{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JM5BIDNVCP3RE4ITLUZ6JFKK5O","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":"84b5a50f01efed576da9fd608f88f0f8c8f43236f7ed81fb133dd27bcad04efa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:11:17Z","title_canon_sha256":"90b9c441bba235778d8a67f1d1b094c97502dcde0cda233d2b9396133f16a348"},"schema_version":"1.0","source":{"id":"2605.12413","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12413","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12413v3","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12413","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"JM5BIDNVCP3R","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"JM5BIDNVCP3RE4IT","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"JM5BIDNV","created_at":"2026-05-20T00:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:cd10cf6964b7d431df864d64bf0b73e37726fa80b00e1af32cab7973c32fcd78","target":"graph","created_at":"2026-05-20T00:05:47Z","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":"PCSR is a key bottleneck in current MLLMs and highlight limited but meaningful room for recovery under targeted optimization."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The eight tasks in PCSR-Bench accurately isolate perspective-conditioned spatial reasoning without confounding effects from omnidirectional projection artifacts or question-generation biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A new benchmark reveals MLLMs achieve only 13% or lower accuracy on advanced perspective-conditioned spatial tasks in omnidirectional images, with RL reward shaping raising a 7B model from 31% to 60% in controlled settings."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multimodal large language models show a large gap between perception and perspective-conditioned spatial reasoning on omnidirectional images."}],"snapshot_sha256":"7a17d1ad70428c0b56da8d7e0427ad45f097508494f042233811c88d771824d6"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"3ea6f60a156eda1df9f77acbb6fef223fedf3167d30d1e6554a91ddc180e44ec"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.860991Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T10:35:35.000735Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T08:01:18.507009Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T07:31:32.721814Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.12413/integrity.json","findings":[],"snapshot_sha256":"13154b31e2f6361e4ea177480e6d28d63cd716ad5c838290c8c900c4461b2fe7","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) show strong visual perception, yet remain limited in reasoning about space under changing viewpoints. We study this challenge as Perspective-Conditioned Spatial Reasoning (PCSR) in 360-degree omnidirectional images, where broad scene coverage reduces ambiguity from partial observations without eliminating the need for viewpoint-dependent inference. To assess this capability, we introduce PCSR-Bench, a diagnostic benchmark of 84,373 question-answer pairs from 2,600 omnidirectional images across 26 indoor environments. PCSR-Bench contains eight tasks span","authors_text":"(2) Guangzhou University, (3) Queen Mary University of London, 4) ((1) The Hong Kong Polytechnic University, (4) HKUST (Guangzhou)), Ioannis Patras, Jiaxing Li, Wai Keung Wong, Xu Zheng, Yuangong Chen","cross_cats":[],"headline":"Multimodal large language models show a large gap between perception and perspective-conditioned spatial reasoning on omnidirectional images.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:11:17Z","title":"Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.12413","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-14T21:34:00.189518Z","id":"5063b759-8873-4a38-b55c-4318642c8606","model_set":{"reader":"grok-4.3"},"one_line_summary":"A new benchmark reveals MLLMs achieve only 13% or lower accuracy on advanced perspective-conditioned spatial tasks in omnidirectional images, with RL reward shaping raising a 7B model from 31% to 60% in controlled settings.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Multimodal large language models show a large gap between perception and perspective-conditioned spatial reasoning on omnidirectional images.","strongest_claim":"PCSR is a key bottleneck in current MLLMs and highlight limited but meaningful room for recovery under targeted optimization.","weakest_assumption":"The eight tasks in PCSR-Bench accurately isolate perspective-conditioned spatial reasoning without confounding effects from omnidirectional projection artifacts or question-generation biases."}},"verdict_id":"5063b759-8873-4a38-b55c-4318642c8606"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ea0d0897547ef7ff26b6eb212efa753359892f5d6e63af112c9ec9f289b9186b","target":"record","created_at":"2026-05-20T00:05:47Z","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":"84b5a50f01efed576da9fd608f88f0f8c8f43236f7ed81fb133dd27bcad04efa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:11:17Z","title_canon_sha256":"90b9c441bba235778d8a67f1d1b094c97502dcde0cda233d2b9396133f16a348"},"schema_version":"1.0","source":{"id":"2605.12413","kind":"arxiv","version":3}},"canonical_sha256":"4b3a140db513f71271135d33e4954aebb35e09ab2ad406268bff8aa860c39f3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b3a140db513f71271135d33e4954aebb35e09ab2ad406268bff8aa860c39f3b","first_computed_at":"2026-05-20T00:05:47.312094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:47.312094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4IJ6/BwJ/Kzz4fhLFH7Py4yNxY2lCa5h241vpK57zNwd+EjtUfDQT08dUcqy0AFRmZBBcOuxO/y8Uiczu9fnBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:47.312678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12413","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea0d0897547ef7ff26b6eb212efa753359892f5d6e63af112c9ec9f289b9186b","sha256:cd10cf6964b7d431df864d64bf0b73e37726fa80b00e1af32cab7973c32fcd78"],"state_sha256":"bde3f9c754adedf7b0ff287a9d4bb5a842047adde64f468edb9455b92bf3c3d0"}