{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LVMI43G5P74WCAAN6IPC2DSQFX","short_pith_number":"pith:LVMI43G5","schema_version":"1.0","canonical_sha256":"5d588e6cdd7ff961000df21e2d0e502dd8fe5b19f72f799ee444bd48adeb691a","source":{"kind":"arxiv","id":"2605.18621","version":1},"attestation_state":"computed","paper":{"title":"CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun Xiao, Siliang Tang, Tianwei Lin, Wei Wang, Wenqiao Zhang, Yueting Zhuang, Yuqian Yuan","submitted_at":"2026-05-18T16:31:31Z","abstract_excerpt":"Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and interactions across multiple viewpoints. However, progress in cross-view reasoning remains limited by three major gaps: the scarcity of large-scale well-annotated training data, the lack of comprehensive benchmarks for systematic evaluation, and the absence of explicit alignment mechanisms that establish object-level consistency across views. To address these gaps, we thoroughly develop CrossView Suite across three coordin"},"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":"2605.18621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T16:31:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e6dfeb486d654436ba90795daf444c96f5a9035780d61b7091166236709f1c9f","abstract_canon_sha256":"00db1fcb9a44961645bffe88dc57facfd5297b75c6b479590cf60677a1e74231"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:11.250441Z","signature_b64":"RPLSZX2dsQgTzK2SXUy0h9rbWQ8TpnmzRutXQePw1E53vhyT344PadpO4qv2lxFG4jdEw1TXJS4ZJmFx+t+EBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d588e6cdd7ff961000df21e2d0e502dd8fe5b19f72f799ee444bd48adeb691a","last_reissued_at":"2026-05-20T00:06:11.249533Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:11.249533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun Xiao, Siliang Tang, Tianwei Lin, Wei Wang, Wenqiao Zhang, Yueting Zhuang, Yuqian Yuan","submitted_at":"2026-05-18T16:31:31Z","abstract_excerpt":"Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and interactions across multiple viewpoints. However, progress in cross-view reasoning remains limited by three major gaps: the scarcity of large-scale well-annotated training data, the lack of comprehensive benchmarks for systematic evaluation, and the absence of explicit alignment mechanisms that establish object-level consistency across views. To address these gaps, we thoroughly develop CrossView Suite across three coordin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18621","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/2605.18621/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.220878Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"072d8d274cc96f84d0949714656b2528803bdec3094d91234ec3cbcdf670e1a2"},"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":"2605.18621","created_at":"2026-05-20T00:06:11.249720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18621v1","created_at":"2026-05-20T00:06:11.249720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18621","created_at":"2026-05-20T00:06:11.249720+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVMI43G5P74W","created_at":"2026-05-20T00:06:11.249720+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVMI43G5P74WCAAN","created_at":"2026-05-20T00:06:11.249720+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVMI43G5","created_at":"2026-05-20T00:06:11.249720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LVMI43G5P74WCAAN6IPC2DSQFX","json":"https://pith.science/pith/LVMI43G5P74WCAAN6IPC2DSQFX.json","graph_json":"https://pith.science/api/pith-number/LVMI43G5P74WCAAN6IPC2DSQFX/graph.json","events_json":"https://pith.science/api/pith-number/LVMI43G5P74WCAAN6IPC2DSQFX/events.json","paper":"https://pith.science/paper/LVMI43G5"},"agent_actions":{"view_html":"https://pith.science/pith/LVMI43G5P74WCAAN6IPC2DSQFX","download_json":"https://pith.science/pith/LVMI43G5P74WCAAN6IPC2DSQFX.json","view_paper":"https://pith.science/paper/LVMI43G5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18621&json=true","fetch_graph":"https://pith.science/api/pith-number/LVMI43G5P74WCAAN6IPC2DSQFX/graph.json","fetch_events":"https://pith.science/api/pith-number/LVMI43G5P74WCAAN6IPC2DSQFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVMI43G5P74WCAAN6IPC2DSQFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVMI43G5P74WCAAN6IPC2DSQFX/action/storage_attestation","attest_author":"https://pith.science/pith/LVMI43G5P74WCAAN6IPC2DSQFX/action/author_attestation","sign_citation":"https://pith.science/pith/LVMI43G5P74WCAAN6IPC2DSQFX/action/citation_signature","submit_replication":"https://pith.science/pith/LVMI43G5P74WCAAN6IPC2DSQFX/action/replication_record"}},"created_at":"2026-05-20T00:06:11.249720+00:00","updated_at":"2026-05-20T00:06:11.249720+00:00"}