{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D42YTSRAV7X5OGAD43TREGKO3K","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":"09fc2c5148a64301a62073ddf4b9d8d8f4b8b3821479a2ff17694caaa04ec215","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T07:37:34Z","title_canon_sha256":"59b7f0c6b95a96847797f7f27f053c1f359a018a3d661e00d9ed899ba6b65271"},"schema_version":"1.0","source":{"id":"2505.19015","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19015","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19015v2","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19015","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_12","alias_value":"D42YTSRAV7X5","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_16","alias_value":"D42YTSRAV7X5OGAD","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_8","alias_value":"D42YTSRA","created_at":"2026-07-05T11:50:37Z"}],"graph_snapshots":[{"event_id":"sha256:30a68e78867f03568f3895e0d39ba034e76f11b17615eab8bf5f608b7935da16","target":"graph","created_at":"2026-07-05T11:50:37Z","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/2505.19015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial relation reasoning is a crucial task for multimodal large language models (MLLMs) to understand the objective world. However, current benchmarks have issues like relying on bounding boxes, ignoring perspective substitutions, or allowing questions to be answered using only the model's prior knowledge without image understanding. To address these issues, we introduce SpatialMQA, a human-annotated spatial relation reasoning benchmark based on COCO2017, which enables MLLMs to focus more on understanding images in the objective world. To ensure data quality, we design a well-tailored annota","authors_text":"Haiyun Jiang, Jingping Liu, Tong Ruan, Weiyan Zhang, Yan Zhou, Yinan Zou, Zhedong Cen, Ziyan Liu","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T07:37:34Z","title":"Can Multimodal Large Language Models Understand Spatial Relations?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19015","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":"sha256:7dd482929bfafa59aefea5f1a2b048ed8745c0bd9d844d09c77c119d1a80e34c","target":"record","created_at":"2026-07-05T11:50:37Z","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":"09fc2c5148a64301a62073ddf4b9d8d8f4b8b3821479a2ff17694caaa04ec215","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T07:37:34Z","title_canon_sha256":"59b7f0c6b95a96847797f7f27f053c1f359a018a3d661e00d9ed899ba6b65271"},"schema_version":"1.0","source":{"id":"2505.19015","kind":"arxiv","version":2}},"canonical_sha256":"1f3589ca20afefd71803e6e712194edaad32010a9ec723e8df94ca0c16967549","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f3589ca20afefd71803e6e712194edaad32010a9ec723e8df94ca0c16967549","first_computed_at":"2026-07-05T11:50:37.005219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:37.005219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e9lGz1H+Hu0LQTyCp4qHlEbCmLoGZjIVR7czSSiNo+628frPPcLN/6HU6wrFUyiVNCM00PzifWmW3y3kOD2aDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:37.005792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19015","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dd482929bfafa59aefea5f1a2b048ed8745c0bd9d844d09c77c119d1a80e34c","sha256:30a68e78867f03568f3895e0d39ba034e76f11b17615eab8bf5f608b7935da16"],"state_sha256":"4c91841a4d4ea0a6cb6da2a06d63854c08c168dbd2b79919208ce0aa23260750"}