{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NU54TCI7ZHSBEKQQ3V3DSDQPFB","short_pith_number":"pith:NU54TCI7","schema_version":"1.0","canonical_sha256":"6d3bc9891fc9e4122a10dd76390e0f2845065eb9a95ff92b1c4f840c494fac86","source":{"kind":"arxiv","id":"2511.23204","version":2},"attestation_state":"computed","paper":{"title":"Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carsten Marr, Christian Brechenmacher, Christian Grashei, Ewa Szczurek, Jingsong Liu, Peter J. Sch\\\"uffler, Rao Muhammad Umer","submitted_at":"2025-11-28T14:11:31Z","abstract_excerpt":"Pathology foundation models (FMs) have driven significant progress in computational pathology. However, these high-performing models can easily exceed a billion parameters and produce high-dimensional embeddings, thus limiting their applicability for research or clinical use when computing resources are tight. Here, we introduce Pathryoshka, a multi-teacher distillation framework inspired by RADIO distillation and Matryoshka Representation Learning to reduce pathology FM sizes while allowing for adaptable embedding dimensions. We evaluate our framework with a distilled model on ten public path"},"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":"2511.23204","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-28T14:11:31Z","cross_cats_sorted":[],"title_canon_sha256":"cf80ed0d2a554aecac1f03c3ddd48177abd5b1e02a8006abb4d161a708580d1c","abstract_canon_sha256":"cec988004ec3ff1742994b9e9e7e0e7733ae63f9efc63703c89405efb777681f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:14:00.220085Z","signature_b64":"+BwXzUVF41JZ0hpbpGiQZZNU9s79gRBECJtGwYX6uRts9sCbNRrlFnIgOIiDmCMAeEA/vRWn7aBXKjjnSA+ZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d3bc9891fc9e4122a10dd76390e0f2845065eb9a95ff92b1c4f840c494fac86","last_reissued_at":"2026-08-10T01:14:00.214744Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:14:00.214744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carsten Marr, Christian Brechenmacher, Christian Grashei, Ewa Szczurek, Jingsong Liu, Peter J. Sch\\\"uffler, Rao Muhammad Umer","submitted_at":"2025-11-28T14:11:31Z","abstract_excerpt":"Pathology foundation models (FMs) have driven significant progress in computational pathology. However, these high-performing models can easily exceed a billion parameters and produce high-dimensional embeddings, thus limiting their applicability for research or clinical use when computing resources are tight. Here, we introduce Pathryoshka, a multi-teacher distillation framework inspired by RADIO distillation and Matryoshka Representation Learning to reduce pathology FM sizes while allowing for adaptable embedding dimensions. We evaluate our framework with a distilled model on ten public path"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.23204","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/2511.23204/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":"2511.23204","created_at":"2026-08-10T01:14:00.217177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.23204v2","created_at":"2026-08-10T01:14:00.217177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.23204","created_at":"2026-08-10T01:14:00.217177+00:00"},{"alias_kind":"pith_short_12","alias_value":"NU54TCI7ZHSB","created_at":"2026-08-10T01:14:00.217177+00:00"},{"alias_kind":"pith_short_16","alias_value":"NU54TCI7ZHSBEKQQ","created_at":"2026-08-10T01:14:00.217177+00:00"},{"alias_kind":"pith_short_8","alias_value":"NU54TCI7","created_at":"2026-08-10T01:14:00.217177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.22861","citing_title":"Robustifying pathology foundation models via fine-tuning","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NU54TCI7ZHSBEKQQ3V3DSDQPFB","json":"https://pith.science/pith/NU54TCI7ZHSBEKQQ3V3DSDQPFB.json","graph_json":"https://pith.science/api/pith-number/NU54TCI7ZHSBEKQQ3V3DSDQPFB/graph.json","events_json":"https://pith.science/api/pith-number/NU54TCI7ZHSBEKQQ3V3DSDQPFB/events.json","paper":"https://pith.science/paper/NU54TCI7"},"agent_actions":{"view_html":"https://pith.science/pith/NU54TCI7ZHSBEKQQ3V3DSDQPFB","download_json":"https://pith.science/pith/NU54TCI7ZHSBEKQQ3V3DSDQPFB.json","view_paper":"https://pith.science/paper/NU54TCI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.23204&json=true","fetch_graph":"https://pith.science/api/pith-number/NU54TCI7ZHSBEKQQ3V3DSDQPFB/graph.json","fetch_events":"https://pith.science/api/pith-number/NU54TCI7ZHSBEKQQ3V3DSDQPFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NU54TCI7ZHSBEKQQ3V3DSDQPFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NU54TCI7ZHSBEKQQ3V3DSDQPFB/action/storage_attestation","attest_author":"https://pith.science/pith/NU54TCI7ZHSBEKQQ3V3DSDQPFB/action/author_attestation","sign_citation":"https://pith.science/pith/NU54TCI7ZHSBEKQQ3V3DSDQPFB/action/citation_signature","submit_replication":"https://pith.science/pith/NU54TCI7ZHSBEKQQ3V3DSDQPFB/action/replication_record"}},"created_at":"2026-08-10T01:14:00.217177+00:00","updated_at":"2026-08-10T01:14:00.217177+00:00"}