{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ","short_pith_number":"pith:7OHBPFXN","schema_version":"1.0","canonical_sha256":"fb8e1796ed31f030e74154a474f729441befea1d758425204535d13490045969","source":{"kind":"arxiv","id":"2506.22992","version":1},"attestation_state":"computed","paper":{"title":"MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Maria Brbi\\'c, Michael Moor, Yekun Chai, Yulun Jiang","submitted_at":"2025-06-28T19:44:32Z","abstract_excerpt":"The ability to process information from multiple modalities and to reason through it step-by-step remains a critical challenge in advancing artificial intelligence. However, existing reasoning benchmarks focus on text-only reasoning, or employ multimodal questions that can be answered by directly retrieving information from a non-text modality. Thus, complex reasoning remains poorly understood in multimodal domains. Here, we present MARBLE, a challenging multimodal reasoning benchmark that is designed to scrutinize multimodal language models (MLLMs) in their ability to carefully reason step-by"},"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":"2506.22992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-28T19:44:32Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"2771c4b025ec2d5a2eee375b68b9784c5c36f1227993b28f66d8cad904fdb283","abstract_canon_sha256":"2b6de307da51b3ff7312c3ea26214bbed2a5c69f44c5e4c7c6a4ddb97da651cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:48.900391Z","signature_b64":"9zrLcyxeHWuijjeOZBUjG3Z8GXaRYy2XJC3qWkbMvrZduWEmg6AMeCRsm2S9eAs6bhcH27X6wLiFjgZjvJYzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb8e1796ed31f030e74154a474f729441befea1d758425204535d13490045969","last_reissued_at":"2026-07-05T11:28:48.899896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:48.899896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Maria Brbi\\'c, Michael Moor, Yekun Chai, Yulun Jiang","submitted_at":"2025-06-28T19:44:32Z","abstract_excerpt":"The ability to process information from multiple modalities and to reason through it step-by-step remains a critical challenge in advancing artificial intelligence. However, existing reasoning benchmarks focus on text-only reasoning, or employ multimodal questions that can be answered by directly retrieving information from a non-text modality. Thus, complex reasoning remains poorly understood in multimodal domains. Here, we present MARBLE, a challenging multimodal reasoning benchmark that is designed to scrutinize multimodal language models (MLLMs) in their ability to carefully reason step-by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22992","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/2506.22992/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":"2506.22992","created_at":"2026-07-05T11:28:48.899954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22992v1","created_at":"2026-07-05T11:28:48.899954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22992","created_at":"2026-07-05T11:28:48.899954+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OHBPFXNGHYD","created_at":"2026-07-05T11:28:48.899954+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OHBPFXNGHYDBZ2B","created_at":"2026-07-05T11:28:48.899954+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OHBPFXN","created_at":"2026-07-05T11:28:48.899954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11918","citing_title":"The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11445","citing_title":"Forecasting Future Behavior as a Learning Task","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ","json":"https://pith.science/pith/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ.json","graph_json":"https://pith.science/api/pith-number/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ/graph.json","events_json":"https://pith.science/api/pith-number/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ/events.json","paper":"https://pith.science/paper/7OHBPFXN"},"agent_actions":{"view_html":"https://pith.science/pith/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ","download_json":"https://pith.science/pith/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ.json","view_paper":"https://pith.science/paper/7OHBPFXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22992&json=true","fetch_graph":"https://pith.science/api/pith-number/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ/action/storage_attestation","attest_author":"https://pith.science/pith/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ/action/author_attestation","sign_citation":"https://pith.science/pith/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ/action/citation_signature","submit_replication":"https://pith.science/pith/7OHBPFXNGHYDBZ2BKSSHJ5ZJIQ/action/replication_record"}},"created_at":"2026-07-05T11:28:48.899954+00:00","updated_at":"2026-07-05T11:28:48.899954+00:00"}