{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QNYMSVQLLPHAYRPRRLZSAOTZ3M","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":"be774c1d5c41ff0ddf435f3c63c572bddbcea74aa957fb94cb095ff5dfe21ed8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T11:44:06Z","title_canon_sha256":"9a8375ff00f30c7eff5c1456a2bbb5e5ddc3c9796cc374d81134871563792baf"},"schema_version":"1.0","source":{"id":"2508.00549","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00549","created_at":"2026-07-05T11:50:39Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00549v2","created_at":"2026-07-05T11:50:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00549","created_at":"2026-07-05T11:50:39Z"},{"alias_kind":"pith_short_12","alias_value":"QNYMSVQLLPHA","created_at":"2026-07-05T11:50:39Z"},{"alias_kind":"pith_short_16","alias_value":"QNYMSVQLLPHAYRPR","created_at":"2026-07-05T11:50:39Z"},{"alias_kind":"pith_short_8","alias_value":"QNYMSVQL","created_at":"2026-07-05T11:50:39Z"}],"graph_snapshots":[{"event_id":"sha256:e69f8a3974dc637ab8d83d54c8b89016ee5dbe8f1d4eff8e5b75d644d67c0457","target":"graph","created_at":"2026-07-05T11:50:39Z","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/2508.00549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clinical decision-making relies heavily on understanding relative positions of anatomical structures and anomalies. Therefore, for Vision-Language Models (VLMs) to be applicable in clinical practice, the ability to accurately determine relative positions on medical images is a fundamental prerequisite. Despite its importance, this capability remains highly underexplored. To address this gap, we evaluate the ability of state-of-the-art VLMs, GPT-4o, Llama3.2, Pixtral, and JanusPro, and find that all models fail at this fundamental task. Inspired by successful approaches in computer vision, we i","authors_text":"Alex B\\\"auerle, Billurvan Taskin, Daniel Wolf, Heiko Hillenhagen, Meinrad Beer, Michael G\\\"otz, Timo Ropinski","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T11:44:06Z","title":"Your other Left! Vision-Language Models Fail to Identify Relative Positions in Medical Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00549","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":"sha256:230208dbf871a4ebfddf22aa173287eee37fba31398aa768e8697c4da0d34eed","target":"record","created_at":"2026-07-05T11:50:39Z","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":"be774c1d5c41ff0ddf435f3c63c572bddbcea74aa957fb94cb095ff5dfe21ed8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T11:44:06Z","title_canon_sha256":"9a8375ff00f30c7eff5c1456a2bbb5e5ddc3c9796cc374d81134871563792baf"},"schema_version":"1.0","source":{"id":"2508.00549","kind":"arxiv","version":2}},"canonical_sha256":"8370c9560b5bce0c45f18af3203a79db05a7a75e95d570b288ff660db2bea1b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8370c9560b5bce0c45f18af3203a79db05a7a75e95d570b288ff660db2bea1b7","first_computed_at":"2026-07-05T11:50:39.183065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:39.183065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d6oU3P/aijenzgucIctVKOnwwFcESx7QWU9gZQDgX5T3VvdL7wE5t6K35f3npF0fsfgX51Zp4sy32LbzFk38BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:39.183526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.00549","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:230208dbf871a4ebfddf22aa173287eee37fba31398aa768e8697c4da0d34eed","sha256:e69f8a3974dc637ab8d83d54c8b89016ee5dbe8f1d4eff8e5b75d644d67c0457"],"state_sha256":"36a7c13abca0e3451a6af9526f632cfcedc444694eadefba7687c4d0a9ae4d01"}