{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XVLQQUVRHVJ7LUGICWLQNOSIIK","short_pith_number":"pith:XVLQQUVR","schema_version":"1.0","canonical_sha256":"bd570852b13d53f5d0c8159706ba4842985afb17062b36615d90f088a5286554","source":{"kind":"arxiv","id":"2608.01356","version":1},"attestation_state":"computed","paper":{"title":"Harnessing Adversarial Distillation to Customise Debiased, Disease-Specific Pathology Foundation Models for Breast Cancer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Chen, Jens Rittscher, Kaixiang Yang, Tianyang Zhang, Wei Li, Yakun Ju, Yang Hu, Yingxue Xu, Yuxiang Xiao, Zhiwei Chen","submitted_at":"2026-08-02T16:19:16Z","abstract_excerpt":"Pathology foundation models (PFMs) provide strong tissue representations and have become central to digital pathology. However, deployment in disease-specific settings is limited by 1) the high computational cost of billion-parameter PFMs and 2) distribution mismatch and non-biological bias inherited from pan-cancer, multi-centre pre-training, including site-specific signatures and imbalanced disease prevalence. These factors can encourage shortcut learning and under-emphasise subtle morphology required for reliable modelling of a specific cancer type. We present SmartStu (a Smart Student), a "},"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":"2608.01356","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T16:19:16Z","cross_cats_sorted":[],"title_canon_sha256":"264489932c7115a194b2ae52fc44899a9564fcc60d01079f6859cfad9ecce3a3","abstract_canon_sha256":"dcde7205aad02b110bee47966c49a64a191ee1483f1b0cc125f8aaf1979102d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:04:51.476605Z","signature_b64":"Fwf2Pe+J1a8rVoDzBkTAGu5LcsyS/lp1u4GS5ssGYrEKQv/2dpLg+x5xH/6cODc3DpcLeSa4vwdb1P5gvogoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd570852b13d53f5d0c8159706ba4842985afb17062b36615d90f088a5286554","last_reissued_at":"2026-08-04T02:04:51.475068Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:04:51.475068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Adversarial Distillation to Customise Debiased, Disease-Specific Pathology Foundation Models for Breast Cancer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Chen, Jens Rittscher, Kaixiang Yang, Tianyang Zhang, Wei Li, Yakun Ju, Yang Hu, Yingxue Xu, Yuxiang Xiao, Zhiwei Chen","submitted_at":"2026-08-02T16:19:16Z","abstract_excerpt":"Pathology foundation models (PFMs) provide strong tissue representations and have become central to digital pathology. However, deployment in disease-specific settings is limited by 1) the high computational cost of billion-parameter PFMs and 2) distribution mismatch and non-biological bias inherited from pan-cancer, multi-centre pre-training, including site-specific signatures and imbalanced disease prevalence. These factors can encourage shortcut learning and under-emphasise subtle morphology required for reliable modelling of a specific cancer type. We present SmartStu (a Smart Student), a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01356","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/2608.01356/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":"2608.01356","created_at":"2026-08-04T02:04:51.476528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01356v1","created_at":"2026-08-04T02:04:51.476528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01356","created_at":"2026-08-04T02:04:51.476528+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVLQQUVRHVJ7","created_at":"2026-08-04T02:04:51.476528+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVLQQUVRHVJ7LUGI","created_at":"2026-08-04T02:04:51.476528+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVLQQUVR","created_at":"2026-08-04T02:04:51.476528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVLQQUVRHVJ7LUGICWLQNOSIIK","json":"https://pith.science/pith/XVLQQUVRHVJ7LUGICWLQNOSIIK.json","graph_json":"https://pith.science/api/pith-number/XVLQQUVRHVJ7LUGICWLQNOSIIK/graph.json","events_json":"https://pith.science/api/pith-number/XVLQQUVRHVJ7LUGICWLQNOSIIK/events.json","paper":"https://pith.science/paper/XVLQQUVR"},"agent_actions":{"view_html":"https://pith.science/pith/XVLQQUVRHVJ7LUGICWLQNOSIIK","download_json":"https://pith.science/pith/XVLQQUVRHVJ7LUGICWLQNOSIIK.json","view_paper":"https://pith.science/paper/XVLQQUVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01356&json=true","fetch_graph":"https://pith.science/api/pith-number/XVLQQUVRHVJ7LUGICWLQNOSIIK/graph.json","fetch_events":"https://pith.science/api/pith-number/XVLQQUVRHVJ7LUGICWLQNOSIIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVLQQUVRHVJ7LUGICWLQNOSIIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVLQQUVRHVJ7LUGICWLQNOSIIK/action/storage_attestation","attest_author":"https://pith.science/pith/XVLQQUVRHVJ7LUGICWLQNOSIIK/action/author_attestation","sign_citation":"https://pith.science/pith/XVLQQUVRHVJ7LUGICWLQNOSIIK/action/citation_signature","submit_replication":"https://pith.science/pith/XVLQQUVRHVJ7LUGICWLQNOSIIK/action/replication_record"}},"created_at":"2026-08-04T02:04:51.476528+00:00","updated_at":"2026-08-04T02:04:51.476528+00:00"}