{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HQISPW25N3F3ZCUUD4BULSRVC2","short_pith_number":"pith:HQISPW25","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"},"canonical_sha256":"3c1127db5d6ecbbc8a941f0345ca35169c8cb3bfd5f359c169aec439d9573369","source":{"kind":"arxiv","id":"2605.05161","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.05161","created_at":"2026-06-23T02:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.05161v2","created_at":"2026-06-23T02:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05161","created_at":"2026-06-23T02:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"HQISPW25N3F3","created_at":"2026-06-23T02:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"HQISPW25N3F3ZCUU","created_at":"2026-06-23T02:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"HQISPW25","created_at":"2026-06-23T02:12:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HQISPW25N3F3ZCUUD4BULSRVC2","target":"record","payload":{"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"},"canonical_sha256":"3c1127db5d6ecbbc8a941f0345ca35169c8cb3bfd5f359c169aec439d9573369","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"},"source_kind":"arxiv","source_id":"2605.05161","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":"2026-06-23T02:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GEj8yrONGjLobjEIFMA3kevzjgF2ArAFF+scBkTlsdGXAVMuVHJtYFeZB/lQxoiD/digiO7u/t8Z1UYfe5thBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:17:06.283735Z"},"content_sha256":"33f98c2b5ef907fdd4b2082535362c074a26612760cac03b5449586dca6a8186","schema_version":"1.0","event_id":"sha256:33f98c2b5ef907fdd4b2082535362c074a26612760cac03b5449586dca6a8186"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HQISPW25N3F3ZCUUD4BULSRVC2","target":"graph","payload":{"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"},"verdict_id":"d0712e97-fdef-4779-b88f-7808776b9384"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1S0WSeT5K29nxcbBkIqcWEZlaTZi6UWviwcWxXXKykUiOBpDUVW75s4znthq6myxDjRlTmECptz9dvPb+SGaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:17:06.284306Z"},"content_sha256":"28125268263a8c583abfdf2e48a5277c70ca8fbe85607f9f1a67881efd01d3a6","schema_version":"1.0","event_id":"sha256:28125268263a8c583abfdf2e48a5277c70ca8fbe85607f9f1a67881efd01d3a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2/bundle.json","state_url":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HQISPW25N3F3ZCUUD4BULSRVC2/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":"2026-07-13T00:17:06Z","links":{"resolver":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2","bundle":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2/bundle.json","state":"https://pith.science/pith/HQISPW25N3F3ZCUUD4BULSRVC2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HQISPW25N3F3ZCUUD4BULSRVC2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HQISPW25N3F3ZCUUD4BULSRVC2","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":"d2fbaab073d37a9a86a573783ef8087d937173b80d66454c7b1a6e4c9af1e460","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-06T17:32:34Z","title_canon_sha256":"26e9a12eb9cc83771084c519162e381b037bcbb7cad4afeeeb6da2a099555a84"},"schema_version":"1.0","source":{"id":"2605.05161","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.05161","created_at":"2026-06-23T02:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.05161v2","created_at":"2026-06-23T02:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05161","created_at":"2026-06-23T02:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"HQISPW25N3F3","created_at":"2026-06-23T02:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"HQISPW25N3F3ZCUU","created_at":"2026-06-23T02:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"HQISPW25","created_at":"2026-06-23T02:12:49Z"}],"graph_snapshots":[{"event_id":"sha256:28125268263a8c583abfdf2e48a5277c70ca8fbe85607f9f1a67881efd01d3a6","target":"graph","created_at":"2026-06-23T02:12:49Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Wasserstein distances let vision-language models pick moderately similar normal anatomy references to localize anomalies in medical images."}],"snapshot_sha256":"e902904c901851938bdce7d34a7255cd501cc22ee62d5fcc2db09ae776337df1"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.05161/integrity.json","findings":[],"snapshot_sha256":"4e202d90f21440286011b3652365686311dd32a0de03ae4f5211e11989f8749d","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bernhard Kainz, Cosmin Bercea, Johanna P Mueller, Matthew Baugh","cross_cats":[],"headline":"Wasserstein distances let vision-language models pick moderately similar normal anatomy references to localize anomalies in medical images.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-06T17:32:34Z","title":"Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.05161","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T16:36:15.678369Z","id":"d0712e97-fdef-4779-b88f-7808776b9384","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Wasserstein distances let vision-language models pick moderately similar normal anatomy references to localize anomalies in medical images.","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).","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."}},"verdict_id":"d0712e97-fdef-4779-b88f-7808776b9384"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:33f98c2b5ef907fdd4b2082535362c074a26612760cac03b5449586dca6a8186","target":"record","created_at":"2026-06-23T02:12:49Z","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":"d2fbaab073d37a9a86a573783ef8087d937173b80d66454c7b1a6e4c9af1e460","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-06T17:32:34Z","title_canon_sha256":"26e9a12eb9cc83771084c519162e381b037bcbb7cad4afeeeb6da2a099555a84"},"schema_version":"1.0","source":{"id":"2605.05161","kind":"arxiv","version":2}},"canonical_sha256":"3c1127db5d6ecbbc8a941f0345ca35169c8cb3bfd5f359c169aec439d9573369","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c1127db5d6ecbbc8a941f0345ca35169c8cb3bfd5f359c169aec439d9573369","first_computed_at":"2026-06-23T02:12:49.712750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:12:49.712750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"njhjY3Qidhgbb5T/n+sP36zINepHvpvbPfv/ye/c4SJj0CB3hvXZXU/hlH7KhshTWehd9ldd4Esor9rbydRtDw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:12:49.713141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.05161","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33f98c2b5ef907fdd4b2082535362c074a26612760cac03b5449586dca6a8186","sha256:28125268263a8c583abfdf2e48a5277c70ca8fbe85607f9f1a67881efd01d3a6"],"state_sha256":"d6399bbce94e16ee6025756ab2a6fb7c697bdf92d986a63ccd01804fe50d0b96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CDSQTj7z6AM+2MAWxRVY7OXSN0izzyW3WmWkDJZA1CECCEh1V79QekqUR98oB7P87CQyvdFzNGBXuOZ/UHNmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T00:17:06.287049Z","bundle_sha256":"2d6dfc16e420944fe08cf69ead4bdf87eb5dd2cc9593824a9f8ba6c74b4a4ec9"}}