{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MAE7GM5SCWK4SPNFZWEBW3XIOR","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":"580e1a1a32c6d49fe9ec4a1029f0e4c493db3c583b9f25df91226814fc502a29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T05:17:38Z","title_canon_sha256":"bfecb1d8b2dfa2c7c385073ba4767ede419426c2e89669be9431428e1d87214d"},"schema_version":"1.0","source":{"id":"2410.06555","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06555","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06555v1","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06555","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"MAE7GM5SCWK4","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"MAE7GM5SCWK4SPNF","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"MAE7GM5S","created_at":"2026-07-05T09:18:04Z"}],"graph_snapshots":[{"event_id":"sha256:7d7fceb082bcaee4b9c95205eea4496627672374cac956efcc45ae5b4450bbad","target":"graph","created_at":"2026-07-05T09:18:04Z","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/2410.06555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As multimodal large language models (MLLMs) continue to demonstrate increasingly competitive performance across a broad spectrum of tasks, more intricate and comprehensive benchmarks have been developed to assess these cutting-edge models. These benchmarks introduce new challenges to core capabilities such as perception, reasoning, and planning. However, existing multimodal benchmarks fall short in providing a focused evaluation of multi-step planning based on spatial relationships in images. To bridge this gap, we present ING-VP, the first INteractive Game-based Vision Planning benchmark, spe","authors_text":"Ge Zhang, Hangyu Guo, Haoran Zhang, Jiaheng Liu, Meng Cao, Shuyue Guo, Wenhao Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T05:17:38Z","title":"ING-VP: MLLMs cannot Play Easy Vision-based Games Yet"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06555","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":"sha256:25d5efd16307cb7fddbd01e1486012a01381a85e808ed3331ac23aa4f1fb50ed","target":"record","created_at":"2026-07-05T09:18:04Z","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":"580e1a1a32c6d49fe9ec4a1029f0e4c493db3c583b9f25df91226814fc502a29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T05:17:38Z","title_canon_sha256":"bfecb1d8b2dfa2c7c385073ba4767ede419426c2e89669be9431428e1d87214d"},"schema_version":"1.0","source":{"id":"2410.06555","kind":"arxiv","version":1}},"canonical_sha256":"6009f333b21595c93da5cd881b6ee874512af6404779bb2e79d1de8670f24af3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6009f333b21595c93da5cd881b6ee874512af6404779bb2e79d1de8670f24af3","first_computed_at":"2026-07-05T09:18:04.003294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:04.003294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CxyFY+f2w5riUhS7ehzd5WK0A+xkXf3Zktaswh6Y58P8RFnoWT+QHhVJ3d4Anb2tGQQuikGTTQtw6j4T0z/DBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:04.003707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06555","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25d5efd16307cb7fddbd01e1486012a01381a85e808ed3331ac23aa4f1fb50ed","sha256:7d7fceb082bcaee4b9c95205eea4496627672374cac956efcc45ae5b4450bbad"],"state_sha256":"e99bb6d4d4e26f60fd74a2d61db428b769e66fb4daa76ea2761318eacf9c504c"}