{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HQISPW25N3F3ZCUUD4BULSRVC2","short_pith_number":"pith:HQISPW25","schema_version":"1.0","canonical_sha256":"3c1127db5d6ecbbc8a941f0345ca35169c8cb3bfd5f359c169aec439d9573369","source":{"kind":"arxiv","id":"2605.05161","version":2},"attestation_state":"computed","paper":{"title":"Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Wasserstein distances let vision-language models pick moderately similar normal anatomy references to localize anomalies in medical images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernhard Kainz, Cosmin Bercea, Johanna P Mueller, Matthew Baugh","submitted_at":"2026-05-06T17:32:34Z","abstract_excerpt":"Zero-shot anomaly localisation via vision-language models (VLMs) offers a compelling approach for rare pathology detection, yet its performance is fundamentally limited by the absence of healthy anatomical context. We reformulate zero-shot localisation as a comparative inference problem in which anomalies are identified through structured comparison against reference distributions of normal anatomy. We introduce WALDO, a training-free framework grounded in optimal transport theory that enables comparative reasoning through: (i) entropy-weighted Sliced Wasserstein distances for anatomically-awa"},"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":"2605.05161","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-06T17:32:34Z","cross_cats_sorted":[],"title_canon_sha256":"26e9a12eb9cc83771084c519162e381b037bcbb7cad4afeeeb6da2a099555a84","abstract_canon_sha256":"d2fbaab073d37a9a86a573783ef8087d937173b80d66454c7b1a6e4c9af1e460"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:12:49.713141Z","signature_b64":"njhjY3Qidhgbb5T/n+sP36zINepHvpvbPfv/ye/c4SJj0CB3hvXZXU/hlH7KhshTWehd9ldd4Esor9rbydRtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c1127db5d6ecbbc8a941f0345ca35169c8cb3bfd5f359c169aec439d9573369","last_reissued_at":"2026-06-23T02:12:49.712750Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:12:49.712750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Wasserstein distances let vision-language models pick moderately similar normal anatomy references to localize anomalies in medical images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernhard Kainz, Cosmin Bercea, Johanna P Mueller, Matthew Baugh","submitted_at":"2026-05-06T17:32:34Z","abstract_excerpt":"Zero-shot anomaly localisation via vision-language models (VLMs) offers a compelling approach for rare pathology detection, yet its performance is fundamentally limited by the absence of healthy anatomical context. We reformulate zero-shot localisation as a comparative inference problem in which anomalies are identified through structured comparison against reference distributions of normal anatomy. We introduce WALDO, a training-free framework grounded in optimal transport theory that enables comparative reasoning through: (i) entropy-weighted Sliced Wasserstein distances for anatomically-awa"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the NOVA brain MRI benchmark, WALDO with Qwen2.5-VL-72B achieves 43.5±1.6% mAP@30 (95% CI: [40.4, 46.7]), representing a 19% relative improvement over zero-shot baselines. Cross-model evaluation shows consistent gains: GPT-4o achieves 32.0±6.5% and Qwen3-VL-32B achieves 32.0±6.6% mAP@30. Paired McNemar tests confirm statistical significance (p<0.01).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That reference images drawn from DINOv2 patch distributions of normal anatomy, selected via moderate similarity in the Goldilocks zone, provide a reliable bias-variance trade-off for comparative visual reasoning in VLMs, and that the non-monotonic relationship between reference similarity and localisation accuracy holds across the tested models and data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"WALDO improves zero-shot anomaly localization in medical imaging by selecting reference distributions via entropy-weighted Sliced Wasserstein distances and Goldilocks zone sampling, yielding a 19% relative gain on brain MRI benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Wasserstein distances let vision-language models pick moderately similar normal anatomy references to localize anomalies in medical images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e902904c901851938bdce7d34a7255cd501cc22ee62d5fcc2db09ae776337df1"},"source":{"id":"2605.05161","kind":"arxiv","version":2},"verdict":{"id":"d0712e97-fdef-4779-b88f-7808776b9384","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T16:36:15.678369Z","strongest_claim":"On the NOVA brain MRI benchmark, WALDO with Qwen2.5-VL-72B achieves 43.5±1.6% mAP@30 (95% CI: [40.4, 46.7]), representing a 19% relative improvement over zero-shot baselines. Cross-model evaluation shows consistent gains: GPT-4o achieves 32.0±6.5% and Qwen3-VL-32B achieves 32.0±6.6% mAP@30. Paired McNemar tests confirm statistical significance (p<0.01).","one_line_summary":"WALDO improves zero-shot anomaly localization in medical imaging by selecting reference distributions via entropy-weighted Sliced Wasserstein distances and Goldilocks zone sampling, yielding a 19% relative gain on brain MRI benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That reference images drawn from DINOv2 patch distributions of normal anatomy, selected via moderate similarity in the Goldilocks zone, provide a reliable bias-variance trade-off for comparative visual reasoning in VLMs, and that the non-monotonic relationship between reference similarity and localisation accuracy holds across the tested models and data.","pith_extraction_headline":"Wasserstein distances let vision-language models pick moderately similar normal anatomy references to localize anomalies in medical images."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.05161/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T10:35:54.023754Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.796836Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:47:58.196713Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"4e202d90f21440286011b3652365686311dd32a0de03ae4f5211e11989f8749d"},"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":"2605.05161","created_at":"2026-06-23T02:12:49.712801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.05161v2","created_at":"2026-06-23T02:12:49.712801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05161","created_at":"2026-06-23T02:12:49.712801+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQISPW25N3F3","created_at":"2026-06-23T02:12:49.712801+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQISPW25N3F3ZCUU","created_at":"2026-06-23T02:12:49.712801+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQISPW25","created_at":"2026-06-23T02:12:49.712801+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/HQISPW25N3F3ZCUUD4BULSRVC2","json":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2.json","graph_json":"https://pith.science/api/pith-number/HQISPW25N3F3ZCUUD4BULSRVC2/graph.json","events_json":"https://pith.science/api/pith-number/HQISPW25N3F3ZCUUD4BULSRVC2/events.json","paper":"https://pith.science/paper/HQISPW25"},"agent_actions":{"view_html":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2","download_json":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2.json","view_paper":"https://pith.science/paper/HQISPW25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.05161&json=true","fetch_graph":"https://pith.science/api/pith-number/HQISPW25N3F3ZCUUD4BULSRVC2/graph.json","fetch_events":"https://pith.science/api/pith-number/HQISPW25N3F3ZCUUD4BULSRVC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2/action/storage_attestation","attest_author":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2/action/author_attestation","sign_citation":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2/action/citation_signature","submit_replication":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2/action/replication_record"}},"created_at":"2026-06-23T02:12:49.712801+00:00","updated_at":"2026-06-23T02:12:49.712801+00:00"}