{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3QP63GBA6B5R3TX2BIO4SB3AH6","short_pith_number":"pith:3QP63GBA","schema_version":"1.0","canonical_sha256":"dc1fed9820f07b1dcefa0a1dc907603fb61ebca57a1f44d0d00a1e945b2543ec","source":{"kind":"arxiv","id":"2606.06538","version":1},"attestation_state":"computed","paper":{"title":"WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksandra Korolova, Boya Zeng, Chung Peng Lee, Gabriel Sarch, Harish Krishnakumar, Hu Xu, Shengbang Tong, Wenhao Chai, Wenhu Chen, Xingyu Fu, Yida Yin, Zhuang Liu","submitted_at":"2026-06-04T01:11:21Z","abstract_excerpt":"In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types without capturing the visual diversity needed to handle open-ended visual inputs. We present WorldBench, a challenging and visually diverse reasoning benchmark to evaluate Multimodal Large Language Models (MLLMs). We build a taxonomy of thousands of visual concepts across multiple domains (e.g., living things). Guided by this taxonomy, we curate a broad collection of images from search engines and existing datasets to comprehensively represent "},"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":"2606.06538","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T01:11:21Z","cross_cats_sorted":[],"title_canon_sha256":"04942ebe2309323f566c97e9c70a913a83edd81fdcde22b166ae483b9a592874","abstract_canon_sha256":"9ff1355e3e3601bcb271619e92083a4d5ec5dd8542e9f3407b40c5bc8aa1532b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T00:03:41.596110Z","signature_b64":"kDjVk4jHtlk0jnP5jjUkC8P4sOLFmfT/0Do3o7n0Mh5K60ep1RBGWyJjMpZGb4hnOO66od2aLop92QPhhaluBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc1fed9820f07b1dcefa0a1dc907603fb61ebca57a1f44d0d00a1e945b2543ec","last_reissued_at":"2026-06-08T00:03:41.595363Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T00:03:41.595363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksandra Korolova, Boya Zeng, Chung Peng Lee, Gabriel Sarch, Harish Krishnakumar, Hu Xu, Shengbang Tong, Wenhao Chai, Wenhu Chen, Xingyu Fu, Yida Yin, Zhuang Liu","submitted_at":"2026-06-04T01:11:21Z","abstract_excerpt":"In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types without capturing the visual diversity needed to handle open-ended visual inputs. We present WorldBench, a challenging and visually diverse reasoning benchmark to evaluate Multimodal Large Language Models (MLLMs). We build a taxonomy of thousands of visual concepts across multiple domains (e.g., living things). Guided by this taxonomy, we curate a broad collection of images from search engines and existing datasets to comprehensively represent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06538","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/2606.06538/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":"2606.06538","created_at":"2026-06-08T00:03:41.595469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06538v1","created_at":"2026-06-08T00:03:41.595469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06538","created_at":"2026-06-08T00:03:41.595469+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QP63GBA6B5R","created_at":"2026-06-08T00:03:41.595469+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QP63GBA6B5R3TX2","created_at":"2026-06-08T00:03:41.595469+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QP63GBA","created_at":"2026-06-08T00:03:41.595469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QP63GBA6B5R3TX2BIO4SB3AH6","json":"https://pith.science/pith/3QP63GBA6B5R3TX2BIO4SB3AH6.json","graph_json":"https://pith.science/api/pith-number/3QP63GBA6B5R3TX2BIO4SB3AH6/graph.json","events_json":"https://pith.science/api/pith-number/3QP63GBA6B5R3TX2BIO4SB3AH6/events.json","paper":"https://pith.science/paper/3QP63GBA"},"agent_actions":{"view_html":"https://pith.science/pith/3QP63GBA6B5R3TX2BIO4SB3AH6","download_json":"https://pith.science/pith/3QP63GBA6B5R3TX2BIO4SB3AH6.json","view_paper":"https://pith.science/paper/3QP63GBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06538&json=true","fetch_graph":"https://pith.science/api/pith-number/3QP63GBA6B5R3TX2BIO4SB3AH6/graph.json","fetch_events":"https://pith.science/api/pith-number/3QP63GBA6B5R3TX2BIO4SB3AH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QP63GBA6B5R3TX2BIO4SB3AH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QP63GBA6B5R3TX2BIO4SB3AH6/action/storage_attestation","attest_author":"https://pith.science/pith/3QP63GBA6B5R3TX2BIO4SB3AH6/action/author_attestation","sign_citation":"https://pith.science/pith/3QP63GBA6B5R3TX2BIO4SB3AH6/action/citation_signature","submit_replication":"https://pith.science/pith/3QP63GBA6B5R3TX2BIO4SB3AH6/action/replication_record"}},"created_at":"2026-06-08T00:03:41.595469+00:00","updated_at":"2026-06-08T00:03:41.595469+00:00"}