{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SJMAZRVGHUK44CPVKMEGT4QFDY","short_pith_number":"pith:SJMAZRVG","schema_version":"1.0","canonical_sha256":"92580cc6a63d15ce09f5530869f2051e16354d140a1655531f1e663f26bc29e6","source":{"kind":"arxiv","id":"2608.05747","version":1},"attestation_state":"computed","paper":{"title":"GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Dong, Huang Fang, Junjie Zhu, Junting Chen, Kaixiang Huang, Qifeng Zhang, Wei Li, Yonghang Chen, Zhiyu Zhang","submitted_at":"2026-08-06T08:33:13Z","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"},"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":"2608.05747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T08:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"398fa6faf840c5caea0fd948e514e3ed2b51bbff41ad52ffd201f3557935a558","abstract_canon_sha256":"529a454defb0e9f97d94f631f51dad4de00ad492317520958d726d9d31b70374"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:28.151781Z","signature_b64":"GNuTFt3aJqRRnqPFlMHGIisLVSIXWVr47ngWKtyFTU/WNmFw7HecMkD232cxMDDy24FO4YHrPiObh592tmwRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92580cc6a63d15ce09f5530869f2051e16354d140a1655531f1e663f26bc29e6","last_reissued_at":"2026-08-07T00:52:28.150411Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:28.150411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Dong, Huang Fang, Junjie Zhu, Junting Chen, Kaixiang Huang, Qifeng Zhang, Wei Li, Yonghang Chen, Zhiyu Zhang","submitted_at":"2026-08-06T08:33:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05747","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/2608.05747/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":"2608.05747","created_at":"2026-08-07T00:52:28.151924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05747v1","created_at":"2026-08-07T00:52:28.151924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05747","created_at":"2026-08-07T00:52:28.151924+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJMAZRVGHUK4","created_at":"2026-08-07T00:52:28.151924+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJMAZRVGHUK44CPV","created_at":"2026-08-07T00:52:28.151924+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJMAZRVG","created_at":"2026-08-07T00:52:28.151924+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/SJMAZRVGHUK44CPVKMEGT4QFDY","json":"https://pith.science/pith/SJMAZRVGHUK44CPVKMEGT4QFDY.json","graph_json":"https://pith.science/api/pith-number/SJMAZRVGHUK44CPVKMEGT4QFDY/graph.json","events_json":"https://pith.science/api/pith-number/SJMAZRVGHUK44CPVKMEGT4QFDY/events.json","paper":"https://pith.science/paper/SJMAZRVG"},"agent_actions":{"view_html":"https://pith.science/pith/SJMAZRVGHUK44CPVKMEGT4QFDY","download_json":"https://pith.science/pith/SJMAZRVGHUK44CPVKMEGT4QFDY.json","view_paper":"https://pith.science/paper/SJMAZRVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05747&json=true","fetch_graph":"https://pith.science/api/pith-number/SJMAZRVGHUK44CPVKMEGT4QFDY/graph.json","fetch_events":"https://pith.science/api/pith-number/SJMAZRVGHUK44CPVKMEGT4QFDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJMAZRVGHUK44CPVKMEGT4QFDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJMAZRVGHUK44CPVKMEGT4QFDY/action/storage_attestation","attest_author":"https://pith.science/pith/SJMAZRVGHUK44CPVKMEGT4QFDY/action/author_attestation","sign_citation":"https://pith.science/pith/SJMAZRVGHUK44CPVKMEGT4QFDY/action/citation_signature","submit_replication":"https://pith.science/pith/SJMAZRVGHUK44CPVKMEGT4QFDY/action/replication_record"}},"created_at":"2026-08-07T00:52:28.151924+00:00","updated_at":"2026-08-07T00:52:28.151924+00:00"}