{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XFV5UMRQ4OYFAWOAJTBTZF45PM","short_pith_number":"pith:XFV5UMRQ","schema_version":"1.0","canonical_sha256":"b96bda3230e3b05059c04cc33c979d7b2ba996241ccb967284366eeb8206bc2a","source":{"kind":"arxiv","id":"2602.04585","version":2},"attestation_state":"computed","paper":{"title":"ImmuVis: Hyperconvolutional Foundation Model for Imaging Mass Cytometry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ImmuVis generates convolutional kernels on the fly from marker embeddings so one model works with any combination of molecular markers in tissue images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dawid Uchal, Eike Staub, Ewa Szczurek, Jakub Giezga{\\l}a, Kacper Pietrzyk, Karol Zagr\\'odka, Krzysztof Gogolewski, Marcin Mo\\.zejko, Mateusz Sulimowicz, Michal Orzy{\\l}owski, Piotr Kupidura, Robert Pieniuta, Szymon {\\L}ukasik, Tomasz Noco\\'n, Tomasz Si{\\l}kowski","submitted_at":"2026-02-04T14:11:33Z","abstract_excerpt":"We present ImmuVis, a family of efficient foundation models for imaging mass cytometry (IMC), a high-throughput multiplex imaging technology that handles molecular marker measurements as image channels and enables large-scale spatial tissue profiling. Unlike natural images, multiplex imaging lacks a fixed channel space, as real-world marker sets vary across studies, violating a core assumption of standard vision backbones. To address this, ImmuVis introduces marker-adaptive hyperconvolutions that generate convolutional kernels from learned marker embeddings, enabling a single model to operate "},"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":"2602.04585","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T14:11:33Z","cross_cats_sorted":[],"title_canon_sha256":"377eeeb05c995142d241816ab41a1d157878460b55e54a69eb3ff70fa1ced1fa","abstract_canon_sha256":"ff02c986f51959fb57c14509ec6f357178c95dbbcdd1e062c90e6c3ac5426a2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:16.358127Z","signature_b64":"z4TzycPI5ddw/1hAGyARK3QB6+w6QO66NBIeMz97NLiVLg3CpILElWnWNV5O/hnn+3eeyfZCDg7QnEX+UI+VDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b96bda3230e3b05059c04cc33c979d7b2ba996241ccb967284366eeb8206bc2a","last_reissued_at":"2026-05-17T23:39:16.357445Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:16.357445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImmuVis: Hyperconvolutional Foundation Model for Imaging Mass Cytometry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ImmuVis generates convolutional kernels on the fly from marker embeddings so one model works with any combination of molecular markers in tissue images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dawid Uchal, Eike Staub, Ewa Szczurek, Jakub Giezga{\\l}a, Kacper Pietrzyk, Karol Zagr\\'odka, Krzysztof Gogolewski, Marcin Mo\\.zejko, Mateusz Sulimowicz, Michal Orzy{\\l}owski, Piotr Kupidura, Robert Pieniuta, Szymon {\\L}ukasik, Tomasz Noco\\'n, Tomasz Si{\\l}kowski","submitted_at":"2026-02-04T14:11:33Z","abstract_excerpt":"We present ImmuVis, a family of efficient foundation models for imaging mass cytometry (IMC), a high-throughput multiplex imaging technology that handles molecular marker measurements as image channels and enables large-scale spatial tissue profiling. Unlike natural images, multiplex imaging lacks a fixed channel space, as real-world marker sets vary across studies, violating a core assumption of standard vision backbones. To address this, ImmuVis introduces marker-adaptive hyperconvolutions that generate convolutional kernels from learned marker embeddings, enabling a single model to operate "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ImmuVis introduces marker-adaptive hyperconvolutions that generate convolutional kernels from learned marker embeddings, enabling a single model to operate on arbitrary measured marker subsets without retraining.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That embeddings learned from the pretraining marker set can generate effective kernels for entirely new marker combinations never seen during training or fine-tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ImmuVis uses hyperconvolutions generated from marker embeddings to create a foundation model that processes variable marker subsets in IMC images, pretrained on 17M patches and providing uncertainty estimates.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ImmuVis generates convolutional kernels on the fly from marker embeddings so one model works with any combination of molecular markers in tissue images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0fa647e8ba9407033be875e37594af57e5543dc680faba3e76565d204fb2303b"},"source":{"id":"2602.04585","kind":"arxiv","version":2},"verdict":{"id":"2ebcd494-a07f-4b68-8c39-be1f1ba40ce7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T07:32:09.971514Z","strongest_claim":"ImmuVis introduces marker-adaptive hyperconvolutions that generate convolutional kernels from learned marker embeddings, enabling a single model to operate on arbitrary measured marker subsets without retraining.","one_line_summary":"ImmuVis uses hyperconvolutions generated from marker embeddings to create a foundation model that processes variable marker subsets in IMC images, pretrained on 17M patches and providing uncertainty estimates.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That embeddings learned from the pretraining marker set can generate effective kernels for entirely new marker combinations never seen during training or fine-tuning.","pith_extraction_headline":"ImmuVis generates convolutional kernels on the fly from marker embeddings so one model works with any combination of molecular markers in tissue images."},"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":"2602.04585","created_at":"2026-05-17T23:39:16.357557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.04585v2","created_at":"2026-05-17T23:39:16.357557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04585","created_at":"2026-05-17T23:39:16.357557+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFV5UMRQ4OYF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFV5UMRQ4OYFAWOA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFV5UMRQ","created_at":"2026-05-18T12:33:37.589309+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/XFV5UMRQ4OYFAWOAJTBTZF45PM","json":"https://pith.science/pith/XFV5UMRQ4OYFAWOAJTBTZF45PM.json","graph_json":"https://pith.science/api/pith-number/XFV5UMRQ4OYFAWOAJTBTZF45PM/graph.json","events_json":"https://pith.science/api/pith-number/XFV5UMRQ4OYFAWOAJTBTZF45PM/events.json","paper":"https://pith.science/paper/XFV5UMRQ"},"agent_actions":{"view_html":"https://pith.science/pith/XFV5UMRQ4OYFAWOAJTBTZF45PM","download_json":"https://pith.science/pith/XFV5UMRQ4OYFAWOAJTBTZF45PM.json","view_paper":"https://pith.science/paper/XFV5UMRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.04585&json=true","fetch_graph":"https://pith.science/api/pith-number/XFV5UMRQ4OYFAWOAJTBTZF45PM/graph.json","fetch_events":"https://pith.science/api/pith-number/XFV5UMRQ4OYFAWOAJTBTZF45PM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFV5UMRQ4OYFAWOAJTBTZF45PM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFV5UMRQ4OYFAWOAJTBTZF45PM/action/storage_attestation","attest_author":"https://pith.science/pith/XFV5UMRQ4OYFAWOAJTBTZF45PM/action/author_attestation","sign_citation":"https://pith.science/pith/XFV5UMRQ4OYFAWOAJTBTZF45PM/action/citation_signature","submit_replication":"https://pith.science/pith/XFV5UMRQ4OYFAWOAJTBTZF45PM/action/replication_record"}},"created_at":"2026-05-17T23:39:16.357557+00:00","updated_at":"2026-05-17T23:39:16.357557+00:00"}