{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4DUTBFXM2YSEJQSIIO7Y7BPDWP","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":"f73834da3d647af69a32f90d816162b057320925944d4e647daf68dc96b0aed4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T14:48:35Z","title_canon_sha256":"9b36636d48e72d748376caf61d1d457897a239405cca33814747a9c1ff9ff0d7"},"schema_version":"1.0","source":{"id":"2605.22570","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22570","created_at":"2026-05-22T01:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22570v1","created_at":"2026-05-22T01:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22570","created_at":"2026-05-22T01:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"4DUTBFXM2YSE","created_at":"2026-05-22T01:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"4DUTBFXM2YSEJQSI","created_at":"2026-05-22T01:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"4DUTBFXM","created_at":"2026-05-22T01:04:58Z"}],"graph_snapshots":[{"event_id":"sha256:fbe46c2635681d53ef5d36cbebf6de33eb0ab2ec6f9fe1f5a8f058ee4068c9dd","target":"graph","created_at":"2026-05-22T01:04:58Z","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/2605.22570/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatio-temporal reasoning is a core capability for Multimodal Large Language Models (MLLMs) operating in the real world. As such, evaluating it precisely has become an essential challenge. However, existing spatio-temporal reasoning benchmark datasets primarily rely on static image sets or passively curated video data, which limits the evaluation of fine-grained reasoning capabilities. In this paper, we introduce VGenST-Bench, a video benchmark that employs generative models to actively synthesize highly controlled and diverse evaluation scenarios. To construct VGenST-Bench, we propose a multi","authors_text":"Eunbyung Park, Hogun Park, Jinho Park, Youbin Kim","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T14:48:35Z","title":"VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22570","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:a4f286b851778f087e208fcaa3b53c7782d3775fbc631565d711a79655f4b2a7","target":"record","created_at":"2026-05-22T01:04:58Z","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":"f73834da3d647af69a32f90d816162b057320925944d4e647daf68dc96b0aed4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T14:48:35Z","title_canon_sha256":"9b36636d48e72d748376caf61d1d457897a239405cca33814747a9c1ff9ff0d7"},"schema_version":"1.0","source":{"id":"2605.22570","kind":"arxiv","version":1}},"canonical_sha256":"e0e93096ecd62444c24843bf8f85e3b3e503796fbfa657a2ab477fe2ec25f58d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0e93096ecd62444c24843bf8f85e3b3e503796fbfa657a2ab477fe2ec25f58d","first_computed_at":"2026-05-22T01:04:58.086439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:58.086439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NOZbj4rh+CaP1ovU4yin4HP7wfjZV4wYllfpHYgpBUUzGeP00pq6Mr5NDBEDWfDN2sOXadqdFUMQDPQKGHQbCQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:58.087333Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22570","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4f286b851778f087e208fcaa3b53c7782d3775fbc631565d711a79655f4b2a7","sha256:fbe46c2635681d53ef5d36cbebf6de33eb0ab2ec6f9fe1f5a8f058ee4068c9dd"],"state_sha256":"a70f8f85c80b0d6a191adba0ffd20fea480742831ed566d2b78faf1f719227a9"}