{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FW46JWWGRADROCB6LGT5LAO7IZ","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":"a6c81b9d635f9feea01399682428324f65932aaf66b9ce2d73eef2a5bfc49c71","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T19:12:45Z","title_canon_sha256":"d621ad88966e4377eb2448aa0815d7cc024edc61d6fabaa9190fdf77739601bf"},"schema_version":"1.0","source":{"id":"2506.05523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05523","created_at":"2026-07-05T11:17:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05523v1","created_at":"2026-07-05T11:17:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05523","created_at":"2026-07-05T11:17:04Z"},{"alias_kind":"pith_short_12","alias_value":"FW46JWWGRADR","created_at":"2026-07-05T11:17:04Z"},{"alias_kind":"pith_short_16","alias_value":"FW46JWWGRADROCB6","created_at":"2026-07-05T11:17:04Z"},{"alias_kind":"pith_short_8","alias_value":"FW46JWWG","created_at":"2026-07-05T11:17:04Z"}],"graph_snapshots":[{"event_id":"sha256:8db8b012c1c45f54d452dcde72f3a726ea7cab42447778c70bf2eeebf1665c02","target":"graph","created_at":"2026-07-05T11:17:04Z","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/2506.05523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T19:12:45Z","title":"MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05523","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":"sha256:53384b60e778145f600f4c9a8764c94abde497bb12d6c2f15cddce4814db66c1","target":"record","created_at":"2026-07-05T11:17:04Z","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":"a6c81b9d635f9feea01399682428324f65932aaf66b9ce2d73eef2a5bfc49c71","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T19:12:45Z","title_canon_sha256":"d621ad88966e4377eb2448aa0815d7cc024edc61d6fabaa9190fdf77739601bf"},"schema_version":"1.0","source":{"id":"2506.05523","kind":"arxiv","version":1}},"canonical_sha256":"2db9e4dac6880717083e59a7d581df465e7f8b5c1bc1ddcbbbb335ad1947179e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2db9e4dac6880717083e59a7d581df465e7f8b5c1bc1ddcbbbb335ad1947179e","first_computed_at":"2026-07-05T11:17:04.981715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:04.981715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cPnETEvO5Z2ObFmB1/FyEEf/MJvxvXCT+BbNt3YcJs7yMnBnAGL7mGm18FPNUZUlBhK1lktVcYFJzMwqw8BRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:04.982288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53384b60e778145f600f4c9a8764c94abde497bb12d6c2f15cddce4814db66c1","sha256:8db8b012c1c45f54d452dcde72f3a726ea7cab42447778c70bf2eeebf1665c02"],"state_sha256":"c07c36a3bdffe2649d4ee7f6993ccdb1129ff0143d64b2b9aa4213dfdd0d01c5"}