{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MK5GEPM567UYM3DHAASD25SKMZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"814e378b954227fe8b98b1374d2995a0476dfb6f1255107264a3219e9a5abc3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T13:49:17Z","title_canon_sha256":"bce95e45b7eb57c8766f301825beae0713ee51a491cdd9fe189a33aab15bb00d"},"schema_version":"1.0","source":{"id":"2511.19119","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.19119","created_at":"2026-06-30T01:17:29Z"},{"alias_kind":"arxiv_version","alias_value":"2511.19119v2","created_at":"2026-06-30T01:17:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19119","created_at":"2026-06-30T01:17:29Z"},{"alias_kind":"pith_short_12","alias_value":"MK5GEPM567UY","created_at":"2026-06-30T01:17:29Z"},{"alias_kind":"pith_short_16","alias_value":"MK5GEPM567UYM3DH","created_at":"2026-06-30T01:17:29Z"},{"alias_kind":"pith_short_8","alias_value":"MK5GEPM5","created_at":"2026-06-30T01:17:29Z"}],"graph_snapshots":[{"event_id":"sha256:5f8357ea786a1b56b780cd2e4995dd75df001a40a42777a72410ac2d1771b33a","target":"graph","created_at":"2026-06-30T01:17:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2511.19119/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jingyi He, Qirui Wang, Shijie Li, Si Yong Yeo, Xulei Yang, Yining Pan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T13:49:17Z","title":"MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19119","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:79754126a244af3013c6eac542037547f61c842b0ac68c276e7363083a8a80cb","target":"record","created_at":"2026-06-30T01:17:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"814e378b954227fe8b98b1374d2995a0476dfb6f1255107264a3219e9a5abc3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T13:49:17Z","title_canon_sha256":"bce95e45b7eb57c8766f301825beae0713ee51a491cdd9fe189a33aab15bb00d"},"schema_version":"1.0","source":{"id":"2511.19119","kind":"arxiv","version":2}},"canonical_sha256":"62ba623d9df7e9866c6700243d764a6641002b65a980e51dcea9b9c989bfbcf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62ba623d9df7e9866c6700243d764a6641002b65a980e51dcea9b9c989bfbcf8","first_computed_at":"2026-06-30T01:17:29.835820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:29.835820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jAxZkGhqZ+ap9McSlPNZNWoBzi/R0j26J1z0yMTMiCqxuFhOniIb6NlFdrv/Bk2UkS5hjIb4mv62BNU5jdPCAw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:29.836710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.19119","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79754126a244af3013c6eac542037547f61c842b0ac68c276e7363083a8a80cb","sha256:5f8357ea786a1b56b780cd2e4995dd75df001a40a42777a72410ac2d1771b33a"],"state_sha256":"11dc799e9ceaeb6bb71e2880937a61b8437bfd6fd0cbd61ed06b563ac750c2be"}