{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GF535LANZLNCALV4X5KWMX34EP","short_pith_number":"pith:GF535LAN","schema_version":"1.0","canonical_sha256":"317bbeac0dcada202ebcbf55665f7c23f854aba4a34f216a98e1b60cf6a4b0c8","source":{"kind":"arxiv","id":"2606.22617","version":1},"attestation_state":"computed","paper":{"title":"OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Duc Minh Nguyen, Duy Minh Ho Nguyen, Hao Vo, Khoa Vo, Ngan Le, Nghi D. Q. Bui, Ngo Xuan Cuong, Phu Loc Nguyen, Sieu Tran","submitted_at":"2026-06-21T17:47:31Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved remarkable performance on 2D visual tasks, yet enhancing their spatial intelligence for real-world applications such as Autonomous Vehicles (AV) remains an open challenge. Existing geometry-aware MLLMs typically rely on auxiliary 3D models at inference time, introducing pipeline complexity and the risk of cascading failures. In this paper, we present OmniSpace, a simple yet effective plug-and-play paradigm for geometry-aware spatial reasoning from purely 2D observations. Motivated by our finding that current MLLMs are bottlenecked by weak "},"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":"2606.22617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-21T17:47:31Z","cross_cats_sorted":[],"title_canon_sha256":"6a629a991f913f57293fdcad3e2d2abf4de52caed835e7e023d54a3f9d74fc57","abstract_canon_sha256":"0c2b60c4059908d7db536db58f06b96b29823c6f15995bc22a6d13fb3786c51f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:43.204215Z","signature_b64":"5N4lMb+GjhuRz7nbMTMrBzop1wOg9ZOQPtFWNmOAuZggZWWoguhwUZ5A0zrqpsQc8zZcX9ReOQRIPkCh38kLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"317bbeac0dcada202ebcbf55665f7c23f854aba4a34f216a98e1b60cf6a4b0c8","last_reissued_at":"2026-06-23T02:13:43.203801Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:43.203801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Duc Minh Nguyen, Duy Minh Ho Nguyen, Hao Vo, Khoa Vo, Ngan Le, Nghi D. Q. Bui, Ngo Xuan Cuong, Phu Loc Nguyen, Sieu Tran","submitted_at":"2026-06-21T17:47:31Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved remarkable performance on 2D visual tasks, yet enhancing their spatial intelligence for real-world applications such as Autonomous Vehicles (AV) remains an open challenge. Existing geometry-aware MLLMs typically rely on auxiliary 3D models at inference time, introducing pipeline complexity and the risk of cascading failures. In this paper, we present OmniSpace, a simple yet effective plug-and-play paradigm for geometry-aware spatial reasoning from purely 2D observations. Motivated by our finding that current MLLMs are bottlenecked by weak "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22617","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/2606.22617/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":"2606.22617","created_at":"2026-06-23T02:13:43.203865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22617v1","created_at":"2026-06-23T02:13:43.203865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22617","created_at":"2026-06-23T02:13:43.203865+00:00"},{"alias_kind":"pith_short_12","alias_value":"GF535LANZLNC","created_at":"2026-06-23T02:13:43.203865+00:00"},{"alias_kind":"pith_short_16","alias_value":"GF535LANZLNCALV4","created_at":"2026-06-23T02:13:43.203865+00:00"},{"alias_kind":"pith_short_8","alias_value":"GF535LAN","created_at":"2026-06-23T02:13:43.203865+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/GF535LANZLNCALV4X5KWMX34EP","json":"https://pith.science/pith/GF535LANZLNCALV4X5KWMX34EP.json","graph_json":"https://pith.science/api/pith-number/GF535LANZLNCALV4X5KWMX34EP/graph.json","events_json":"https://pith.science/api/pith-number/GF535LANZLNCALV4X5KWMX34EP/events.json","paper":"https://pith.science/paper/GF535LAN"},"agent_actions":{"view_html":"https://pith.science/pith/GF535LANZLNCALV4X5KWMX34EP","download_json":"https://pith.science/pith/GF535LANZLNCALV4X5KWMX34EP.json","view_paper":"https://pith.science/paper/GF535LAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22617&json=true","fetch_graph":"https://pith.science/api/pith-number/GF535LANZLNCALV4X5KWMX34EP/graph.json","fetch_events":"https://pith.science/api/pith-number/GF535LANZLNCALV4X5KWMX34EP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GF535LANZLNCALV4X5KWMX34EP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GF535LANZLNCALV4X5KWMX34EP/action/storage_attestation","attest_author":"https://pith.science/pith/GF535LANZLNCALV4X5KWMX34EP/action/author_attestation","sign_citation":"https://pith.science/pith/GF535LANZLNCALV4X5KWMX34EP/action/citation_signature","submit_replication":"https://pith.science/pith/GF535LANZLNCALV4X5KWMX34EP/action/replication_record"}},"created_at":"2026-06-23T02:13:43.203865+00:00","updated_at":"2026-06-23T02:13:43.203865+00:00"}