{"id":"7f8392ea376d5870e69392e04174d5a155236ead3a4d3cbf89f0f111afe23707","title":"Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses","argument":"The authors investigate whether Self-Supervised Learning (SSL) can reduce the need for labelled expressions when training Facial Expression Recognition (FER) on optomyographic (OMG) smart glasses. They pretrain a Vision Transformer on unlabelled OCOsense recordings, then finetune it for five-class FER and evaluate it using person-independent cross-validation. The authors report that pretraining improves performance across label budgets from 5% to 100%; with only 5% of the labels, the pretrained model outperforms a model trained from scratch using all labels. They argue that this makes SSL pretraining a practical way to reduce labelling cost for smart eyewear FER, and discuss possible implications for personalization and continual adaptation. The reported result concerns this study’s setup; the abstract does not give performance figures or establish how the approach would fare in deployment beyond that evaluation.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The publisher-page evidence provides the abstract, but not performance figures or detailed evaluation results, so the size and practical significance of the reported improvement cannot be assessed here. The results described are for OCOsense recordings and five-class FER under person-independent cross-validation; the evidence does not establish performance in other settings.","speaker":{"name":"Gao, Zhengtao, De Bona, Francesco Bombassei, Alchieri, Leonardo, Kiprijanovska, Ivana, Stankoski, Simon, Sofronievski, Bojan, Gjoreski, Hristijan, Langheinrich, Marc, Gjoreski, Martin","roleAtSource":"Article author"},"source":{"title":"Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.05711","publishedAt":"2026-11-03","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors evaluate SSL pretraining for five-class FER on optomyographic smart glasses, using unlabelled OCOsense recordings and person-independent cross-validation.","excerpt":"We pretrain a Vision Transformer with a masked-autoencoder objective on unlabelled OCOsense recordings and finetune it for five-class FER under person-independent cross-validation.","url":"https://arxiv.org/abs/2611.05711","relationship":"Source-stated"},{"text":"The authors report improved performance across tested label budgets, including a pretrained model using 5% of labels outperforming a from-scratch model using all labels.","excerpt":"with only 5% of the labels, the pretrained model outperforms the from-scratch model trained with all labels.","url":"https://arxiv.org/abs/2611.05711","relationship":"Source-stated"},{"text":"The authors characterize SSL pretraining as a practical way to reduce labelling cost for smart eyewear FER and discuss possible future personalization and continual adaptation.","excerpt":"Our results show that SSL pretraining is a practical way to reduce labelling cost for smart eyewear FER, and we discuss the implications for future personalization and continual adaptation.","url":"https://arxiv.org/abs/2611.05711","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05711","checkedAt":"2026-11-09T13:56:07.468Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Does the reported advantage persist across people and settings beyond the study’s person-independent cross-validation?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses","summary":"The authors investigate whether Self-Supervised Learning (SSL) can reduce the need for labelled expressions when training Facial Expression Recognition (FER) on optomyographic (OMG) smart glasses. They pretrain a Vision Transformer on unlabelled OCOsense recordings, then finetune it for five-class FER and evaluate it using person-independent cross-validation. The authors report that pretraining improves performance across label budgets from 5% to 100%; with only 5% of the labels, the pretrained model outperforms a model trained from scratch using all labels. They argue that this makes SSL pretraining a practical way to reduce labelling cost for smart eyewear FER, and discuss possible implications for personalization and continual adaptation. The reported result concerns this study’s setup; the abstract does not give performance figures or establish how the approach would fare in deployment beyond that evaluation.","question":"Does the reported advantage persist across people and settings beyond the study’s person-independent cross-validation?","claims":[{"text":"The authors evaluate SSL pretraining for five-class FER on optomyographic smart glasses, using unlabelled OCOsense recordings and person-independent cross-validation.","excerpt":"We pretrain a Vision Transformer with a masked-autoencoder objective on unlabelled OCOsense recordings and finetune it for five-class FER under person-independent cross-validation.","support":"source-stated"},{"text":"The authors report improved performance across tested label budgets, including a pretrained model using 5% of labels outperforming a from-scratch model using all labels.","excerpt":"with only 5% of the labels, the pretrained model outperforms the from-scratch model trained with all labels.","support":"source-stated"},{"text":"The authors characterize SSL pretraining as a practical way to reduce labelling cost for smart eyewear FER and discuss possible future personalization and continual adaptation.","excerpt":"Our results show that SSL pretraining is a practical way to reduce labelling cost for smart eyewear FER, and we discuss the implications for future personalization and continual adaptation.","support":"source-stated"}],"limitations":["The publisher-page evidence provides the abstract, but not performance figures or detailed evaluation results, so the size and practical significance of the reported improvement cannot be assessed here.","The results described are for OCOsense recordings and five-class FER under person-independent cross-validation; the evidence does not establish performance in other settings."],"mediaId":"eaa34d56bdf5502efa8f5a5ba2379e3ebab5a18473251855d064b347f2b542a6","correctionReason":null,"id":"7f8392ea376d5870e69392e04174d5a155236ead3a4d3cbf89f0f111afe23707","publicationId":"53a1b03f-7104-41f3-838e-435ff3f5ead9","version":1,"sourceUrl":"https://arxiv.org/abs/2611.05711","sourceTitle":"Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-03","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:06:40.396Z","createdAt":"2026-11-09T13:24:21.065Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"eaa34d56bdf5502efa8f5a5ba2379e3ebab5a18473251855d064b347f2b542a6","kind":"article","url":"https://arxiv.org/abs/2611.05711","sourceUrl":"https://arxiv.org/abs/2611.05711","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T13:23:19.925Z","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/2611.05711","checkedAt":"2026-11-09T13:56:07.468Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"eaa34d56bdf5502efa8f5a5ba2379e3ebab5a18473251855d064b347f2b542a6","confidence":0.77,"provider":"typesafe","model":"jev-1.13.0","inputHash":"ff3b3e6daff91fa16d7d87a0bcd6ee596f878054b8c7de17c9c1c9292eb43456","decidedAt":"2026-11-09T13:23:23.057Z"},"provenance":{"textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observationId":"bd9b375ed5a821677f09e70001285c69c7c0608505baa3ee435a983a47ea0171","retrievedAt":"2026-11-09T13:23:19.358Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"5631abab-19ba-4dfb-854d-577704f0d11a"},"reviewer":{"model":"gpt-6-luna","runId":"d929cc35-ae04-4e62-88ba-72bcd67e4902"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-09T13:24:21.065Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Gao, Zhengtao","url":null,"kind":"unknown"},{"name":"De Bona, Francesco Bombassei","url":null,"kind":"unknown"},{"name":"Alchieri, Leonardo","url":null,"kind":"unknown"},{"name":"Kiprijanovska, Ivana","url":null,"kind":"unknown"},{"name":"Stankoski, Simon","url":null,"kind":"unknown"},{"name":"Sofronievski, Bojan","url":null,"kind":"unknown"},{"name":"Gjoreski, Hristijan","url":null,"kind":"unknown"},{"name":"Langheinrich, Marc","url":null,"kind":"unknown"},{"name":"Gjoreski, Martin","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Gao, Zhengtao","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Gao, Zhengtao","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"De Bona, Francesco Bombassei","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"De Bona, Francesco Bombassei","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Alchieri, Leonardo","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Alchieri, Leonardo","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Kiprijanovska, Ivana","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kiprijanovska, Ivana","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Stankoski, Simon","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Stankoski, Simon","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Sofronievski, Bojan","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Sofronievski, Bojan","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:5","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Gjoreski, Hristijan","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Gjoreski, Hristijan","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:6","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Langheinrich, Marc","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Langheinrich, Marc","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:7","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Gjoreski, Martin","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Gjoreski, Martin","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:8","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}}],"participationCoverage":{"total":9,"returned":9,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.05711","snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z","basis":"publisher-page-metadata","sourceLinks":48,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/7f8392ea376d5870e69392e04174d5a155236ead3a4d3cbf89f0f111afe23707/source"}},"canonicalUrl":"https://escapemeridian.com/readings/self-supervised-pretraining-for-label-efficient-facial-7f8392ea","formats":{"html":"/readings/self-supervised-pretraining-for-label-efficient-facial-7f8392ea","markdown":"/readings/self-supervised-pretraining-for-label-efficient-facial-7f8392ea.md","json":"/readings/self-supervised-pretraining-for-label-efficient-facial-7f8392ea.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":[],"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-pre-training","name":"Pre-training","explanation":"A model's initial training on a large dataset, before further adaptation for particular uses.","referenceUrl":"https://developers.google.com/machine-learning/glossary#pre-training"}],"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":"7f8392ea376d5870e69392e04174d5a155236ead3a4d3cbf89f0f111afe23707","revision":"53a1b03f-7104-41f3-838e-435ff3f5ead9","revisionKind":"publication-id","title":"Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses","url":"https://escapemeridian.com/readings/self-supervised-pretraining-for-label-efficient-facial-7f8392ea"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.05711","revision":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","revisionKind":"sha256-source-text","title":"Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses","url":"https://arxiv.org/abs/2611.05711"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"7f8392ea376d5870e69392e04174d5a155236ead3a4d3cbf89f0f111afe23707","title":"Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses","argument":"The authors investigate whether Self-Supervised Learning (SSL) can reduce the need for labelled expressions when training Facial Expression Recognition (FER) on optomyographic (OMG) smart glasses. They pretrain a Vision Transformer on unlabelled OCOsense recordings, then finetune it for five-class FER and evaluate it using person-independent cross-validation. The authors report that pretraining improves performance across label budgets from 5% to 100%; with only 5% of the labels, the pretrained model outperforms a model trained from scratch using all labels. They argue that this makes SSL pretraining a practical way to reduce labelling cost for smart eyewear FER, and discuss possible implications for personalization and continual adaptation. The reported result concerns this study’s setup; the abstract does not give performance figures or establish how the approach would fare in deployment beyond that evaluation.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The publisher-page evidence provides the abstract, but not performance figures or detailed evaluation results, so the size and practical significance of the reported improvement cannot be assessed here. The results described are for OCOsense recordings and five-class FER under person-independent cross-validation; the evidence does not establish performance in other settings.","speaker":{"name":"Gao, Zhengtao, De Bona, Francesco Bombassei, Alchieri, Leonardo, Kiprijanovska, Ivana, Stankoski, Simon, Sofronievski, Bojan, Gjoreski, Hristijan, Langheinrich, Marc, Gjoreski, Martin","roleAtSource":"Article author"},"source":{"title":"Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.05711","publishedAt":"2026-11-03","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors evaluate SSL pretraining for five-class FER on optomyographic smart glasses, using unlabelled OCOsense recordings and person-independent cross-validation.","excerpt":"We pretrain a Vision Transformer with a masked-autoencoder objective on unlabelled OCOsense recordings and finetune it for five-class FER under person-independent cross-validation.","url":"https://arxiv.org/abs/2611.05711","relationship":"Source-stated"},{"text":"The authors report improved performance across tested label budgets, including a pretrained model using 5% of labels outperforming a from-scratch model using all labels.","excerpt":"with only 5% of the labels, the pretrained model outperforms the from-scratch model trained with all labels.","url":"https://arxiv.org/abs/2611.05711","relationship":"Source-stated"},{"text":"The authors characterize SSL pretraining as a practical way to reduce labelling cost for smart eyewear FER and discuss possible future personalization and continual adaptation.","excerpt":"Our results show that SSL pretraining is a practical way to reduce labelling cost for smart eyewear FER, and we discuss the implications for future personalization and continual adaptation.","url":"https://arxiv.org/abs/2611.05711","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05711","checkedAt":"2026-11-09T13:56:07.468Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Does the reported advantage persist across people and settings beyond the study’s person-independent cross-validation?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses","summary":"The authors investigate whether Self-Supervised Learning (SSL) can reduce the need for labelled expressions when training Facial Expression Recognition (FER) on optomyographic (OMG) smart glasses. They pretrain a Vision Transformer on unlabelled OCOsense recordings, then finetune it for five-class FER and evaluate it using person-independent cross-validation. The authors report that pretraining improves performance across label budgets from 5% to 100%; with only 5% of the labels, the pretrained model outperforms a model trained from scratch using all labels. They argue that this makes SSL pretraining a practical way to reduce labelling cost for smart eyewear FER, and discuss possible implications for personalization and continual adaptation. The reported result concerns this study’s setup; the abstract does not give performance figures or establish how the approach would fare in deployment beyond that evaluation.","question":"Does the reported advantage persist across people and settings beyond the study’s person-independent cross-validation?","claims":[{"text":"The authors evaluate SSL pretraining for five-class FER on optomyographic smart glasses, using unlabelled OCOsense recordings and person-independent cross-validation.","excerpt":"We pretrain a Vision Transformer with a masked-autoencoder objective on unlabelled OCOsense recordings and finetune it for five-class FER under person-independent cross-validation.","support":"source-stated"},{"text":"The authors report improved performance across tested label budgets, including a pretrained model using 5% of labels outperforming a from-scratch model using all labels.","excerpt":"with only 5% of the labels, the pretrained model outperforms the from-scratch model trained with all labels.","support":"source-stated"},{"text":"The authors characterize SSL pretraining as a practical way to reduce labelling cost for smart eyewear FER and discuss possible future personalization and continual adaptation.","excerpt":"Our results show that SSL pretraining is a practical way to reduce labelling cost for smart eyewear FER, and we discuss the implications for future personalization and continual adaptation.","support":"source-stated"}],"limitations":["The publisher-page evidence provides the abstract, but not performance figures or detailed evaluation results, so the size and practical significance of the reported improvement cannot be assessed here.","The results described are for OCOsense recordings and five-class FER under person-independent cross-validation; the evidence does not establish performance in other settings."],"mediaId":"eaa34d56bdf5502efa8f5a5ba2379e3ebab5a18473251855d064b347f2b542a6","correctionReason":null,"id":"7f8392ea376d5870e69392e04174d5a155236ead3a4d3cbf89f0f111afe23707","publicationId":"53a1b03f-7104-41f3-838e-435ff3f5ead9","version":1,"sourceUrl":"https://arxiv.org/abs/2611.05711","sourceTitle":"Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-03","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:06:40.396Z","createdAt":"2026-11-09T13:24:21.065Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"eaa34d56bdf5502efa8f5a5ba2379e3ebab5a18473251855d064b347f2b542a6","kind":"article","url":"https://arxiv.org/abs/2611.05711","sourceUrl":"https://arxiv.org/abs/2611.05711","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T13:23:19.925Z","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/2611.05711","checkedAt":"2026-11-09T13:56:07.468Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"eaa34d56bdf5502efa8f5a5ba2379e3ebab5a18473251855d064b347f2b542a6","confidence":0.77,"provider":"typesafe","model":"jev-1.13.0","inputHash":"ff3b3e6daff91fa16d7d87a0bcd6ee596f878054b8c7de17c9c1c9292eb43456","decidedAt":"2026-11-09T13:23:23.057Z"},"provenance":{"textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observationId":"bd9b375ed5a821677f09e70001285c69c7c0608505baa3ee435a983a47ea0171","retrievedAt":"2026-11-09T13:23:19.358Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"5631abab-19ba-4dfb-854d-577704f0d11a"},"reviewer":{"model":"gpt-6-luna","runId":"d929cc35-ae04-4e62-88ba-72bcd67e4902"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-09T13:24:21.065Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Gao, Zhengtao","url":null,"kind":"unknown"},{"name":"De Bona, Francesco Bombassei","url":null,"kind":"unknown"},{"name":"Alchieri, Leonardo","url":null,"kind":"unknown"},{"name":"Kiprijanovska, Ivana","url":null,"kind":"unknown"},{"name":"Stankoski, Simon","url":null,"kind":"unknown"},{"name":"Sofronievski, Bojan","url":null,"kind":"unknown"},{"name":"Gjoreski, Hristijan","url":null,"kind":"unknown"},{"name":"Langheinrich, Marc","url":null,"kind":"unknown"},{"name":"Gjoreski, Martin","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Gao, Zhengtao","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Gao, Zhengtao","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"De Bona, Francesco Bombassei","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"De Bona, Francesco Bombassei","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Alchieri, Leonardo","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Alchieri, Leonardo","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Kiprijanovska, Ivana","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kiprijanovska, Ivana","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Stankoski, Simon","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Stankoski, Simon","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Sofronievski, Bojan","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Sofronievski, Bojan","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:5","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Gjoreski, Hristijan","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Gjoreski, Hristijan","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:6","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Langheinrich, Marc","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Langheinrich, Marc","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:7","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}},{"actor":{"name":"Gjoreski, Martin","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Gjoreski, Martin","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05711","locator":"head/meta[name=author|citation_author]"},"assertionId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f:participation:8","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T13:56:07.468Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","sourceUrl":"https://arxiv.org/abs/2611.05711","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z"}}],"participationCoverage":{"total":9,"returned":9,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.05711","snapshotId":"3a6fe5cdf0742b80fab7abd966440f51e2e390bc85d9dbe3dc0573d759eb6d0f","contentSha256":"04a44c13f91ada4e6e213e239a8cef8cbe09b46fbae6f25f2897969c2b4ab455","textHash":"32eba00f7a3093f654ee9449bc44ddbab4753189c2f289fc414c39d43c8c8e57","observedAt":"2026-11-09T13:56:07.468Z","basis":"publisher-page-metadata","sourceLinks":48,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/7f8392ea376d5870e69392e04174d5a155236ead3a4d3cbf89f0f111afe23707/source"}}}],"audits":[{"publicationId":"53a1b03f-7104-41f3-838e-435ff3f5ead9","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The draft consistently attributes the method, results and the practicality claim to the paper's authors. It keeps the conclusion that SSL is practical as the authors' assertion rather than stating it as established fact.","excerpt":"Our results show that SSL pretraining is a practical way to reduce labelling cost for smart eyewear FER"},{"dimension":"summary","status":"uncertain","explanation":"The summary is faithful, but a non-specialist would struggle with it. Central terms are left unexplained: optomyographic (OMG) glasses, Self-Supervised Learning, finetune, label budgets and person-independent cross-validation. It also drops the source's own stated motivation, privacy-preserving, camera-free affect sensing for health and well-being, which is the main reason the work matters. The masked-autoencoder objective is omitted as well. Smallest repair: add the source's motivation sentence, and add or suggest tooltips for OMG, SSL, masked-autoencoder and person-independent cross-validation.","excerpt":"enables privacy-preserving, camera-free affect sensing for health and well-being"},{"dimension":"date","status":"pass","explanation":"originalPublished is 2026-11-03, which matches the arXiv v1 submission date. The feed date of 2026-11-05 is later and correctly not used.","excerpt":"[Submitted on 3 Nov 2026]"},{"dimension":"support","status":"pass","explanation":"Each claim maps to verbatim abstract text, and the limitations accurately note that no figures are given and that scope is limited to OCOsense and the study's setup. The draft implies no benefits or costs beyond the source. The question is a legitimate open issue, though person-independent validation already tests generalization across held-out people, so its framing slightly overlaps with what was evaluated.","excerpt":"Across label budgets from 5% to 100%, pretraining consistently improves performance"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified arXiv abstract page, which is the direct original source.","excerpt":null}],"createdAt":"2026-11-09T13:24:21.065Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}