{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SJMAZRVGHUK44CPVKMEGT4QFDY","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":"529a454defb0e9f97d94f631f51dad4de00ad492317520958d726d9d31b70374","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T08:33:13Z","title_canon_sha256":"398fa6faf840c5caea0fd948e514e3ed2b51bbff41ad52ffd201f3557935a558"},"schema_version":"1.0","source":{"id":"2608.05747","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05747","created_at":"2026-08-07T00:52:28Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05747v1","created_at":"2026-08-07T00:52:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05747","created_at":"2026-08-07T00:52:28Z"},{"alias_kind":"pith_short_12","alias_value":"SJMAZRVGHUK4","created_at":"2026-08-07T00:52:28Z"},{"alias_kind":"pith_short_16","alias_value":"SJMAZRVGHUK44CPV","created_at":"2026-08-07T00:52:28Z"},{"alias_kind":"pith_short_8","alias_value":"SJMAZRVG","created_at":"2026-08-07T00:52:28Z"}],"graph_snapshots":[{"event_id":"sha256:0a3e4fee640e98ff7540fd2b8a518868e986697b67c2447494cb13f81c3d5a29","target":"graph","created_at":"2026-08-07T00:52:28Z","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/2608.05747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or few viewpoints, overlooking global spatial awareness over continuous, long-horizon visual streams. To address this limitation, we introduce the Global-Spatial-Temporal Benchmark (GST-Bench), a VQA benchmark for global spatial intelligence in video understanding, comprising human-verified questions derived from 6,790 minutes of synthetically generated video. It requires models to perform accurate spatial inference from novel viewpoints unseen in the input video and to","authors_text":"Heng Dong, Huang Fang, Junjie Zhu, Junting Chen, Kaixiang Huang, Qifeng Zhang, Wei Li, Yonghang Chen, Zhiyu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T08:33:13Z","title":"GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05747","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":"sha256:52e8c40d6ed3b5574874a2b1cbf27896f2c06e0b3b0803b970300890c1130168","target":"record","created_at":"2026-08-07T00:52:28Z","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":"529a454defb0e9f97d94f631f51dad4de00ad492317520958d726d9d31b70374","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T08:33:13Z","title_canon_sha256":"398fa6faf840c5caea0fd948e514e3ed2b51bbff41ad52ffd201f3557935a558"},"schema_version":"1.0","source":{"id":"2608.05747","kind":"arxiv","version":1}},"canonical_sha256":"92580cc6a63d15ce09f5530869f2051e16354d140a1655531f1e663f26bc29e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92580cc6a63d15ce09f5530869f2051e16354d140a1655531f1e663f26bc29e6","first_computed_at":"2026-08-07T00:52:28.150411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:52:28.150411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GNuTFt3aJqRRnqPFlMHGIisLVSIXWVr47ngWKtyFTU/WNmFw7HecMkD232cxMDDy24FO4YHrPiObh592tmwRAA==","signature_status":"signed_v1","signed_at":"2026-08-07T00:52:28.151781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05747","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52e8c40d6ed3b5574874a2b1cbf27896f2c06e0b3b0803b970300890c1130168","sha256:0a3e4fee640e98ff7540fd2b8a518868e986697b67c2447494cb13f81c3d5a29"],"state_sha256":"e9ef67a34cebec46a3f0ec1d6b7196e25050e2e6e9635e73259e7a32bc234974"}