{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MK5GEPM567UYM3DHAASD25SKMZ","short_pith_number":"pith:MK5GEPM5","schema_version":"1.0","canonical_sha256":"62ba623d9df7e9866c6700243d764a6641002b65a980e51dcea9b9c989bfbcf8","source":{"kind":"arxiv","id":"2511.19119","version":2},"attestation_state":"computed","paper":{"title":"MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingyi He, Qirui Wang, Shijie Li, Si Yong Yeo, Xulei Yang, Yining Pan","submitted_at":"2025-11-24T13:49:17Z","abstract_excerpt":"Spatial reasoning (SR), the ability to infer 3D spatial information from 2D inputs, is essential for real-world applications such as embodied AI and autonomous driving. However, existing research primarily focuses on indoor environments and typically relies on multi-view observations, which limits their generalizability to outdoor scenarios and constrains their applicability to monocular images, the most common real-world setting. In this work, we propose MonoSR, a large-scale monocular spatial reasoning dataset that spans diverse scenarios including indoor, outdoor, and object-centric setting"},"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":"2511.19119","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T13:49:17Z","cross_cats_sorted":[],"title_canon_sha256":"bce95e45b7eb57c8766f301825beae0713ee51a491cdd9fe189a33aab15bb00d","abstract_canon_sha256":"814e378b954227fe8b98b1374d2995a0476dfb6f1255107264a3219e9a5abc3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:29.836710Z","signature_b64":"jAxZkGhqZ+ap9McSlPNZNWoBzi/R0j26J1z0yMTMiCqxuFhOniIb6NlFdrv/Bk2UkS5hjIb4mv62BNU5jdPCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62ba623d9df7e9866c6700243d764a6641002b65a980e51dcea9b9c989bfbcf8","last_reissued_at":"2026-06-30T01:17:29.835820Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:29.835820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingyi He, Qirui Wang, Shijie Li, Si Yong Yeo, Xulei Yang, Yining Pan","submitted_at":"2025-11-24T13:49:17Z","abstract_excerpt":"Spatial reasoning (SR), the ability to infer 3D spatial information from 2D inputs, is essential for real-world applications such as embodied AI and autonomous driving. However, existing research primarily focuses on indoor environments and typically relies on multi-view observations, which limits their generalizability to outdoor scenarios and constrains their applicability to monocular images, the most common real-world setting. In this work, we propose MonoSR, a large-scale monocular spatial reasoning dataset that spans diverse scenarios including indoor, outdoor, and object-centric setting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19119","kind":"arxiv","version":2},"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/2511.19119/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":"2511.19119","created_at":"2026-06-30T01:17:29.835948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.19119v2","created_at":"2026-06-30T01:17:29.835948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19119","created_at":"2026-06-30T01:17:29.835948+00:00"},{"alias_kind":"pith_short_12","alias_value":"MK5GEPM567UY","created_at":"2026-06-30T01:17:29.835948+00:00"},{"alias_kind":"pith_short_16","alias_value":"MK5GEPM567UYM3DH","created_at":"2026-06-30T01:17:29.835948+00:00"},{"alias_kind":"pith_short_8","alias_value":"MK5GEPM5","created_at":"2026-06-30T01:17:29.835948+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/MK5GEPM567UYM3DHAASD25SKMZ","json":"https://pith.science/pith/MK5GEPM567UYM3DHAASD25SKMZ.json","graph_json":"https://pith.science/api/pith-number/MK5GEPM567UYM3DHAASD25SKMZ/graph.json","events_json":"https://pith.science/api/pith-number/MK5GEPM567UYM3DHAASD25SKMZ/events.json","paper":"https://pith.science/paper/MK5GEPM5"},"agent_actions":{"view_html":"https://pith.science/pith/MK5GEPM567UYM3DHAASD25SKMZ","download_json":"https://pith.science/pith/MK5GEPM567UYM3DHAASD25SKMZ.json","view_paper":"https://pith.science/paper/MK5GEPM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.19119&json=true","fetch_graph":"https://pith.science/api/pith-number/MK5GEPM567UYM3DHAASD25SKMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MK5GEPM567UYM3DHAASD25SKMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MK5GEPM567UYM3DHAASD25SKMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MK5GEPM567UYM3DHAASD25SKMZ/action/storage_attestation","attest_author":"https://pith.science/pith/MK5GEPM567UYM3DHAASD25SKMZ/action/author_attestation","sign_citation":"https://pith.science/pith/MK5GEPM567UYM3DHAASD25SKMZ/action/citation_signature","submit_replication":"https://pith.science/pith/MK5GEPM567UYM3DHAASD25SKMZ/action/replication_record"}},"created_at":"2026-06-30T01:17:29.835948+00:00","updated_at":"2026-06-30T01:17:29.835948+00:00"}