{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2CCIWGGE2ZEBMHCKKEBWQVP2SN","short_pith_number":"pith:2CCIWGGE","schema_version":"1.0","canonical_sha256":"d0848b18c4d648161c4a51036855fa9379780983ff5c60522081d0b195ecf92f","source":{"kind":"arxiv","id":"2508.16748","version":1},"attestation_state":"computed","paper":{"title":"FAIRWELL: Fair Multimodal Self-Supervised Learning for Wellbeing Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abtin Mogharabin, Hatice Gunes, Jiaee Cheong, Paul Liang, Sinan Kalkan","submitted_at":"2025-08-22T19:03:06Z","abstract_excerpt":"Early efforts on leveraging self-supervised learning (SSL) to improve machine learning (ML) fairness has proven promising. However, such an approach has yet to be explored within a multimodal context. Prior work has shown that, within a multimodal setting, different modalities contain modality-unique information that can complement information of other modalities. Leveraging on this, we propose a novel subject-level loss function to learn fairer representations via the following three mechanisms, adapting the variance-invariance-covariance regularization (VICReg) method: (i) the variance term,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.16748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-22T19:03:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e2183cb74fa2d050a655fab70d8bf3d12bb192303b557ba3dde6c71b6292311","abstract_canon_sha256":"66dd388bfa393c89a7608688fd0a32dd3f583077b71abc4b920035996eb59463"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:02.889238Z","signature_b64":"MWyO/Udg2gTrNZYlrVkR2mfYW0P+6fvniXLojnmlrgf7j6fYVSzz6GBfnzjgLjmVUvIvm2puPETTCl90dwseDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0848b18c4d648161c4a51036855fa9379780983ff5c60522081d0b195ecf92f","last_reissued_at":"2026-07-05T11:58:02.888685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:02.888685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FAIRWELL: Fair Multimodal Self-Supervised Learning for Wellbeing Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abtin Mogharabin, Hatice Gunes, Jiaee Cheong, Paul Liang, Sinan Kalkan","submitted_at":"2025-08-22T19:03:06Z","abstract_excerpt":"Early efforts on leveraging self-supervised learning (SSL) to improve machine learning (ML) fairness has proven promising. However, such an approach has yet to be explored within a multimodal context. Prior work has shown that, within a multimodal setting, different modalities contain modality-unique information that can complement information of other modalities. Leveraging on this, we propose a novel subject-level loss function to learn fairer representations via the following three mechanisms, adapting the variance-invariance-covariance regularization (VICReg) method: (i) the variance term,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16748","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.16748/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.16748","created_at":"2026-07-05T11:58:02.888757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16748v1","created_at":"2026-07-05T11:58:02.888757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16748","created_at":"2026-07-05T11:58:02.888757+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CCIWGGE2ZEB","created_at":"2026-07-05T11:58:02.888757+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CCIWGGE2ZEBMHCK","created_at":"2026-07-05T11:58:02.888757+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CCIWGGE","created_at":"2026-07-05T11:58:02.888757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23786","citing_title":"FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CCIWGGE2ZEBMHCKKEBWQVP2SN","json":"https://pith.science/pith/2CCIWGGE2ZEBMHCKKEBWQVP2SN.json","graph_json":"https://pith.science/api/pith-number/2CCIWGGE2ZEBMHCKKEBWQVP2SN/graph.json","events_json":"https://pith.science/api/pith-number/2CCIWGGE2ZEBMHCKKEBWQVP2SN/events.json","paper":"https://pith.science/paper/2CCIWGGE"},"agent_actions":{"view_html":"https://pith.science/pith/2CCIWGGE2ZEBMHCKKEBWQVP2SN","download_json":"https://pith.science/pith/2CCIWGGE2ZEBMHCKKEBWQVP2SN.json","view_paper":"https://pith.science/paper/2CCIWGGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16748&json=true","fetch_graph":"https://pith.science/api/pith-number/2CCIWGGE2ZEBMHCKKEBWQVP2SN/graph.json","fetch_events":"https://pith.science/api/pith-number/2CCIWGGE2ZEBMHCKKEBWQVP2SN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CCIWGGE2ZEBMHCKKEBWQVP2SN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CCIWGGE2ZEBMHCKKEBWQVP2SN/action/storage_attestation","attest_author":"https://pith.science/pith/2CCIWGGE2ZEBMHCKKEBWQVP2SN/action/author_attestation","sign_citation":"https://pith.science/pith/2CCIWGGE2ZEBMHCKKEBWQVP2SN/action/citation_signature","submit_replication":"https://pith.science/pith/2CCIWGGE2ZEBMHCKKEBWQVP2SN/action/replication_record"}},"created_at":"2026-07-05T11:58:02.888757+00:00","updated_at":"2026-07-05T11:58:02.888757+00:00"}