sourceUrl":"https://arxiv.org/abs/2611.24970","contentSha256":"a66413857eb73294dab24661a6e8b2cbca4c90d7698ab8e6d2caf8d0be14bb9c","textHash":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","observedAt":"2026-11-21T02:50:09.268Z"}}],"participationCoverage":{"total":3,"returned":3,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.24970","snapshotId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b","contentSha256":"a66413857eb73294dab24661a6e8b2cbca4c90d7698ab8e6d2caf8d0be14bb9c","textHash":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","observedAt":"2026-11-21T02:50:09.268Z","basis":"publisher-page-metadata","sourceLinks":44,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/39a03af8e0016d9eb89fd8ce4b96e88b2b5d165b3ae920052d7948093af467d2/source"}},"canonicalUrl":"https://escapemeridian.com/readings/huy-nghiem-maria-kostylew-and-noam-kolt-introduce-hirewatch-to-39a03af8","formats":{"html":"/readings/huy-nghiem-maria-kostylew-and-noam-kolt-introduce-hirewatch-to-39a03af8","markdown":"/readings/huy-nghiem-maria-kostylew-and-noam-kolt-introduce-hirewatch-to-39a03af8.md","json":"/readings/huy-nghiem-maria-kostylew-and-noam-kolt-introduce-hirewatch-to-39a03af8.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"conditions":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-llm","name":"Large language model","explanation":"A language model with many learned numerical settings, used to process and generate language.","referenceUrl":"https://developers.google.com/machine-learning/glossary#large-language-model"},{"id":"term-open-weights","name":"Open weights","explanation":"A model whose trained numbers are published so others can download, run and inspect it; the license and training data may still be restricted.","referenceUrl":"https://opensource.org/ai/open-weights"}],"entities":[{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"39a03af8e0016d9eb89fd8ce4b96e88b2b5d165b3ae920052d7948093af467d2","revision":"37d9fdad-8012-4260-84e9-e53f317f70c4","revisionKind":"publication-id","title":"Huy Nghiem, Maria Kostylew and Noam Kolt introduce HireWatch to test LLM compliance","url":"https://escapemeridian.com/readings/huy-nghiem-maria-kostylew-and-noam-kolt-introduce-hirewatch-to-39a03af8"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.24970","revision":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","revisionKind":"sha256-source-text","title":"HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure","url":"https://arxiv.org/abs/2611.24970"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings to this reading. Shared topics are not citations. Other record types need an explicit reference adapter."},"revisions":[{"id":"39a03af8e0016d9eb89fd8ce4b96e88b2b5d165b3ae920052d7948093af467d2","title":"Huy Nghiem, Maria Kostylew and Noam Kolt introduce HireWatch to test LLM compliance","argument":"Authors Huy Nghiem, Maria Kostylew and Noam Kolt introduce HireWatch, an evaluation of whether large language models (LLMs) comply with U.S. laws governing questions asked of job candidates. It uses a 200-item bank of lawful and unlawful interview questions, classified using federal statutes, regulations and agency guidance. Models select questions from the bank while preparing for interviews across occupations and contexts; the authors measure the fraction of unlawful questions selected. Across about 100,000 trials, the authors report that 18 closed and open-weight LLMs generally avoid unlawful questions under low pressure, but violations increase sharply under higher pressure. Explicit prompts to comply with law improve compliance rates, but do not eliminate violations. The authors’ results show a gap between an instruction to follow the law and performance under changing contextual pressure. As an Escape Meridian interpretation, the abstract describes question selection for interview preparation, not observations of real hiring decisions. The authors say they publicly release the code and data.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The evidence provided is the abstract; it does not specify the contextual-pressure conditions or provide detailed results by occupation or context. The reported evaluation measures selection of questions from a constructed bank, not observed behavior in real hiring decisions.","speaker":{"name":"Nghiem, Huy, Kostylew, Maria, Kolt, Noam","roleAtSource":"Article author"},"source":{"title":"HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.24970","publishedAt":"2026-11-16","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors introduce HireWatch to evaluate LLM compliance with U.S. laws governing questions that job candidates may be asked.","excerpt":"we introduce HireWatch, an evaluation that assesses whether LLMs comply with U.S. laws that govern the questions that job candidates may be asked","url":"https://arxiv.org/abs/2611.24970","relationship":"Source-stated"},{"text":"The evaluation uses a 200-item bank of lawful and unlawful interview questions classified using U.S. federal statutes, regulations and agency guidance.","excerpt":"We construct a 200-item bank of lawful and unlawful interview questions, whose legal classification is based on U.S. federal statutes, regulations, and agency guidance.","url":"https://arxiv.org/abs/2611.24970","relationship":"Source-stated"},{"text":"The authors evaluate 18 closed and open-weight LLMs across about 100,000 trials and report increased legal violations under higher contextual pressure.","excerpt":"Evaluation of 18 closed and open-weight LLMs across ~100,000 trials under different types of contextual pressure reveals that LLMs' legal compliance is brittle.","url":"https://arxiv.org/abs/2611.24970","relationship":"Source-stated"},{"text":"The authors report that explicit prompts to comply with law improve compliance rates but do not eliminate legal violations.","excerpt":"Explicit prompts to comply with law can improve compliance rates, but do not altogether eliminate legal violations.","url":"https://arxiv.org/abs/2611.24970","relationship":"Source-stated"},{"text":"The abstract describes selecting questions from a bank for interview preparation; it does not report observations of real hiring decisions.","excerpt":"We instruct LLMs to select questions from this bank in preparing for job interviews","url":"https://arxiv.org/abs/2611.24970","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.24970","checkedAt":"2026-11-21T02:50:09.268Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How do the reported compliance changes vary across the different types of contextual pressure, occupations and interview contexts tested?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Huy Nghiem, Maria Kostylew and Noam Kolt introduce HireWatch to test LLM compliance","summary":"Authors Huy Nghiem, Maria Kostylew and Noam Kolt introduce HireWatch, an evaluation of whether large language models (LLMs) comply with U.S. laws governing questions asked of job candidates. It uses a 200-item bank of lawful and unlawful interview questions, classified using federal statutes, regulations and agency guidance. Models select questions from the bank while preparing for interviews across occupations and contexts; the authors measure the fraction of unlawful questions selected. Across about 100,000 trials, the authors report that 18 closed and open-weight LLMs generally avoid unlawful questions under low pressure, but violations increase sharply under higher pressure. Explicit prompts to comply with law improve compliance rates, but do not eliminate violations. The authors’ results show a gap between an instruction to follow the law and performance under changing contextual pressure. As an Escape Meridian interpretation, the abstract describes question selection for interview preparation, not observations of real hiring decisions. The authors say they publicly release the code and data.","question":"How do the reported compliance changes vary across the different types of contextual pressure, occupations and interview contexts tested?","claims":[{"text":"The authors introduce HireWatch to evaluate LLM compliance with U.S. laws governing questions that job candidates may be asked.","excerpt":"we introduce HireWatch, an evaluation that assesses whether LLMs comply with U.S. laws that govern the questions that job candidates may be asked","support":"source-stated"},{"text":"The evaluation uses a 200-item bank of lawful and unlawful interview questions classified using U.S. federal statutes, regulations and agency guidance.","excerpt":"We construct a 200-item bank of lawful and unlawful interview questions, whose legal classification is based on U.S. federal statutes, regulations, and agency guidance.","support":"source-stated"},{"text":"The authors evaluate 18 closed and open-weight LLMs across about 100,000 trials and report increased legal violations under higher contextual pressure.","excerpt":"Evaluation of 18 closed and open-weight LLMs across ~100,000 trials under different types of contextual pressure reveals that LLMs' legal compliance is brittle.","support":"source-stated"},{"text":"The authors report that explicit prompts to comply with law improve compliance rates but do not eliminate legal violations.","excerpt":"Explicit prompts to comply with law can improve compliance rates, but do not altogether eliminate legal violations.","support":"source-stated"},{"text":"The abstract describes selecting questions from a bank for interview preparation; it does not report observations of real hiring decisions.","excerpt":"We instruct LLMs to select questions from this bank in preparing for job interviews","support":"interpretation"}],"limitations":["The evidence provided is the abstract; it does not specify the contextual-pressure conditions or provide detailed results by occupation or context.","The reported evaluation measures selection of questions from a constructed bank, not observed behavior in real hiring decisions."],"mediaId":"7b5522d641a8a9e954e1713407c868470ba30c6c9cc7f908f9b37c4595ab9983","correctionReason":null,"id":"39a03af8e0016d9eb89fd8ce4b96e88b2b5d165b3ae920052d7948093af467d2","publicationId":"37d9fdad-8012-4260-84e9-e53f317f70c4","version":1,"sourceUrl":"https://arxiv.org/abs/2611.24970","sourceTitle":"HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-16","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-20T05:01:27.854Z","createdAt":"2026-11-20T09:46:22.249Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"7b5522d641a8a9e954e1713407c868470ba30c6c9cc7f908f9b37c4595ab9983","kind":"article","url":"https://arxiv.org/abs/2611.24970","sourceUrl":"https://arxiv.org/abs/2611.24970","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-20T09:33:25.040Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.24970","checkedAt":"2026-11-21T02:50:09.268Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v9","mediaId":"7b5522d641a8a9e954e1713407c868470ba30c6c9cc7f908f9b37c4595ab9983","confidence":0.77,"provider":"typesafe","model":"jev-1.13.0","inputHash":"963fa8c1a480b1338ebb42769da2940de5fe4831fd74aaba2052a5b690f27e0d","decidedAt":"2026-11-20T09:33:26.969Z"},"provenance":{"textHash":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","observationId":"259055a23e97321af5fb25d52985b2affe45b1ab45708d171950c04b9b464224","retrievedAt":"2026-11-20T09:33:24.757Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"77e20c5c-de16-47d6-87ee-008af3d292c4"},"reviewer":{"model":"gpt-6-luna","runId":"e23cf6e4-104d-4471-8a16-e4b96c91cc97"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-20T09:46:22.249Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Nghiem, Huy","url":null,"kind":"unknown"},{"name":"Kostylew, Maria","url":null,"kind":"unknown"},{"name":"Kolt, Noam","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Nghiem, Huy","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Nghiem, Huy","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.24970","locator":"head/meta[name=author|citation_author]"},"assertionId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-21T02:50:09.268Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b","sourceUrl":"https://arxiv.org/abs/2611.24970","contentSha256":"a66413857eb73294dab24661a6e8b2cbca4c90d7698ab8e6d2caf8d0be14bb9c","textHash":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","observedAt":"2026-11-21T02:50:09.268Z"}},{"actor":{"name":"Kostylew, Maria","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kostylew, Maria","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.24970","locator":"head/meta[name=author|citation_author]"},"assertionId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-21T02:50:09.268Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b","sourceUrl":"https://arxiv.org/abs/2611.24970","contentSha256":"a66413857eb73294dab24661a6e8b2cbca4c90d7698ab8e6d2caf8d0be14bb9c","textHash":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","observedAt":"2026-11-21T02:50:09.268Z"}},{"actor":{"name":"Kolt, Noam","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kolt, Noam","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.24970","locator":"head/meta[name=author|citation_author]"},"assertionId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-21T02:50:09.268Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b","sourceUrl":"https://arxiv.org/abs/2611.24970","contentSha256":"a66413857eb73294dab24661a6e8b2cbca4c90d7698ab8e6d2caf8d0be14bb9c","textHash":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","observedAt":"2026-11-21T02:50:09.268Z"}}],"participationCoverage":{"total":3,"returned":3,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.24970","snapshotId":"a891c3bf5550e10b35f6a83a591934e0537f392366e1ed04b13fde8db8f1490b","contentSha256":"a66413857eb73294dab24661a6e8b2cbca4c90d7698ab8e6d2caf8d0be14bb9c","textHash":"d7b289bea5ee203b52cd863a06d6b9057ee49d03c040b50c23e5e80e9393daa1","observedAt":"2026-11-21T02:50:09.268Z","basis":"publisher-page-metadata","sourceLinks":44,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/39a03af8e0016d9eb89fd8ce4b96e88b2b5d165b3ae920052d7948093af467d2/source"}}}],"audits":[{"publicationId":"37d9fdad-8012-4260-84e9-e53f317f70c4","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly credits Huy Nghiem, Maria Kostylew and Noam Kolt as the authors of HireWatch. It keeps findings framed as the authors' reports, and its own inference is explicitly labeled as Escape Meridian interpretation.","excerpt":"Authors:Huy Nghiem, Maria Kostylew, Noam Kolt"},{"dimension":"summary","status":"uncertain","explanation":"The summary is accurate, but the central term contextual pressure is never explained. The reading does not say that the abstract leaves it undefined; that gap appears only in the limitations. A non-specialist cannot tell what higher pressure means. The reading also omits the abstract's motivation that LLM use in hiring pipelines is growing, which is what makes the result matter. Smallest repairs: add that framing, and state in the summary that the abstract does not describe the pressure conditions. The title's word compliance is vague; adding with U.S. employment law would clarify it.","excerpt":"The deployment of large language models (LLMs) in hiring pipelines is growing, yet existing evaluations generally overlook their compliance with legal rules."},{"dimension":"date","status":"pass","explanation":"originalPublished 2026-11-16 matches the v1 submission date shown on the arXiv page. It is not the later feed date of 2026-11-20.","excerpt":"[Submitted on 16 Nov 2026]"},{"dimension":"support","status":"pass","explanation":"All factual claims match the abstract: the 200-item bank, its federal legal basis, the 18 models, about 100,000 trials, sharply increased violations under higher pressure, partial improvement from explicit compliance prompts, and the code/data release. The interpretation about interview preparation rather than real hiring decisions is labeled and grounded in the task description. No unsupported benefits or costs are asserted.","excerpt":"While LLMs generally avoid selecting unlawful questions in low-pressure contexts, legal violations increase sharply under higher pressure."},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct arXiv abstract page for this paper. That is the most direct access to the source.","excerpt":null}],"createdAt":"2026-11-20T09:46:22.249Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}