{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ATTPJXZLQFGVIYMVRYJHYGWX2K","short_pith_number":"pith:ATTPJXZL","schema_version":"1.0","canonical_sha256":"04e6f4df2b814d5461958e127c1ad7d296278f1a00c43c68827035ead2676a10","source":{"kind":"arxiv","id":"2510.09606","version":2},"attestation_state":"computed","paper":{"title":"SpaceVista: All-Scale Visual Spatial Reasoning from mm to km","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongming Wu, Huadai Liu, Jianan Wang, Kaituo Feng, Peiwen Sun, Rui Liu, Shiqiang Lang, Xiangyu Yue, Yi Ding, Yun-hui Liu, Zhen Ye","submitted_at":"2025-10-10T17:59:46Z","abstract_excerpt":"With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to advance all-scale spatial reasoning across diverse scenarios by tackling two key challenges: 1) the heavy reliance on indoor 3D scans and labor-intensive manual annotations for dataset curation; 2) the absence of effective all-scale scene modeling, which often leads to overfitting to individual scenes. In this paper, we introduce a holistic solution that integ"},"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":"2510.09606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-10T17:59:46Z","cross_cats_sorted":[],"title_canon_sha256":"5faca01b83d2cf9a48bf7639d5640274ed4ab4161278f457513e3003fd68a437","abstract_canon_sha256":"fb4c1ec9987139194740f57a24a7d7ecf2e97f068c047d76cf7d0e53466c6ffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:38.715057Z","signature_b64":"AsZxOOK0JDAo0NTbyPImAVIKpiX/SqTw0j1RhqTjfAoFx1PRm6VsrfNbW8CfD3QuqbZGqgQRUHNEv3MSk3LkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04e6f4df2b814d5461958e127c1ad7d296278f1a00c43c68827035ead2676a10","last_reissued_at":"2026-05-27T01:05:38.714443Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:38.714443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpaceVista: All-Scale Visual Spatial Reasoning from mm to km","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongming Wu, Huadai Liu, Jianan Wang, Kaituo Feng, Peiwen Sun, Rui Liu, Shiqiang Lang, Xiangyu Yue, Yi Ding, Yun-hui Liu, Zhen Ye","submitted_at":"2025-10-10T17:59:46Z","abstract_excerpt":"With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to advance all-scale spatial reasoning across diverse scenarios by tackling two key challenges: 1) the heavy reliance on indoor 3D scans and labor-intensive manual annotations for dataset curation; 2) the absence of effective all-scale scene modeling, which often leads to overfitting to individual scenes. In this paper, we introduce a holistic solution that integ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09606","kind":"arxiv","version":2},"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/2510.09606/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":"2510.09606","created_at":"2026-05-27T01:05:38.714502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.09606v2","created_at":"2026-05-27T01:05:38.714502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09606","created_at":"2026-05-27T01:05:38.714502+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATTPJXZLQFGV","created_at":"2026-05-27T01:05:38.714502+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATTPJXZLQFGVIYMV","created_at":"2026-05-27T01:05:38.714502+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATTPJXZL","created_at":"2026-05-27T01:05:38.714502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2512.03043","citing_title":"OneThinker: All-in-one Reasoning Model for Image and Video","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2512.17012","citing_title":"4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2602.00181","citing_title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03318","citing_title":"EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02913","citing_title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","ref_index":107,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATTPJXZLQFGVIYMVRYJHYGWX2K","json":"https://pith.science/pith/ATTPJXZLQFGVIYMVRYJHYGWX2K.json","graph_json":"https://pith.science/api/pith-number/ATTPJXZLQFGVIYMVRYJHYGWX2K/graph.json","events_json":"https://pith.science/api/pith-number/ATTPJXZLQFGVIYMVRYJHYGWX2K/events.json","paper":"https://pith.science/paper/ATTPJXZL"},"agent_actions":{"view_html":"https://pith.science/pith/ATTPJXZLQFGVIYMVRYJHYGWX2K","download_json":"https://pith.science/pith/ATTPJXZLQFGVIYMVRYJHYGWX2K.json","view_paper":"https://pith.science/paper/ATTPJXZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.09606&json=true","fetch_graph":"https://pith.science/api/pith-number/ATTPJXZLQFGVIYMVRYJHYGWX2K/graph.json","fetch_events":"https://pith.science/api/pith-number/ATTPJXZLQFGVIYMVRYJHYGWX2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATTPJXZLQFGVIYMVRYJHYGWX2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATTPJXZLQFGVIYMVRYJHYGWX2K/action/storage_attestation","attest_author":"https://pith.science/pith/ATTPJXZLQFGVIYMVRYJHYGWX2K/action/author_attestation","sign_citation":"https://pith.science/pith/ATTPJXZLQFGVIYMVRYJHYGWX2K/action/citation_signature","submit_replication":"https://pith.science/pith/ATTPJXZLQFGVIYMVRYJHYGWX2K/action/replication_record"}},"created_at":"2026-05-27T01:05:38.714502+00:00","updated_at":"2026-05-27T01:05:38.714502+00:00"}