{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PSSPTBC77GW65F7HTNXGYPNPZF","short_pith_number":"pith:PSSPTBC7","schema_version":"1.0","canonical_sha256":"7ca4f9845ff9adee97e79b6e6c3dafc943649b24346ec680b5570c5a4455f124","source":{"kind":"arxiv","id":"2409.09173","version":1},"attestation_state":"computed","paper":{"title":"Phikon-v2, A large and public feature extractor for biomarker prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Alexandre Filiot, Alice Mac Kain, Charlie Saillard, Paul Jacob","submitted_at":"2024-09-13T20:12:29Z","abstract_excerpt":"Gathering histopathology slides from over 100 publicly available cohorts, we compile a diverse dataset of 460 million pathology tiles covering more than 30 cancer sites. Using this dataset, we train a large self-supervised vision transformer using DINOv2 and publicly release one iteration of this model for further experimentation, coined Phikon-v2. While trained on publicly available histology slides, Phikon-v2 surpasses our previously released model (Phikon) and performs on par with other histopathology foundation models (FM) trained on proprietary data. Our benchmarks include eight slide-lev"},"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":"2409.09173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2024-09-13T20:12:29Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2d7cee211fe72cef16b01f440d95d91b67fedb19ade360e21a9358c0e32a6784","abstract_canon_sha256":"d90590e96d49b5919b1f2723c5d88776139e5485657815482d0a087bfdf4fc10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:05.948291Z","signature_b64":"48Im09xED8hYM/LYCmDw7cBX9VXZcYtP0bu3IOLIVi7rm9QMTN53lxTW/bjFcQY/W/uV0Q4ti27M96rI7QHjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ca4f9845ff9adee97e79b6e6c3dafc943649b24346ec680b5570c5a4455f124","last_reissued_at":"2026-07-05T09:07:05.947821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:05.947821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phikon-v2, A large and public feature extractor for biomarker prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Alexandre Filiot, Alice Mac Kain, Charlie Saillard, Paul Jacob","submitted_at":"2024-09-13T20:12:29Z","abstract_excerpt":"Gathering histopathology slides from over 100 publicly available cohorts, we compile a diverse dataset of 460 million pathology tiles covering more than 30 cancer sites. Using this dataset, we train a large self-supervised vision transformer using DINOv2 and publicly release one iteration of this model for further experimentation, coined Phikon-v2. While trained on publicly available histology slides, Phikon-v2 surpasses our previously released model (Phikon) and performs on par with other histopathology foundation models (FM) trained on proprietary data. Our benchmarks include eight slide-lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09173","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/2409.09173/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":"2409.09173","created_at":"2026-07-05T09:07:05.947879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09173v1","created_at":"2026-07-05T09:07:05.947879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09173","created_at":"2026-07-05T09:07:05.947879+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSSPTBC77GW6","created_at":"2026-07-05T09:07:05.947879+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSSPTBC77GW65F7H","created_at":"2026-07-05T09:07:05.947879+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSSPTBC7","created_at":"2026-07-05T09:07:05.947879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06983","citing_title":"DaX: Learning General Pathology Representations Across Scales","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00802","citing_title":"CellPrior-Net: Prior-Guided Nuclei Detection and Classification for H&E Whole-Slide Images","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28697","citing_title":"Mitigating Batch Effects in Histopathology via Language-Mediated Robust Embedding Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25764","citing_title":"Benchmarking Pathology Foundation Models for Spatial Domain Understanding","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00578","citing_title":"Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22347","citing_title":"Enabling clinical use of foundation models for computational pathology","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08276","citing_title":"Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00578","citing_title":"Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PSSPTBC77GW65F7HTNXGYPNPZF","json":"https://pith.science/pith/PSSPTBC77GW65F7HTNXGYPNPZF.json","graph_json":"https://pith.science/api/pith-number/PSSPTBC77GW65F7HTNXGYPNPZF/graph.json","events_json":"https://pith.science/api/pith-number/PSSPTBC77GW65F7HTNXGYPNPZF/events.json","paper":"https://pith.science/paper/PSSPTBC7"},"agent_actions":{"view_html":"https://pith.science/pith/PSSPTBC77GW65F7HTNXGYPNPZF","download_json":"https://pith.science/pith/PSSPTBC77GW65F7HTNXGYPNPZF.json","view_paper":"https://pith.science/paper/PSSPTBC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09173&json=true","fetch_graph":"https://pith.science/api/pith-number/PSSPTBC77GW65F7HTNXGYPNPZF/graph.json","fetch_events":"https://pith.science/api/pith-number/PSSPTBC77GW65F7HTNXGYPNPZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSSPTBC77GW65F7HTNXGYPNPZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSSPTBC77GW65F7HTNXGYPNPZF/action/storage_attestation","attest_author":"https://pith.science/pith/PSSPTBC77GW65F7HTNXGYPNPZF/action/author_attestation","sign_citation":"https://pith.science/pith/PSSPTBC77GW65F7HTNXGYPNPZF/action/citation_signature","submit_replication":"https://pith.science/pith/PSSPTBC77GW65F7HTNXGYPNPZF/action/replication_record"}},"created_at":"2026-07-05T09:07:05.947879+00:00","updated_at":"2026-07-05T09:07:05.947879+00:00"}