{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JM5BIDNVCP3RE4ITLUZ6JFKK5O","short_pith_number":"pith:JM5BIDNV","canonical_record":{"source":{"id":"2605.12413","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:11:17Z","cross_cats_sorted":[],"title_canon_sha256":"90b9c441bba235778d8a67f1d1b094c97502dcde0cda233d2b9396133f16a348","abstract_canon_sha256":"84b5a50f01efed576da9fd608f88f0f8c8f43236f7ed81fb133dd27bcad04efa"},"schema_version":"1.0"},"canonical_sha256":"4b3a140db513f71271135d33e4954aebb35e09ab2ad406268bff8aa860c39f3b","source":{"kind":"arxiv","id":"2605.12413","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JM5BIDNVCP3RE4ITLUZ6JFKK5O","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12413","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:11:17Z","cross_cats_sorted":[],"title_canon_sha256":"90b9c441bba235778d8a67f1d1b094c97502dcde0cda233d2b9396133f16a348","abstract_canon_sha256":"84b5a50f01efed576da9fd608f88f0f8c8f43236f7ed81fb133dd27bcad04efa"},"schema_version":"1.0"},"canonical_sha256":"4b3a140db513f71271135d33e4954aebb35e09ab2ad406268bff8aa860c39f3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:47.312678Z","signature_b64":"4IJ6/BwJ/Kzz4fhLFH7Py4yNxY2lCa5h241vpK57zNwd+EjtUfDQT08dUcqy0AFRmZBBcOuxO/y8Uiczu9fnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b3a140db513f71271135d33e4954aebb35e09ab2ad406268bff8aa860c39f3b","last_reissued_at":"2026-05-20T00:05:47.312094Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:47.312094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12413","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8PThfrn81yaxWSXFelqeaDoHFJ+FCq6VIaGn7MpfBWAT0f0v3X+6lvWhGYOyg24MhhAk0TONTsXNSnUHeqwfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:48:27.610880Z"},"content_sha256":"ea0d0897547ef7ff26b6eb212efa753359892f5d6e63af112c9ec9f289b9186b","schema_version":"1.0","event_id":"sha256:ea0d0897547ef7ff26b6eb212efa753359892f5d6e63af112c9ec9f289b9186b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JM5BIDNVCP3RE4ITLUZ6JFKK5O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multimodal large language models show a large gap between perception and perspective-conditioned spatial reasoning on omnidirectional images.","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-05-12T17:11:17Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PCSR is a key bottleneck in current MLLMs and highlight limited but meaningful room for recovery under targeted optimization.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The eight tasks in PCSR-Bench accurately isolate perspective-conditioned spatial reasoning without confounding effects from omnidirectional projection artifacts or question-generation biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multimodal large language models show a large gap between perception and perspective-conditioned spatial reasoning on omnidirectional images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7a17d1ad70428c0b56da8d7e0427ad45f097508494f042233811c88d771824d6"},"source":{"id":"2605.12413","kind":"arxiv","version":3},"verdict":{"id":"5063b759-8873-4a38-b55c-4318642c8606","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:34:00.189518Z","strongest_claim":"PCSR is a key bottleneck in current MLLMs and highlight limited but meaningful room for recovery under targeted optimization.","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","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.","pith_extraction_headline":"Multimodal large language models show a large gap between perception and perspective-conditioned spatial reasoning on omnidirectional images."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.12413/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"13154b31e2f6361e4ea177480e6d28d63cd716ad5c838290c8c900c4461b2fe7"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"3ea6f60a156eda1df9f77acbb6fef223fedf3167d30d1e6554a91ddc180e44ec"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"5063b759-8873-4a38-b55c-4318642c8606"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TU299OubdRYbHi5IN/qGzcQYIIufY/B2Zz27l8C43TtE+erLoL0TZIn5Ar6dOTwxFyePfwsXU7BErugo+C95BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:48:27.611443Z"},"content_sha256":"cd10cf6964b7d431df864d64bf0b73e37726fa80b00e1af32cab7973c32fcd78","schema_version":"1.0","event_id":"sha256:cd10cf6964b7d431df864d64bf0b73e37726fa80b00e1af32cab7973c32fcd78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JM5BIDNVCP3RE4ITLUZ6JFKK5O/bundle.json","state_url":"https://pith.science/pith/JM5BIDNVCP3RE4ITLUZ6JFKK5O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JM5BIDNVCP3RE4ITLUZ6JFKK5O/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":"2026-05-28T20:48:27Z","links":{"resolver":"https://pith.science/pith/JM5BIDNVCP3RE4ITLUZ6JFKK5O","bundle":"https://pith.science/pith/JM5BIDNVCP3RE4ITLUZ6JFKK5O/bundle.json","state":"https://pith.science/pith/JM5BIDNVCP3RE4ITLUZ6JFKK5O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JM5BIDNVCP3RE4ITLUZ6JFKK5O/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17OTUcGcUmkuFL3Xbk5HZC2pyt1O8VI2c7He3uaP/KrBmmOw1QaeVYrwhRA9kyd4QVA0adEe9fhLbNVHOdU7Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T20:48:27.614039Z","bundle_sha256":"118bc3059062eaf0801863c340c49bbff0861d7c629c3f827ac1674d09894dd6"}}