{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WORIUDFKTTQZZRH5NXNTGMOEBZ","short_pith_number":"pith:WORIUDFK","schema_version":"1.0","canonical_sha256":"b3a28a0caa9ce19cc4fd6ddb3331c40e7d7cd56570410c002420ce46bb5a6d00","source":{"kind":"arxiv","id":"2602.21186","version":2},"attestation_state":"computed","paper":{"title":"Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyi Jiang, Liu Liu, Wei Sui, Wenyu Liu, Xinggang Wang, Xinjie Wang, Yonghao He, Zhizhong Su","submitted_at":"2026-02-24T18:37:34Z","abstract_excerpt":"Vision-language models excel at 2D visual understanding but remain limited in 3D spatial reasoning. Existing approaches either depend on explicit 3D modalities, which limits scalability, or inject partial, view-conditioned geometric priors and leave the language model to recover global scene structure from sparse cues. We introduce Spa3R, a self-supervised framework that learns a unified, view-invariant spatial representation from unposed multi-view RGB images. Its Predictive Spatial Field Modeling objective compresses context views into a compact latent representation and predicts aligned geo"},"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":"2602.21186","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-24T18:37:34Z","cross_cats_sorted":[],"title_canon_sha256":"323fcb2bb27ebbda7d5dc23e2b044634ad1d527b6d40c1c7bc669b1641693d26","abstract_canon_sha256":"6db67c5cfa084bed856a4fb5482997114379c4a421bf1038fc8d88c58baaf51e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:55:45.402738Z","signature_b64":"E9AUyFVSdVJYXsFm0oaJopVhdgY0IJkYGKS9pqaN9uPfW4eu9eK5YbdjGkGtK3y8bqH/5pE6EpuxlVBPsj9hAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3a28a0caa9ce19cc4fd6ddb3331c40e7d7cd56570410c002420ce46bb5a6d00","last_reissued_at":"2026-08-14T00:55:45.383554Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:55:45.383554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyi Jiang, Liu Liu, Wei Sui, Wenyu Liu, Xinggang Wang, Xinjie Wang, Yonghao He, Zhizhong Su","submitted_at":"2026-02-24T18:37:34Z","abstract_excerpt":"Vision-language models excel at 2D visual understanding but remain limited in 3D spatial reasoning. Existing approaches either depend on explicit 3D modalities, which limits scalability, or inject partial, view-conditioned geometric priors and leave the language model to recover global scene structure from sparse cues. We introduce Spa3R, a self-supervised framework that learns a unified, view-invariant spatial representation from unposed multi-view RGB images. Its Predictive Spatial Field Modeling objective compresses context views into a compact latent representation and predicts aligned geo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.21186","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/2602.21186/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":"2602.21186","created_at":"2026-08-14T00:55:45.395371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.21186v2","created_at":"2026-08-14T00:55:45.395371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.21186","created_at":"2026-08-14T00:55:45.395371+00:00"},{"alias_kind":"pith_short_12","alias_value":"WORIUDFKTTQZ","created_at":"2026-08-14T00:55:45.395371+00:00"},{"alias_kind":"pith_short_16","alias_value":"WORIUDFKTTQZZRH5","created_at":"2026-08-14T00:55:45.395371+00:00"},{"alias_kind":"pith_short_8","alias_value":"WORIUDFK","created_at":"2026-08-14T00:55:45.395371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.23565","citing_title":"HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25979","citing_title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WORIUDFKTTQZZRH5NXNTGMOEBZ","json":"https://pith.science/pith/WORIUDFKTTQZZRH5NXNTGMOEBZ.json","graph_json":"https://pith.science/api/pith-number/WORIUDFKTTQZZRH5NXNTGMOEBZ/graph.json","events_json":"https://pith.science/api/pith-number/WORIUDFKTTQZZRH5NXNTGMOEBZ/events.json","paper":"https://pith.science/paper/WORIUDFK"},"agent_actions":{"view_html":"https://pith.science/pith/WORIUDFKTTQZZRH5NXNTGMOEBZ","download_json":"https://pith.science/pith/WORIUDFKTTQZZRH5NXNTGMOEBZ.json","view_paper":"https://pith.science/paper/WORIUDFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.21186&json=true","fetch_graph":"https://pith.science/api/pith-number/WORIUDFKTTQZZRH5NXNTGMOEBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WORIUDFKTTQZZRH5NXNTGMOEBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WORIUDFKTTQZZRH5NXNTGMOEBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WORIUDFKTTQZZRH5NXNTGMOEBZ/action/storage_attestation","attest_author":"https://pith.science/pith/WORIUDFKTTQZZRH5NXNTGMOEBZ/action/author_attestation","sign_citation":"https://pith.science/pith/WORIUDFKTTQZZRH5NXNTGMOEBZ/action/citation_signature","submit_replication":"https://pith.science/pith/WORIUDFKTTQZZRH5NXNTGMOEBZ/action/replication_record"}},"created_at":"2026-08-14T00:55:45.395371+00:00","updated_at":"2026-08-14T00:55:45.395371+00:00"}