{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5U5RHM2IYIOMWNZIV2GQTRC72Q","short_pith_number":"pith:5U5RHM2I","schema_version":"1.0","canonical_sha256":"ed3b13b348c21ccb3728ae8d09c45fd41d9c25d3e023a08d60f449700966a283","source":{"kind":"arxiv","id":"2012.03583","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Axel Camara, Axel de Lavergne, Olivier Dehaene, Olivier Moindrot, Pierre Courtiol","submitted_at":"2020-12-07T10:59:38Z","abstract_excerpt":"One of the biggest challenges for applying machine learning to histopathology is weak supervision: whole-slide images have billions of pixels yet often only one global label. The state of the art therefore relies on strongly-supervised model training using additional local annotations from domain experts. However, in the absence of detailed annotations, most weakly-supervised approaches depend on a frozen feature extractor pre-trained on ImageNet. We identify this as a key weakness and propose to train an in-domain feature extractor on histology images using MoCo v2, a recent self-supervised l"},"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":"2012.03583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-12-07T10:59:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d9796c6f6df148999b6fa7113770c34aedc037936a97ed4737e32527e105b722","abstract_canon_sha256":"aa86270b2cf8c247c7c0fc50234bf9dd03685f37e4bc4d675d8846d239a05331"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:31.482062Z","signature_b64":"VMa7yMH32vsMSNqXWatCT+VvIpnjnQzxCpsdD6qN+erzGP3eWXcSoUr8MkRFKmsCyYgvD/GE3X10J00+Yi83Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed3b13b348c21ccb3728ae8d09c45fd41d9c25d3e023a08d60f449700966a283","last_reissued_at":"2026-07-05T01:57:31.481616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:31.481616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Axel Camara, Axel de Lavergne, Olivier Dehaene, Olivier Moindrot, Pierre Courtiol","submitted_at":"2020-12-07T10:59:38Z","abstract_excerpt":"One of the biggest challenges for applying machine learning to histopathology is weak supervision: whole-slide images have billions of pixels yet often only one global label. The state of the art therefore relies on strongly-supervised model training using additional local annotations from domain experts. However, in the absence of detailed annotations, most weakly-supervised approaches depend on a frozen feature extractor pre-trained on ImageNet. We identify this as a key weakness and propose to train an in-domain feature extractor on histology images using MoCo v2, a recent self-supervised l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.03583","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/2012.03583/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":"2012.03583","created_at":"2026-07-05T01:57:31.481666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.03583v1","created_at":"2026-07-05T01:57:31.481666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.03583","created_at":"2026-07-05T01:57:31.481666+00:00"},{"alias_kind":"pith_short_12","alias_value":"5U5RHM2IYIOM","created_at":"2026-07-05T01:57:31.481666+00:00"},{"alias_kind":"pith_short_16","alias_value":"5U5RHM2IYIOMWNZI","created_at":"2026-07-05T01:57:31.481666+00:00"},{"alias_kind":"pith_short_8","alias_value":"5U5RHM2I","created_at":"2026-07-05T01:57:31.481666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01370","citing_title":"Understanding Synergistic Interactions among Pathology Foundation Models via Adaptive Fusion","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5U5RHM2IYIOMWNZIV2GQTRC72Q","json":"https://pith.science/pith/5U5RHM2IYIOMWNZIV2GQTRC72Q.json","graph_json":"https://pith.science/api/pith-number/5U5RHM2IYIOMWNZIV2GQTRC72Q/graph.json","events_json":"https://pith.science/api/pith-number/5U5RHM2IYIOMWNZIV2GQTRC72Q/events.json","paper":"https://pith.science/paper/5U5RHM2I"},"agent_actions":{"view_html":"https://pith.science/pith/5U5RHM2IYIOMWNZIV2GQTRC72Q","download_json":"https://pith.science/pith/5U5RHM2IYIOMWNZIV2GQTRC72Q.json","view_paper":"https://pith.science/paper/5U5RHM2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.03583&json=true","fetch_graph":"https://pith.science/api/pith-number/5U5RHM2IYIOMWNZIV2GQTRC72Q/graph.json","fetch_events":"https://pith.science/api/pith-number/5U5RHM2IYIOMWNZIV2GQTRC72Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5U5RHM2IYIOMWNZIV2GQTRC72Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5U5RHM2IYIOMWNZIV2GQTRC72Q/action/storage_attestation","attest_author":"https://pith.science/pith/5U5RHM2IYIOMWNZIV2GQTRC72Q/action/author_attestation","sign_citation":"https://pith.science/pith/5U5RHM2IYIOMWNZIV2GQTRC72Q/action/citation_signature","submit_replication":"https://pith.science/pith/5U5RHM2IYIOMWNZIV2GQTRC72Q/action/replication_record"}},"created_at":"2026-07-05T01:57:31.481666+00:00","updated_at":"2026-07-05T01:57:31.481666+00:00"}