{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4DUTBFXM2YSEJQSIIO7Y7BPDWP","short_pith_number":"pith:4DUTBFXM","schema_version":"1.0","canonical_sha256":"e0e93096ecd62444c24843bf8f85e3b3e503796fbfa657a2ab477fe2ec25f58d","source":{"kind":"arxiv","id":"2605.22570","version":1},"attestation_state":"computed","paper":{"title":"VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Eunbyung Park, Hogun Park, Jinho Park, Youbin Kim","submitted_at":"2026-05-21T14:48:35Z","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"},"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":"2605.22570","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T14:48:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9b36636d48e72d748376caf61d1d457897a239405cca33814747a9c1ff9ff0d7","abstract_canon_sha256":"f73834da3d647af69a32f90d816162b057320925944d4e647daf68dc96b0aed4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:58.087333Z","signature_b64":"NOZbj4rh+CaP1ovU4yin4HP7wfjZV4wYllfpHYgpBUUzGeP00pq6Mr5NDBEDWfDN2sOXadqdFUMQDPQKGHQbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0e93096ecd62444c24843bf8f85e3b3e503796fbfa657a2ab477fe2ec25f58d","last_reissued_at":"2026-05-22T01:04:58.086439Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:58.086439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Eunbyung Park, Hogun Park, Jinho Park, Youbin Kim","submitted_at":"2026-05-21T14:48:35Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22570","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/2605.22570/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":"2605.22570","created_at":"2026-05-22T01:04:58.086597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22570v1","created_at":"2026-05-22T01:04:58.086597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22570","created_at":"2026-05-22T01:04:58.086597+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DUTBFXM2YSE","created_at":"2026-05-22T01:04:58.086597+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DUTBFXM2YSEJQSI","created_at":"2026-05-22T01:04:58.086597+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DUTBFXM","created_at":"2026-05-22T01:04:58.086597+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/4DUTBFXM2YSEJQSIIO7Y7BPDWP","json":"https://pith.science/pith/4DUTBFXM2YSEJQSIIO7Y7BPDWP.json","graph_json":"https://pith.science/api/pith-number/4DUTBFXM2YSEJQSIIO7Y7BPDWP/graph.json","events_json":"https://pith.science/api/pith-number/4DUTBFXM2YSEJQSIIO7Y7BPDWP/events.json","paper":"https://pith.science/paper/4DUTBFXM"},"agent_actions":{"view_html":"https://pith.science/pith/4DUTBFXM2YSEJQSIIO7Y7BPDWP","download_json":"https://pith.science/pith/4DUTBFXM2YSEJQSIIO7Y7BPDWP.json","view_paper":"https://pith.science/paper/4DUTBFXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22570&json=true","fetch_graph":"https://pith.science/api/pith-number/4DUTBFXM2YSEJQSIIO7Y7BPDWP/graph.json","fetch_events":"https://pith.science/api/pith-number/4DUTBFXM2YSEJQSIIO7Y7BPDWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DUTBFXM2YSEJQSIIO7Y7BPDWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DUTBFXM2YSEJQSIIO7Y7BPDWP/action/storage_attestation","attest_author":"https://pith.science/pith/4DUTBFXM2YSEJQSIIO7Y7BPDWP/action/author_attestation","sign_citation":"https://pith.science/pith/4DUTBFXM2YSEJQSIIO7Y7BPDWP/action/citation_signature","submit_replication":"https://pith.science/pith/4DUTBFXM2YSEJQSIIO7Y7BPDWP/action/replication_record"}},"created_at":"2026-05-22T01:04:58.086597+00:00","updated_at":"2026-05-22T01:04:58.086597+00:00"}