{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OWZ6MIWJDWB3KJ3DP6F6P3KCJ5","short_pith_number":"pith:OWZ6MIWJ","schema_version":"1.0","canonical_sha256":"75b3e622c91d83b527637f8be7ed424f4bdf9d903bd38134aff2bf403762a8f7","source":{"kind":"arxiv","id":"2607.01784","version":1},"attestation_state":"computed","paper":{"title":"SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Qianlong Xiang, Weili Guan, Yaowei Wang","submitted_at":"2026-07-02T06:56:29Z","abstract_excerpt":"Visual-spatial understanding, defined as the ability to infer object relationships and scene layouts from visual inputs, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, pre-trained vision-language models (VLMs) remain constrained by spatial uncertainty stemming from inherently 2D observations and by the scarcity of data for 3D spatial understanding. To address these limitations, we proposed a novel framework, SpaceEra, in the NeurIPS 2025 Spotlight paper. Although it achieved significant performance gains, we further observed that its effectiven"},"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":"2607.01784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T06:56:29Z","cross_cats_sorted":[],"title_canon_sha256":"14b4cb6ea91f29d970889493467551cec3ffbff4bc72dc3c3bca93283f38c6b3","abstract_canon_sha256":"ca2c3624878a2ff4f3c849a354fa58a46d4e7595ab51a4e654e4582e812ab55c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:29.696173Z","signature_b64":"+s6mO2glb8vpZ9eMBEvzcLyLNoySr56HrM0qVysm0/DbBLLLslw/qbPJ9obmLxp4JxJKMv5NdQ7fcCHg40YKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75b3e622c91d83b527637f8be7ed424f4bdf9d903bd38134aff2bf403762a8f7","last_reissued_at":"2026-07-03T01:17:29.695739Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:29.695739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Qianlong Xiang, Weili Guan, Yaowei Wang","submitted_at":"2026-07-02T06:56:29Z","abstract_excerpt":"Visual-spatial understanding, defined as the ability to infer object relationships and scene layouts from visual inputs, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, pre-trained vision-language models (VLMs) remain constrained by spatial uncertainty stemming from inherently 2D observations and by the scarcity of data for 3D spatial understanding. To address these limitations, we proposed a novel framework, SpaceEra, in the NeurIPS 2025 Spotlight paper. Although it achieved significant performance gains, we further observed that its effectiven"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01784","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/2607.01784/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":"2607.01784","created_at":"2026-07-03T01:17:29.695806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01784v1","created_at":"2026-07-03T01:17:29.695806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01784","created_at":"2026-07-03T01:17:29.695806+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWZ6MIWJDWB3","created_at":"2026-07-03T01:17:29.695806+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWZ6MIWJDWB3KJ3D","created_at":"2026-07-03T01:17:29.695806+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWZ6MIWJ","created_at":"2026-07-03T01:17:29.695806+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/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5","json":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5.json","graph_json":"https://pith.science/api/pith-number/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/graph.json","events_json":"https://pith.science/api/pith-number/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/events.json","paper":"https://pith.science/paper/OWZ6MIWJ"},"agent_actions":{"view_html":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5","download_json":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5.json","view_paper":"https://pith.science/paper/OWZ6MIWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01784&json=true","fetch_graph":"https://pith.science/api/pith-number/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/action/storage_attestation","attest_author":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/action/author_attestation","sign_citation":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/action/citation_signature","submit_replication":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/action/replication_record"}},"created_at":"2026-07-03T01:17:29.695806+00:00","updated_at":"2026-07-03T01:17:29.695806+00:00"}