{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2TIXMAIHHPJKLZW6RCNM2LYZMV","short_pith_number":"pith:2TIXMAIH","schema_version":"1.0","canonical_sha256":"d4d17601073bd2a5e6de889acd2f19656a32c36285a3a7a67d7cfb904531b219","source":{"kind":"arxiv","id":"2506.14471","version":1},"attestation_state":"computed","paper":{"title":"Dense360: Dense Understanding from Omnidirectional Panoramas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dizhe Zhang, Lu Qi, Shunping Ji, Tao Zhang, Xiangtai Li, Yikang Zhou","submitted_at":"2025-06-17T12:35:23Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) require comprehensive visual inputs to achieve dense understanding of the physical world. While existing MLLMs demonstrate impressive world understanding capabilities through limited field-of-view (FOV) visual inputs (e.g., 70 degree), we take the first step toward dense understanding from omnidirectional panoramas. We first introduce an omnidirectional panoramas dataset featuring a comprehensive suite of reliability-scored annotations. Specifically, our dataset contains 160K panoramas with 5M dense entity-level captions, 1M unique referring expressions"},"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":"2506.14471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T12:35:23Z","cross_cats_sorted":[],"title_canon_sha256":"403f7dcf802ea99e7bcadc58b2ec612ea4838b9321f14d2af17a4722068f869a","abstract_canon_sha256":"7e26d7372ca99fafa5eeef33a5aa2e1bb3da2e36917d486a82b714c248be65ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:57.203406Z","signature_b64":"vOUoME8phE3G341kiJfdhsU2OSoZtJFAu/yVZNxvm5t7hhV6tS4YC366YwvL96oicgkMaSunTH+6nqewKddwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4d17601073bd2a5e6de889acd2f19656a32c36285a3a7a67d7cfb904531b219","last_reissued_at":"2026-07-05T11:22:57.202879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:57.202879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense360: Dense Understanding from Omnidirectional Panoramas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dizhe Zhang, Lu Qi, Shunping Ji, Tao Zhang, Xiangtai Li, Yikang Zhou","submitted_at":"2025-06-17T12:35:23Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) require comprehensive visual inputs to achieve dense understanding of the physical world. While existing MLLMs demonstrate impressive world understanding capabilities through limited field-of-view (FOV) visual inputs (e.g., 70 degree), we take the first step toward dense understanding from omnidirectional panoramas. We first introduce an omnidirectional panoramas dataset featuring a comprehensive suite of reliability-scored annotations. Specifically, our dataset contains 160K panoramas with 5M dense entity-level captions, 1M unique referring expressions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14471","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/2506.14471/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":"2506.14471","created_at":"2026-07-05T11:22:57.202943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14471v1","created_at":"2026-07-05T11:22:57.202943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14471","created_at":"2026-07-05T11:22:57.202943+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TIXMAIHHPJK","created_at":"2026-07-05T11:22:57.202943+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TIXMAIHHPJKLZW6","created_at":"2026-07-05T11:22:57.202943+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TIXMAIH","created_at":"2026-07-05T11:22:57.202943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02497","citing_title":"Seek to Segment: Active Perception for Panoramic Referring Segmentation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30378","citing_title":"OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning","ref_index":52,"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":141,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13169","citing_title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13169","citing_title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2TIXMAIHHPJKLZW6RCNM2LYZMV","json":"https://pith.science/pith/2TIXMAIHHPJKLZW6RCNM2LYZMV.json","graph_json":"https://pith.science/api/pith-number/2TIXMAIHHPJKLZW6RCNM2LYZMV/graph.json","events_json":"https://pith.science/api/pith-number/2TIXMAIHHPJKLZW6RCNM2LYZMV/events.json","paper":"https://pith.science/paper/2TIXMAIH"},"agent_actions":{"view_html":"https://pith.science/pith/2TIXMAIHHPJKLZW6RCNM2LYZMV","download_json":"https://pith.science/pith/2TIXMAIHHPJKLZW6RCNM2LYZMV.json","view_paper":"https://pith.science/paper/2TIXMAIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14471&json=true","fetch_graph":"https://pith.science/api/pith-number/2TIXMAIHHPJKLZW6RCNM2LYZMV/graph.json","fetch_events":"https://pith.science/api/pith-number/2TIXMAIHHPJKLZW6RCNM2LYZMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TIXMAIHHPJKLZW6RCNM2LYZMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TIXMAIHHPJKLZW6RCNM2LYZMV/action/storage_attestation","attest_author":"https://pith.science/pith/2TIXMAIHHPJKLZW6RCNM2LYZMV/action/author_attestation","sign_citation":"https://pith.science/pith/2TIXMAIHHPJKLZW6RCNM2LYZMV/action/citation_signature","submit_replication":"https://pith.science/pith/2TIXMAIHHPJKLZW6RCNM2LYZMV/action/replication_record"}},"created_at":"2026-07-05T11:22:57.202943+00:00","updated_at":"2026-07-05T11:22:57.202943+00:00"}