{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3VDRO65GHSMFKOEJ4CG7NHO37B","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":"282786e288417fc5a4cbac735bcebe1074228664294d7b284505e2afda8dbc43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:59Z","title_canon_sha256":"d6bc9f0f4663acb17b23ba591dda3e51e8fcc90118f6899f27d930093717594e"},"schema_version":"1.0","source":{"id":"2501.01428","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01428","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01428v4","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01428","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"pith_short_12","alias_value":"3VDRO65GHSMF","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"pith_short_16","alias_value":"3VDRO65GHSMFKOEJ","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"pith_short_8","alias_value":"3VDRO65G","created_at":"2026-07-05T10:28:31Z"}],"graph_snapshots":[{"event_id":"sha256:15b68865c912dd881fc3618d435ab936b67f7518fc853628fa47f9dc4e261969","target":"graph","created_at":"2026-07-05T10:28:31Z","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/2501.01428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, 2D Vision-Language Models (VLMs) have made significant strides in image-text understanding tasks. However, their performance in 3D spatial comprehension, which is critical for embodied intelligence, remains limited. Recent advances have leveraged 3D point clouds and multi-view images as inputs, yielding promising results. However, we propose exploring a purely vision-based solution inspired by human perception, which merely relies on visual cues for 3D spatial understanding. This paper empirically investigates the limitations of VLMs in 3D spatial knowledge, revealing that the","authors_text":"Hengshuang Zhao, Jiaqi Wang, Ye Fang, Zhangyang Qi, Zhixiong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:59Z","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01428","kind":"arxiv","version":4},"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":"sha256:89f5bb73183f3cadd1e1bab5f71a98506307b5b94311122d53ef15f386cb18f8","target":"record","created_at":"2026-07-05T10:28:31Z","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":"282786e288417fc5a4cbac735bcebe1074228664294d7b284505e2afda8dbc43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T18:59:59Z","title_canon_sha256":"d6bc9f0f4663acb17b23ba591dda3e51e8fcc90118f6899f27d930093717594e"},"schema_version":"1.0","source":{"id":"2501.01428","kind":"arxiv","version":4}},"canonical_sha256":"dd47177ba63c98553889e08df69ddbf86e721acd4f2c0042145b08311d5d46a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd47177ba63c98553889e08df69ddbf86e721acd4f2c0042145b08311d5d46a2","first_computed_at":"2026-07-05T10:28:31.630273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:31.630273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wp6qhL3isppSDL4Ysh+bTu+g2tYhbmypLJzIqbFhsV84HDHdeCWyYoujGqUrFLTK/qaVRy8h2I40r7YatuDZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:31.631343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01428","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89f5bb73183f3cadd1e1bab5f71a98506307b5b94311122d53ef15f386cb18f8","sha256:15b68865c912dd881fc3618d435ab936b67f7518fc853628fa47f9dc4e261969"],"state_sha256":"f4177a530e8eb0a6e0a52d6a98c3f9413416dd190939316c97a8a0042be7bb28"}