{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MSZ36UTZDVEEQTVV2J5VOC7SOC","short_pith_number":"pith:MSZ36UTZ","canonical_record":{"source":{"id":"2504.06299","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-04-07T09:56:16Z","cross_cats_sorted":["cs.CV","cs.LG","stat.AP"],"title_canon_sha256":"e277b1a507e7712a0e50584c258749484756c9fd53fdeb70721f05a0e32edb3d","abstract_canon_sha256":"f8a574803fc165832afa2bbefc321a7fe1c5c23c464e884bf3f721d6c147dd86"},"schema_version":"1.0"},"canonical_sha256":"64b3bf52791d48484eb5d27b570bf270a04264f34e9698e98cc5b50e5c5b9bb2","source":{"kind":"arxiv","id":"2504.06299","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.06299","created_at":"2026-07-02T01:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2504.06299v2","created_at":"2026-07-02T01:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06299","created_at":"2026-07-02T01:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"MSZ36UTZDVEE","created_at":"2026-07-02T01:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"MSZ36UTZDVEEQTVV","created_at":"2026-07-02T01:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"MSZ36UTZ","created_at":"2026-07-02T01:17:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MSZ36UTZDVEEQTVV2J5VOC7SOC","target":"record","payload":{"canonical_record":{"source":{"id":"2504.06299","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-04-07T09:56:16Z","cross_cats_sorted":["cs.CV","cs.LG","stat.AP"],"title_canon_sha256":"e277b1a507e7712a0e50584c258749484756c9fd53fdeb70721f05a0e32edb3d","abstract_canon_sha256":"f8a574803fc165832afa2bbefc321a7fe1c5c23c464e884bf3f721d6c147dd86"},"schema_version":"1.0"},"canonical_sha256":"64b3bf52791d48484eb5d27b570bf270a04264f34e9698e98cc5b50e5c5b9bb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:12.263397Z","signature_b64":"SjqktxVp82xdmwDHKdPswK8YOFYpxRkvQc3Vqi8c671OpRiNpQo3VHe1+oGg44Y6gHPfov0Vo3CDRVYeRRLTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64b3bf52791d48484eb5d27b570bf270a04264f34e9698e98cc5b50e5c5b9bb2","last_reissued_at":"2026-07-02T01:17:12.262975Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:12.262975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.06299","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:17:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hNfC0v5LoUY1q4nlTiNJDn3WwN0FNB+KSlwgtoxpzEacx0HU29TuYjbZPHisnXX3boA+OzLRDLIzCYhZgVZSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T07:01:36.972442Z"},"content_sha256":"f10c5af492aa185d9830b7bf114cc58c1ec1943bb8681118b307af4c32818f90","schema_version":"1.0","event_id":"sha256:f10c5af492aa185d9830b7bf114cc58c1ec1943bb8681118b307af4c32818f90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MSZ36UTZDVEEQTVV2J5VOC7SOC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explainability in mulimodal deep transformation models for stroke outcome prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.AP"],"primary_cat":"eess.IV","authors_text":"Beate Sick, Hakim Baazaoui, Jonas Br\\\"andli, Lisa Herzog, Loran Avci, Martin H\\\"ansel, Maurice Schneeberger, Nordin Dari, Pascal B\\\"uhler, Susanne Wegener","submitted_at":"2025-04-07T09:56:16Z","abstract_excerpt":"Multimodal prediction models based on imaging and clinical data are increasingly used for clinical decision support, yet their interpretability remains limited. We present multimodal Deep Transformation Models (DTMs) combining statistical approaches and neural networks to achieve strong predictive performance while preserving interpretability for tabular data. A key contribution of this work is the adaption of the xAI methods Grad-CAM and Occlusion to DTMs relying on 3D CNNs, enabling interpretation of the image branch through the generation of explanation maps. We developed DTMs to predict fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06299","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/2504.06299/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:17:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHkqtvTOphFpljw/hg3hLAnYDTtMuW82b6XBhX/Pg7P+MBHBscxad0npRCasRosHyzAji4ZkJhAQ7/uwbTIWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T07:01:36.972809Z"},"content_sha256":"17b6a3d9c3f3e8d5a608ff7b41008785d5259c10696ab788001193d7eb9b8548","schema_version":"1.0","event_id":"sha256:17b6a3d9c3f3e8d5a608ff7b41008785d5259c10696ab788001193d7eb9b8548"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSZ36UTZDVEEQTVV2J5VOC7SOC/bundle.json","state_url":"https://pith.science/pith/MSZ36UTZDVEEQTVV2J5VOC7SOC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSZ36UTZDVEEQTVV2J5VOC7SOC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T07:01:36Z","links":{"resolver":"https://pith.science/pith/MSZ36UTZDVEEQTVV2J5VOC7SOC","bundle":"https://pith.science/pith/MSZ36UTZDVEEQTVV2J5VOC7SOC/bundle.json","state":"https://pith.science/pith/MSZ36UTZDVEEQTVV2J5VOC7SOC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSZ36UTZDVEEQTVV2J5VOC7SOC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MSZ36UTZDVEEQTVV2J5VOC7SOC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f8a574803fc165832afa2bbefc321a7fe1c5c23c464e884bf3f721d6c147dd86","cross_cats_sorted":["cs.CV","cs.LG","stat.AP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-04-07T09:56:16Z","title_canon_sha256":"e277b1a507e7712a0e50584c258749484756c9fd53fdeb70721f05a0e32edb3d"},"schema_version":"1.0","source":{"id":"2504.06299","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.06299","created_at":"2026-07-02T01:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2504.06299v2","created_at":"2026-07-02T01:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06299","created_at":"2026-07-02T01:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"MSZ36UTZDVEE","created_at":"2026-07-02T01:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"MSZ36UTZDVEEQTVV","created_at":"2026-07-02T01:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"MSZ36UTZ","created_at":"2026-07-02T01:17:12Z"}],"graph_snapshots":[{"event_id":"sha256:17b6a3d9c3f3e8d5a608ff7b41008785d5259c10696ab788001193d7eb9b8548","target":"graph","created_at":"2026-07-02T01:17:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.06299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal prediction models based on imaging and clinical data are increasingly used for clinical decision support, yet their interpretability remains limited. We present multimodal Deep Transformation Models (DTMs) combining statistical approaches and neural networks to achieve strong predictive performance while preserving interpretability for tabular data. A key contribution of this work is the adaption of the xAI methods Grad-CAM and Occlusion to DTMs relying on 3D CNNs, enabling interpretation of the image branch through the generation of explanation maps. We developed DTMs to predict fu","authors_text":"Beate Sick, Hakim Baazaoui, Jonas Br\\\"andli, Lisa Herzog, Loran Avci, Martin H\\\"ansel, Maurice Schneeberger, Nordin Dari, Pascal B\\\"uhler, Susanne Wegener","cross_cats":["cs.CV","cs.LG","stat.AP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-04-07T09:56:16Z","title":"Explainability in mulimodal deep transformation models for stroke outcome prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06299","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f10c5af492aa185d9830b7bf114cc58c1ec1943bb8681118b307af4c32818f90","target":"record","created_at":"2026-07-02T01:17:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f8a574803fc165832afa2bbefc321a7fe1c5c23c464e884bf3f721d6c147dd86","cross_cats_sorted":["cs.CV","cs.LG","stat.AP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-04-07T09:56:16Z","title_canon_sha256":"e277b1a507e7712a0e50584c258749484756c9fd53fdeb70721f05a0e32edb3d"},"schema_version":"1.0","source":{"id":"2504.06299","kind":"arxiv","version":2}},"canonical_sha256":"64b3bf52791d48484eb5d27b570bf270a04264f34e9698e98cc5b50e5c5b9bb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64b3bf52791d48484eb5d27b570bf270a04264f34e9698e98cc5b50e5c5b9bb2","first_computed_at":"2026-07-02T01:17:12.262975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:12.262975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SjqktxVp82xdmwDHKdPswK8YOFYpxRkvQc3Vqi8c671OpRiNpQo3VHe1+oGg44Y6gHPfov0Vo3CDRVYeRRLTAQ==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:12.263397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.06299","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f10c5af492aa185d9830b7bf114cc58c1ec1943bb8681118b307af4c32818f90","sha256:17b6a3d9c3f3e8d5a608ff7b41008785d5259c10696ab788001193d7eb9b8548"],"state_sha256":"5af127712792555a87f312260fc062f296911c27b183638f349d22fcc7233630"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p/AzEczmvmLE3hK5Rw8XeQh4rr5cGVUYznURj8O0V6v4L/ExQvhfeisvkrwA22amZeZEjB1/3doLljy7G5cgBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T07:01:36.974761Z","bundle_sha256":"5e476d1723d7476dc330b0142e602e651d88a417d43b87481d4ad229d6a70894"}}