{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MAE7GM5SCWK4SPNFZWEBW3XIOR","short_pith_number":"pith:MAE7GM5S","schema_version":"1.0","canonical_sha256":"6009f333b21595c93da5cd881b6ee874512af6404779bb2e79d1de8670f24af3","source":{"kind":"arxiv","id":"2410.06555","version":1},"attestation_state":"computed","paper":{"title":"ING-VP: MLLMs cannot Play Easy Vision-based Games Yet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ge Zhang, Hangyu Guo, Haoran Zhang, Jiaheng Liu, Meng Cao, Shuyue Guo, Wenhao Huang","submitted_at":"2024-10-09T05:17:38Z","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"},"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":"2410.06555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T05:17:38Z","cross_cats_sorted":[],"title_canon_sha256":"bfecb1d8b2dfa2c7c385073ba4767ede419426c2e89669be9431428e1d87214d","abstract_canon_sha256":"580e1a1a32c6d49fe9ec4a1029f0e4c493db3c583b9f25df91226814fc502a29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:04.003707Z","signature_b64":"CxyFY+f2w5riUhS7ehzd5WK0A+xkXf3Zktaswh6Y58P8RFnoWT+QHhVJ3d4Anb2tGQQuikGTTQtw6j4T0z/DBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6009f333b21595c93da5cd881b6ee874512af6404779bb2e79d1de8670f24af3","last_reissued_at":"2026-07-05T09:18:04.003294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:04.003294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ING-VP: MLLMs cannot Play Easy Vision-based Games Yet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ge Zhang, Hangyu Guo, Haoran Zhang, Jiaheng Liu, Meng Cao, Shuyue Guo, Wenhao Huang","submitted_at":"2024-10-09T05:17:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06555","kind":"arxiv","version":1},"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/2410.06555/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":"2410.06555","created_at":"2026-07-05T09:18:04.003361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06555v1","created_at":"2026-07-05T09:18:04.003361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06555","created_at":"2026-07-05T09:18:04.003361+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAE7GM5SCWK4","created_at":"2026-07-05T09:18:04.003361+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAE7GM5SCWK4SPNF","created_at":"2026-07-05T09:18:04.003361+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAE7GM5S","created_at":"2026-07-05T09:18:04.003361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03644","citing_title":"Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details","ref_index":267,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MAE7GM5SCWK4SPNFZWEBW3XIOR","json":"https://pith.science/pith/MAE7GM5SCWK4SPNFZWEBW3XIOR.json","graph_json":"https://pith.science/api/pith-number/MAE7GM5SCWK4SPNFZWEBW3XIOR/graph.json","events_json":"https://pith.science/api/pith-number/MAE7GM5SCWK4SPNFZWEBW3XIOR/events.json","paper":"https://pith.science/paper/MAE7GM5S"},"agent_actions":{"view_html":"https://pith.science/pith/MAE7GM5SCWK4SPNFZWEBW3XIOR","download_json":"https://pith.science/pith/MAE7GM5SCWK4SPNFZWEBW3XIOR.json","view_paper":"https://pith.science/paper/MAE7GM5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06555&json=true","fetch_graph":"https://pith.science/api/pith-number/MAE7GM5SCWK4SPNFZWEBW3XIOR/graph.json","fetch_events":"https://pith.science/api/pith-number/MAE7GM5SCWK4SPNFZWEBW3XIOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAE7GM5SCWK4SPNFZWEBW3XIOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAE7GM5SCWK4SPNFZWEBW3XIOR/action/storage_attestation","attest_author":"https://pith.science/pith/MAE7GM5SCWK4SPNFZWEBW3XIOR/action/author_attestation","sign_citation":"https://pith.science/pith/MAE7GM5SCWK4SPNFZWEBW3XIOR/action/citation_signature","submit_replication":"https://pith.science/pith/MAE7GM5SCWK4SPNFZWEBW3XIOR/action/replication_record"}},"created_at":"2026-07-05T09:18:04.003361+00:00","updated_at":"2026-07-05T09:18:04.003361+00:00"}