{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XOO2MUNBVES7S3T2KLUS57NGIF","short_pith_number":"pith:XOO2MUNB","schema_version":"1.0","canonical_sha256":"bb9da651a1a925f96e7a52e92efda6415eaef6d9705ff7630434add079c81dc4","source":{"kind":"arxiv","id":"2402.14611","version":2},"attestation_state":"computed","paper":{"title":"Overcoming Dimensional Collapse in Self-supervised Contrastive Learning for Medical Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Didier Mutter, Jamshid Hassanpour, Nicolas Padoy, Vinkle Srivastav","submitted_at":"2024-02-22T15:02:13Z","abstract_excerpt":"Self-supervised learning (SSL) approaches have achieved great success when the amount of labeled data is limited. Within SSL, models learn robust feature representations by solving pretext tasks. One such pretext task is contrastive learning, which involves forming pairs of similar and dissimilar input samples, guiding the model to distinguish between them. In this work, we investigate the application of contrastive learning to the domain of medical image analysis. Our findings reveal that MoCo v2, a state-of-the-art contrastive learning method, encounters dimensional collapse when applied to "},"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":"2402.14611","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T15:02:13Z","cross_cats_sorted":[],"title_canon_sha256":"c3f27c77b32a12c63e1a31985b2606ab4bb23e75655ecd0fe4de658611ef327f","abstract_canon_sha256":"33bf4a904e39cc6ec9c3cc71386fd0ef7899e2dfb1d603789be5509862c49d77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:37.408061Z","signature_b64":"iu7YUm4xHqiphqc0bUhsXgltJyKxerTcHcHw1qjYkybPEGqizCfH/AE+HlYdwonqamY9dK7qXQJAaimsf3IDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb9da651a1a925f96e7a52e92efda6415eaef6d9705ff7630434add079c81dc4","last_reissued_at":"2026-07-05T07:49:37.407485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:37.407485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Dimensional Collapse in Self-supervised Contrastive Learning for Medical Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Didier Mutter, Jamshid Hassanpour, Nicolas Padoy, Vinkle Srivastav","submitted_at":"2024-02-22T15:02:13Z","abstract_excerpt":"Self-supervised learning (SSL) approaches have achieved great success when the amount of labeled data is limited. Within SSL, models learn robust feature representations by solving pretext tasks. One such pretext task is contrastive learning, which involves forming pairs of similar and dissimilar input samples, guiding the model to distinguish between them. In this work, we investigate the application of contrastive learning to the domain of medical image analysis. Our findings reveal that MoCo v2, a state-of-the-art contrastive learning method, encounters dimensional collapse when applied to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14611","kind":"arxiv","version":2},"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/2402.14611/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":"2402.14611","created_at":"2026-07-05T07:49:37.407554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14611v2","created_at":"2026-07-05T07:49:37.407554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14611","created_at":"2026-07-05T07:49:37.407554+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOO2MUNBVES7","created_at":"2026-07-05T07:49:37.407554+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOO2MUNBVES7S3T2","created_at":"2026-07-05T07:49:37.407554+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOO2MUNB","created_at":"2026-07-05T07:49:37.407554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18804","citing_title":"Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOO2MUNBVES7S3T2KLUS57NGIF","json":"https://pith.science/pith/XOO2MUNBVES7S3T2KLUS57NGIF.json","graph_json":"https://pith.science/api/pith-number/XOO2MUNBVES7S3T2KLUS57NGIF/graph.json","events_json":"https://pith.science/api/pith-number/XOO2MUNBVES7S3T2KLUS57NGIF/events.json","paper":"https://pith.science/paper/XOO2MUNB"},"agent_actions":{"view_html":"https://pith.science/pith/XOO2MUNBVES7S3T2KLUS57NGIF","download_json":"https://pith.science/pith/XOO2MUNBVES7S3T2KLUS57NGIF.json","view_paper":"https://pith.science/paper/XOO2MUNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14611&json=true","fetch_graph":"https://pith.science/api/pith-number/XOO2MUNBVES7S3T2KLUS57NGIF/graph.json","fetch_events":"https://pith.science/api/pith-number/XOO2MUNBVES7S3T2KLUS57NGIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOO2MUNBVES7S3T2KLUS57NGIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOO2MUNBVES7S3T2KLUS57NGIF/action/storage_attestation","attest_author":"https://pith.science/pith/XOO2MUNBVES7S3T2KLUS57NGIF/action/author_attestation","sign_citation":"https://pith.science/pith/XOO2MUNBVES7S3T2KLUS57NGIF/action/citation_signature","submit_replication":"https://pith.science/pith/XOO2MUNBVES7S3T2KLUS57NGIF/action/replication_record"}},"created_at":"2026-07-05T07:49:37.407554+00:00","updated_at":"2026-07-05T07:49:37.407554+00:00"}