{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3UNT65XALHIDRHRC3CVJNQMAW5","short_pith_number":"pith:3UNT65XA","schema_version":"1.0","canonical_sha256":"dd1b3f76e059d0389e22d8aa96c180b75b297fffacdf9ca48e8764b3d6c11c51","source":{"kind":"arxiv","id":"2505.11907","version":1},"attestation_state":"computed","paper":{"title":"Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danda Pani Paudel, Kailun Yang, Luc Van Gool, Xuming Hu, Xu Zheng, Yuanhuiyi Lyu, Zihao Dongfang, Ziqiao Weng","submitted_at":"2025-05-17T08:48:40Z","abstract_excerpt":"The 180x360 omnidirectional field of view captured by 360-degree cameras enables their use in a wide range of applications such as embodied AI and virtual reality. Although recent advances in multimodal large language models (MLLMs) have shown promise in visual-spatial reasoning, most studies focus on standard pinhole-view images, leaving omnidirectional perception largely unexplored. In this paper, we ask: Are MLLMs ready for omnidirectional spatial reasoning? To investigate this, we introduce OSR-Bench, the first benchmark specifically designed for this setting. OSR-Bench includes over 153,0"},"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":"2505.11907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-17T08:48:40Z","cross_cats_sorted":[],"title_canon_sha256":"cbbb5e908d4e95ec991b72e58c3b800f4d5d02bc1ca03d84485a2b4b7079d271","abstract_canon_sha256":"8917fae69274740b2279b338799177142d687df3847b2379873ef7a7e50abe86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:54.474623Z","signature_b64":"pH2CKNE0wJ2QpK80HU/s/Rn6z3G6F0Dnn+XTVylVl12WD2gyqMtvtYkHUgTJX6ZEudI12lY4g+4nUt0Q2641Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd1b3f76e059d0389e22d8aa96c180b75b297fffacdf9ca48e8764b3d6c11c51","last_reissued_at":"2026-07-05T11:04:54.474080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:54.474080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danda Pani Paudel, Kailun Yang, Luc Van Gool, Xuming Hu, Xu Zheng, Yuanhuiyi Lyu, Zihao Dongfang, Ziqiao Weng","submitted_at":"2025-05-17T08:48:40Z","abstract_excerpt":"The 180x360 omnidirectional field of view captured by 360-degree cameras enables their use in a wide range of applications such as embodied AI and virtual reality. Although recent advances in multimodal large language models (MLLMs) have shown promise in visual-spatial reasoning, most studies focus on standard pinhole-view images, leaving omnidirectional perception largely unexplored. In this paper, we ask: Are MLLMs ready for omnidirectional spatial reasoning? To investigate this, we introduce OSR-Bench, the first benchmark specifically designed for this setting. OSR-Bench includes over 153,0"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11907","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.11907/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2505.11907","created_at":"2026-07-05T11:04:54.474139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11907v1","created_at":"2026-07-05T11:04:54.474139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11907","created_at":"2026-07-05T11:04:54.474139+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UNT65XALHID","created_at":"2026-07-05T11:04:54.474139+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UNT65XALHIDRHRC","created_at":"2026-07-05T11:04:54.474139+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UNT65XA","created_at":"2026-07-05T11:04:54.474139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06165","citing_title":"EAGOR: Embodied Reasoning in Omni-direction","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02497","citing_title":"Seek to Segment: Active Perception for Panoramic Referring Segmentation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03577","citing_title":"Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30378","citing_title":"OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27745","citing_title":"Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12413","citing_title":"Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13169","citing_title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12413","citing_title":"Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13169","citing_title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12413","citing_title":"Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09146","citing_title":"Beyond Thinking: Imagining in 360$^\\circ$ for Humanoid Visual Search","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UNT65XALHIDRHRC3CVJNQMAW5","json":"https://pith.science/pith/3UNT65XALHIDRHRC3CVJNQMAW5.json","graph_json":"https://pith.science/api/pith-number/3UNT65XALHIDRHRC3CVJNQMAW5/graph.json","events_json":"https://pith.science/api/pith-number/3UNT65XALHIDRHRC3CVJNQMAW5/events.json","paper":"https://pith.science/paper/3UNT65XA"},"agent_actions":{"view_html":"https://pith.science/pith/3UNT65XALHIDRHRC3CVJNQMAW5","download_json":"https://pith.science/pith/3UNT65XALHIDRHRC3CVJNQMAW5.json","view_paper":"https://pith.science/paper/3UNT65XA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11907&json=true","fetch_graph":"https://pith.science/api/pith-number/3UNT65XALHIDRHRC3CVJNQMAW5/graph.json","fetch_events":"https://pith.science/api/pith-number/3UNT65XALHIDRHRC3CVJNQMAW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UNT65XALHIDRHRC3CVJNQMAW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UNT65XALHIDRHRC3CVJNQMAW5/action/storage_attestation","attest_author":"https://pith.science/pith/3UNT65XALHIDRHRC3CVJNQMAW5/action/author_attestation","sign_citation":"https://pith.science/pith/3UNT65XALHIDRHRC3CVJNQMAW5/action/citation_signature","submit_replication":"https://pith.science/pith/3UNT65XALHIDRHRC3CVJNQMAW5/action/replication_record"}},"created_at":"2026-07-05T11:04:54.474139+00:00","updated_at":"2026-07-05T11:04:54.474139+00:00"}