{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IEHJM7B3YDDMDOD3I2PXZHCG4R","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":"6a1db9ca4e0466e279828fa0f3226cd006910f38bdad00715e050ea917661823","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T07:13:17Z","title_canon_sha256":"32e857d56cb5db89fd04b4bbf8a2dbe234089b5c9b2b511795c43903db2f1ca5"},"schema_version":"1.0","source":{"id":"2412.18224","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18224","created_at":"2026-07-05T09:53:51Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18224v1","created_at":"2026-07-05T09:53:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18224","created_at":"2026-07-05T09:53:51Z"},{"alias_kind":"pith_short_12","alias_value":"IEHJM7B3YDDM","created_at":"2026-07-05T09:53:51Z"},{"alias_kind":"pith_short_16","alias_value":"IEHJM7B3YDDMDOD3","created_at":"2026-07-05T09:53:51Z"},{"alias_kind":"pith_short_8","alias_value":"IEHJM7B3","created_at":"2026-07-05T09:53:51Z"}],"graph_snapshots":[{"event_id":"sha256:24f2658449113ed689a5a63719698f6291ce13f7c4a9b1e3da74f28200812393","target":"graph","created_at":"2026-07-05T09:53:51Z","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/2412.18224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distinguishing spatial relations is a basic part of human cognition which requires fine-grained perception on cross-instance. Although benchmarks like MME, MMBench and SEED comprehensively have evaluated various capabilities which already include visual spatial reasoning(VSR). There is still a lack of sufficient quantity and quality evaluation and optimization datasets for Vision Large Language Models(VLLMs) specifically targeting visual positional reasoning. To handle this, we first diagnosed current VLLMs with the VSR dataset and proposed a unified test set. We found current VLLMs to exhibit","authors_text":"Bingquan Liu, Chengjie Sun, Dexin Wang, Jiajia Zhang, Lin Sun, Peijin Xie, Xiangzheng Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T07:13:17Z","title":"Expand VSR Benchmark for VLLM to Expertize in Spatial Rules"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18224","kind":"arxiv","version":1},"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:ef046d8e2d4608d35324e6430767a7f73267a6a378afabaab964c47171022282","target":"record","created_at":"2026-07-05T09:53:51Z","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":"6a1db9ca4e0466e279828fa0f3226cd006910f38bdad00715e050ea917661823","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T07:13:17Z","title_canon_sha256":"32e857d56cb5db89fd04b4bbf8a2dbe234089b5c9b2b511795c43903db2f1ca5"},"schema_version":"1.0","source":{"id":"2412.18224","kind":"arxiv","version":1}},"canonical_sha256":"410e967c3bc0c6c1b87b469f7c9c46e4564e86554d9a39e4818a57c6a1b2d015","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"410e967c3bc0c6c1b87b469f7c9c46e4564e86554d9a39e4818a57c6a1b2d015","first_computed_at":"2026-07-05T09:53:51.901609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:51.901609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DtYYc96k0FLsfs6FvobVuR7izC3D38cHLsSGIgC00N1XLpnPkTTcyif6eJt54vksRMjOUDIv27DOeuJRJ7TWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:51.902102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18224","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef046d8e2d4608d35324e6430767a7f73267a6a378afabaab964c47171022282","sha256:24f2658449113ed689a5a63719698f6291ce13f7c4a9b1e3da74f28200812393"],"state_sha256":"ae44e70596f8537672043a15c666fa0c9cd3adcc1ae98ab1caf0634d2998fadd"}