{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SQOPUHA7C3PYJTSEKDRVRLCXZV","short_pith_number":"pith:SQOPUHA7","schema_version":"1.0","canonical_sha256":"941cfa1c1f16df84ce4450e358ac57cd6f0c3fb7a25dac09cbe4d48fffdd4c02","source":{"kind":"arxiv","id":"2607.17599","version":1},"attestation_state":"computed","paper":{"title":"ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tang, Jian Yang, Ting Huang, Wenyuan Huang, Zhenyu Zhang","submitted_at":"2026-07-20T06:40:45Z","abstract_excerpt":"Video spatial reasoning is essential for navigation-oriented perception and long-video question answering, where models must infer spatial relations across long horizons under changing viewpoints. However, existing multimodal large language models (MLLMs) remain largely semantic-centric, and often fail to reliably aggregate consistent spatial evidence from redundant video observations, leading to inefficient or unstable reasoning. To address these issues, we propose ConsiSpace, a geometry-consistency-aware framework for geometry-sensitive video spatial reasoning that turns spatial consistency "},"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":"2607.17599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:40:45Z","cross_cats_sorted":[],"title_canon_sha256":"5ef332a180404eea2a8f618345e670f7b3c238511e021b98c01c93bd0334f131","abstract_canon_sha256":"c47f118061ec6ba66e4e39aa78c3aabe1f9d392e3175f0646b06fe6baff34a0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:54.461622Z","signature_b64":"TW2NYkbctcL/nsnQlEv3KRR0fZSGh+McqqwR0tWuK4bh54oVwPVhBPSj8jYMXM4h9NLUkFf0RbmGjEGsja/IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"941cfa1c1f16df84ce4450e358ac57cd6f0c3fb7a25dac09cbe4d48fffdd4c02","last_reissued_at":"2026-07-21T01:21:54.460750Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:54.460750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tang, Jian Yang, Ting Huang, Wenyuan Huang, Zhenyu Zhang","submitted_at":"2026-07-20T06:40:45Z","abstract_excerpt":"Video spatial reasoning is essential for navigation-oriented perception and long-video question answering, where models must infer spatial relations across long horizons under changing viewpoints. However, existing multimodal large language models (MLLMs) remain largely semantic-centric, and often fail to reliably aggregate consistent spatial evidence from redundant video observations, leading to inefficient or unstable reasoning. To address these issues, we propose ConsiSpace, a geometry-consistency-aware framework for geometry-sensitive video spatial reasoning that turns spatial consistency "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17599","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/2607.17599/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":"2607.17599","created_at":"2026-07-21T01:21:54.461203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17599v1","created_at":"2026-07-21T01:21:54.461203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17599","created_at":"2026-07-21T01:21:54.461203+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQOPUHA7C3PY","created_at":"2026-07-21T01:21:54.461203+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQOPUHA7C3PYJTSE","created_at":"2026-07-21T01:21:54.461203+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQOPUHA7","created_at":"2026-07-21T01:21:54.461203+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/SQOPUHA7C3PYJTSEKDRVRLCXZV","json":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV.json","graph_json":"https://pith.science/api/pith-number/SQOPUHA7C3PYJTSEKDRVRLCXZV/graph.json","events_json":"https://pith.science/api/pith-number/SQOPUHA7C3PYJTSEKDRVRLCXZV/events.json","paper":"https://pith.science/paper/SQOPUHA7"},"agent_actions":{"view_html":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV","download_json":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV.json","view_paper":"https://pith.science/paper/SQOPUHA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17599&json=true","fetch_graph":"https://pith.science/api/pith-number/SQOPUHA7C3PYJTSEKDRVRLCXZV/graph.json","fetch_events":"https://pith.science/api/pith-number/SQOPUHA7C3PYJTSEKDRVRLCXZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/action/storage_attestation","attest_author":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/action/author_attestation","sign_citation":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/action/citation_signature","submit_replication":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/action/replication_record"}},"created_at":"2026-07-21T01:21:54.461203+00:00","updated_at":"2026-07-21T01:21:54.461203+00:00"}