{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WORIUDFKTTQZZRH5NXNTGMOEBZ","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":"6db67c5cfa084bed856a4fb5482997114379c4a421bf1038fc8d88c58baaf51e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-24T18:37:34Z","title_canon_sha256":"323fcb2bb27ebbda7d5dc23e2b044634ad1d527b6d40c1c7bc669b1641693d26"},"schema_version":"1.0","source":{"id":"2602.21186","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.21186","created_at":"2026-08-14T00:55:45Z"},{"alias_kind":"arxiv_version","alias_value":"2602.21186v2","created_at":"2026-08-14T00:55:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.21186","created_at":"2026-08-14T00:55:45Z"},{"alias_kind":"pith_short_12","alias_value":"WORIUDFKTTQZ","created_at":"2026-08-14T00:55:45Z"},{"alias_kind":"pith_short_16","alias_value":"WORIUDFKTTQZZRH5","created_at":"2026-08-14T00:55:45Z"},{"alias_kind":"pith_short_8","alias_value":"WORIUDFK","created_at":"2026-08-14T00:55:45Z"}],"graph_snapshots":[{"event_id":"sha256:152b3a9f5dc2070bf1ba89720d02abd0943f9c6516b44b2cdc7ba936b364df40","target":"graph","created_at":"2026-08-14T00:55:45Z","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/2602.21186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haoyi Jiang, Liu Liu, Wei Sui, Wenyu Liu, Xinggang Wang, Xinjie Wang, Yonghao He, Zhizhong Su","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-24T18:37:34Z","title":"Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.21186","kind":"arxiv","version":2},"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":"sha256:7a707ea5d3b2ef3e4eb51d48ae8baed92985079d5a39ea5a8eb5496567874b4b","target":"record","created_at":"2026-08-14T00:55:45Z","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":"6db67c5cfa084bed856a4fb5482997114379c4a421bf1038fc8d88c58baaf51e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-24T18:37:34Z","title_canon_sha256":"323fcb2bb27ebbda7d5dc23e2b044634ad1d527b6d40c1c7bc669b1641693d26"},"schema_version":"1.0","source":{"id":"2602.21186","kind":"arxiv","version":2}},"canonical_sha256":"b3a28a0caa9ce19cc4fd6ddb3331c40e7d7cd56570410c002420ce46bb5a6d00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3a28a0caa9ce19cc4fd6ddb3331c40e7d7cd56570410c002420ce46bb5a6d00","first_computed_at":"2026-08-14T00:55:45.383554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T00:55:45.383554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E9AUyFVSdVJYXsFm0oaJopVhdgY0IJkYGKS9pqaN9uPfW4eu9eK5YbdjGkGtK3y8bqH/5pE6EpuxlVBPsj9hAQ==","signature_status":"signed_v1","signed_at":"2026-08-14T00:55:45.402738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.21186","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a707ea5d3b2ef3e4eb51d48ae8baed92985079d5a39ea5a8eb5496567874b4b","sha256:152b3a9f5dc2070bf1ba89720d02abd0943f9c6516b44b2cdc7ba936b364df40"],"state_sha256":"717c1286329fd1c544bfc1abcea05031d2e80eb32a9e50a2cec0ced122ca911b"}