{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KER2J5HK3IQTDSQD6VTU762GCJ","short_pith_number":"pith:KER2J5HK","schema_version":"1.0","canonical_sha256":"5123a4f4eada2131ca03f5674ffb46127579a9eb5302d7ff12fe1262f87d4522","source":{"kind":"arxiv","id":"2505.14197","version":1},"attestation_state":"computed","paper":{"title":"Towards Omnidirectional Reasoning with 360-R1: A Dataset, Benchmark, and GRPO-based Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xinshen Zhang, Xu Zheng, Zhen Ye","submitted_at":"2025-05-20T10:55:26Z","abstract_excerpt":"Omnidirectional images (ODIs), with their 360{\\deg} field of view, provide unparalleled spatial awareness for immersive applications like augmented reality and embodied AI. However, the capability of existing multi-modal large language models (MLLMs) to comprehend and reason about such panoramic scenes remains underexplored. This paper addresses this gap by introducing OmniVQA, the first dataset and conducting the first benchmark for omnidirectional visual question answering. Our evaluation of state-of-the-art MLLMs reveals significant limitations in handling omnidirectional visual question an"},"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":"2505.14197","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T10:55:26Z","cross_cats_sorted":[],"title_canon_sha256":"1b7820e1bac9a6075a7645c37fc2e4645cfde0f8d08bec2b6c1739dc459c442e","abstract_canon_sha256":"575a68bab5a57d1f08e43278f2b120749b8323bc51ad8f96ccef7849b576c303"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:57.605997Z","signature_b64":"RMpKJNhhJnGeMSQ7ZbYSVJVJpFW1RdAIeRXynliR79ew56OTdUpVBVFyjpX6wPcO6WXRgUKYwkIFMqvak+3gDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5123a4f4eada2131ca03f5674ffb46127579a9eb5302d7ff12fe1262f87d4522","last_reissued_at":"2026-07-05T11:05:57.605506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:57.605506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Omnidirectional Reasoning with 360-R1: A Dataset, Benchmark, and GRPO-based Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xinshen Zhang, Xu Zheng, Zhen Ye","submitted_at":"2025-05-20T10:55:26Z","abstract_excerpt":"Omnidirectional images (ODIs), with their 360{\\deg} field of view, provide unparalleled spatial awareness for immersive applications like augmented reality and embodied AI. However, the capability of existing multi-modal large language models (MLLMs) to comprehend and reason about such panoramic scenes remains underexplored. This paper addresses this gap by introducing OmniVQA, the first dataset and conducting the first benchmark for omnidirectional visual question answering. Our evaluation of state-of-the-art MLLMs reveals significant limitations in handling omnidirectional visual question an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14197","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/2505.14197/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":"2505.14197","created_at":"2026-07-05T11:05:57.605568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14197v1","created_at":"2026-07-05T11:05:57.605568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14197","created_at":"2026-07-05T11:05:57.605568+00:00"},{"alias_kind":"pith_short_12","alias_value":"KER2J5HK3IQT","created_at":"2026-07-05T11:05:57.605568+00:00"},{"alias_kind":"pith_short_16","alias_value":"KER2J5HK3IQTDSQD","created_at":"2026-07-05T11:05:57.605568+00:00"},{"alias_kind":"pith_short_8","alias_value":"KER2J5HK","created_at":"2026-07-05T11:05:57.605568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30378","citing_title":"OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning","ref_index":45,"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":126,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17171","citing_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","ref_index":62,"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":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13169","citing_title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17171","citing_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","ref_index":62,"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":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13169","citing_title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","ref_index":58,"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":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KER2J5HK3IQTDSQD6VTU762GCJ","json":"https://pith.science/pith/KER2J5HK3IQTDSQD6VTU762GCJ.json","graph_json":"https://pith.science/api/pith-number/KER2J5HK3IQTDSQD6VTU762GCJ/graph.json","events_json":"https://pith.science/api/pith-number/KER2J5HK3IQTDSQD6VTU762GCJ/events.json","paper":"https://pith.science/paper/KER2J5HK"},"agent_actions":{"view_html":"https://pith.science/pith/KER2J5HK3IQTDSQD6VTU762GCJ","download_json":"https://pith.science/pith/KER2J5HK3IQTDSQD6VTU762GCJ.json","view_paper":"https://pith.science/paper/KER2J5HK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14197&json=true","fetch_graph":"https://pith.science/api/pith-number/KER2J5HK3IQTDSQD6VTU762GCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KER2J5HK3IQTDSQD6VTU762GCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KER2J5HK3IQTDSQD6VTU762GCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KER2J5HK3IQTDSQD6VTU762GCJ/action/storage_attestation","attest_author":"https://pith.science/pith/KER2J5HK3IQTDSQD6VTU762GCJ/action/author_attestation","sign_citation":"https://pith.science/pith/KER2J5HK3IQTDSQD6VTU762GCJ/action/citation_signature","submit_replication":"https://pith.science/pith/KER2J5HK3IQTDSQD6VTU762GCJ/action/replication_record"}},"created_at":"2026-07-05T11:05:57.605568+00:00","updated_at":"2026-07-05T11:05:57.605568+00:00"}