{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NRAXXCGYXEFR5GCPSMRIHI5N4O","short_pith_number":"pith:NRAXXCGY","schema_version":"1.0","canonical_sha256":"6c417b88d8b90b1e984f932283a3ade3bb92b2164e3ad27169b23ff1147f9b5c","source":{"kind":"arxiv","id":"2606.06224","version":2},"attestation_state":"computed","paper":{"title":"Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andreas Mock, Julius Hense, Klaus-Robert M\\\"uller, Mina Jamshidi Idaji, Niklas Preni{\\ss}l, Thomas Schnake, Yanqing Luo","submitted_at":"2026-06-04T14:35:22Z","abstract_excerpt":"Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology. Existing methods primarily rely on heatmaps that highlight influential regions but do not explain how evidence from different tissue regions is combined to produce a prediction. This limits interpretability, especially when decisions depend on interactions between tissue features. We introduce Symbolic explainable MIL (Symb-xMIL), a post-hoc explanation framework that quantifies how a MIL model's behavior aligns with human-readable decision rules, expressed as logical"},"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":"2606.06224","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T14:35:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d487c21b1c56273b70529faf708c3358a0080f3d65c06b0f0303e66e76c13cb","abstract_canon_sha256":"1b26fa0e0f239b0e2a831581fba0d8dfc562fd99536313cc5704148a5286890d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:11.924461Z","signature_b64":"S314PJcoaZfqEnNMKqqLCeT/xPwtcmTkCgyEaVmqLrmXYmr5Brb5X4nneRiUIjqVCWGOv+DnN2rFwT/an1+aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c417b88d8b90b1e984f932283a3ade3bb92b2164e3ad27169b23ff1147f9b5c","last_reissued_at":"2026-06-08T01:04:11.923578Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:11.923578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andreas Mock, Julius Hense, Klaus-Robert M\\\"uller, Mina Jamshidi Idaji, Niklas Preni{\\ss}l, Thomas Schnake, Yanqing Luo","submitted_at":"2026-06-04T14:35:22Z","abstract_excerpt":"Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology. Existing methods primarily rely on heatmaps that highlight influential regions but do not explain how evidence from different tissue regions is combined to produce a prediction. This limits interpretability, especially when decisions depend on interactions between tissue features. We introduce Symbolic explainable MIL (Symb-xMIL), a post-hoc explanation framework that quantifies how a MIL model's behavior aligns with human-readable decision rules, expressed as logical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06224","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/2606.06224/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":"2606.06224","created_at":"2026-06-08T01:04:11.923711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06224v2","created_at":"2026-06-08T01:04:11.923711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06224","created_at":"2026-06-08T01:04:11.923711+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRAXXCGYXEFR","created_at":"2026-06-08T01:04:11.923711+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRAXXCGYXEFR5GCP","created_at":"2026-06-08T01:04:11.923711+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRAXXCGY","created_at":"2026-06-08T01:04:11.923711+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/NRAXXCGYXEFR5GCPSMRIHI5N4O","json":"https://pith.science/pith/NRAXXCGYXEFR5GCPSMRIHI5N4O.json","graph_json":"https://pith.science/api/pith-number/NRAXXCGYXEFR5GCPSMRIHI5N4O/graph.json","events_json":"https://pith.science/api/pith-number/NRAXXCGYXEFR5GCPSMRIHI5N4O/events.json","paper":"https://pith.science/paper/NRAXXCGY"},"agent_actions":{"view_html":"https://pith.science/pith/NRAXXCGYXEFR5GCPSMRIHI5N4O","download_json":"https://pith.science/pith/NRAXXCGYXEFR5GCPSMRIHI5N4O.json","view_paper":"https://pith.science/paper/NRAXXCGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06224&json=true","fetch_graph":"https://pith.science/api/pith-number/NRAXXCGYXEFR5GCPSMRIHI5N4O/graph.json","fetch_events":"https://pith.science/api/pith-number/NRAXXCGYXEFR5GCPSMRIHI5N4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRAXXCGYXEFR5GCPSMRIHI5N4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRAXXCGYXEFR5GCPSMRIHI5N4O/action/storage_attestation","attest_author":"https://pith.science/pith/NRAXXCGYXEFR5GCPSMRIHI5N4O/action/author_attestation","sign_citation":"https://pith.science/pith/NRAXXCGYXEFR5GCPSMRIHI5N4O/action/citation_signature","submit_replication":"https://pith.science/pith/NRAXXCGYXEFR5GCPSMRIHI5N4O/action/replication_record"}},"created_at":"2026-06-08T01:04:11.923711+00:00","updated_at":"2026-06-08T01:04:11.923711+00:00"}