{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FW46JWWGRADROCB6LGT5LAO7IZ","short_pith_number":"pith:FW46JWWG","schema_version":"1.0","canonical_sha256":"2db9e4dac6880717083e59a7d581df465e7f8b5c1bc1ddcbbbb335ad1947179e","source":{"kind":"arxiv","id":"2506.05523","version":1},"attestation_state":"computed","paper":{"title":"MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Wang, Anirudh Satheesh, Ankit Nakhawa, Furong Huang, Hyunwoo Jae, Keenan Powell, Minghui Liu, Neel Jay, Sungbin Oh, Tom Goldstein, Xiyao Wang, Yongyuan Liang, Zikui Cai","submitted_at":"2025-06-05T19:12:45Z","abstract_excerpt":"Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static images, failing to capture the temporal complexity of real-world environments. Second, they narrowly focus on mathematical problem-solving, neglecting the broader spectrum of reasoning skills -- including abstract, physical, planning, spatial, and temporal capabilities -- required for robust multimodal intelligence. Third, many benchmarks quickly saturate, offering limited headroom for diagnosing failure modes or meas"},"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":"2506.05523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T19:12:45Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"d621ad88966e4377eb2448aa0815d7cc024edc61d6fabaa9190fdf77739601bf","abstract_canon_sha256":"a6c81b9d635f9feea01399682428324f65932aaf66b9ce2d73eef2a5bfc49c71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:04.982288Z","signature_b64":"cPnETEvO5Z2ObFmB1/FyEEf/MJvxvXCT+BbNt3YcJs7yMnBnAGL7mGm18FPNUZUlBhK1lktVcYFJzMwqw8BRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2db9e4dac6880717083e59a7d581df465e7f8b5c1bc1ddcbbbb335ad1947179e","last_reissued_at":"2026-07-05T11:17:04.981715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:04.981715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Wang, Anirudh Satheesh, Ankit Nakhawa, Furong Huang, Hyunwoo Jae, Keenan Powell, Minghui Liu, Neel Jay, Sungbin Oh, Tom Goldstein, Xiyao Wang, Yongyuan Liang, Zikui Cai","submitted_at":"2025-06-05T19:12:45Z","abstract_excerpt":"Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static images, failing to capture the temporal complexity of real-world environments. Second, they narrowly focus on mathematical problem-solving, neglecting the broader spectrum of reasoning skills -- including abstract, physical, planning, spatial, and temporal capabilities -- required for robust multimodal intelligence. Third, many benchmarks quickly saturate, offering limited headroom for diagnosing failure modes or meas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05523","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/2506.05523/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":"2506.05523","created_at":"2026-07-05T11:17:04.981802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05523v1","created_at":"2026-07-05T11:17:04.981802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05523","created_at":"2026-07-05T11:17:04.981802+00:00"},{"alias_kind":"pith_short_12","alias_value":"FW46JWWGRADR","created_at":"2026-07-05T11:17:04.981802+00:00"},{"alias_kind":"pith_short_16","alias_value":"FW46JWWGRADROCB6","created_at":"2026-07-05T11:17:04.981802+00:00"},{"alias_kind":"pith_short_8","alias_value":"FW46JWWG","created_at":"2026-07-05T11:17:04.981802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00248","citing_title":"Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00148","citing_title":"StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10941","citing_title":"Mull-Tokens: Modality-Agnostic Latent Thinking","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12703","citing_title":"MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FW46JWWGRADROCB6LGT5LAO7IZ","json":"https://pith.science/pith/FW46JWWGRADROCB6LGT5LAO7IZ.json","graph_json":"https://pith.science/api/pith-number/FW46JWWGRADROCB6LGT5LAO7IZ/graph.json","events_json":"https://pith.science/api/pith-number/FW46JWWGRADROCB6LGT5LAO7IZ/events.json","paper":"https://pith.science/paper/FW46JWWG"},"agent_actions":{"view_html":"https://pith.science/pith/FW46JWWGRADROCB6LGT5LAO7IZ","download_json":"https://pith.science/pith/FW46JWWGRADROCB6LGT5LAO7IZ.json","view_paper":"https://pith.science/paper/FW46JWWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05523&json=true","fetch_graph":"https://pith.science/api/pith-number/FW46JWWGRADROCB6LGT5LAO7IZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FW46JWWGRADROCB6LGT5LAO7IZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FW46JWWGRADROCB6LGT5LAO7IZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FW46JWWGRADROCB6LGT5LAO7IZ/action/storage_attestation","attest_author":"https://pith.science/pith/FW46JWWGRADROCB6LGT5LAO7IZ/action/author_attestation","sign_citation":"https://pith.science/pith/FW46JWWGRADROCB6LGT5LAO7IZ/action/citation_signature","submit_replication":"https://pith.science/pith/FW46JWWGRADROCB6LGT5LAO7IZ/action/replication_record"}},"created_at":"2026-07-05T11:17:04.981802+00:00","updated_at":"2026-07-05T11:17:04.981802+00:00"}