{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NG37UDY4HLQYWNJFTT3XGC57PQ","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":"4ccb732210b118ccbc072553c713e5087b4ae6484149c0e11482afcfa864fc40","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:59:51Z","title_canon_sha256":"63b768f5641cd480dbada33da2ca9782807600608c3d2c35404f5499edc2f198"},"schema_version":"1.0","source":{"id":"2410.08208","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08208","created_at":"2026-07-05T10:22:07Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08208v3","created_at":"2026-07-05T10:22:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08208","created_at":"2026-07-05T10:22:07Z"},{"alias_kind":"pith_short_12","alias_value":"NG37UDY4HLQY","created_at":"2026-07-05T10:22:07Z"},{"alias_kind":"pith_short_16","alias_value":"NG37UDY4HLQYWNJF","created_at":"2026-07-05T10:22:07Z"},{"alias_kind":"pith_short_8","alias_value":"NG37UDY4","created_at":"2026-07-05T10:22:07Z"}],"graph_snapshots":[{"event_id":"sha256:8d5c975aca5399ce1abd4c06373fbd1630fa54361254025164b4d78b1b42b06e","target":"graph","created_at":"2026-07-05T10:22:07Z","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/2410.08208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce SPA, a novel representation learning framework that emphasizes the importance of 3D spatial awareness in embodied AI. Our approach leverages differentiable neural rendering on multi-view images to endow a vanilla Vision Transformer (ViT) with intrinsic spatial understanding. We present the most comprehensive evaluation of embodied representation learning to date, covering 268 tasks across 8 simulators with diverse policies in both single-task and language-conditioned multi-task scenarios. The results are compelling: SPA consistently outperforms more than 10 state-of","authors_text":"Haoyi Zhu, Honghui Yang, Jiange Yang, Limin Wang, Tong He, Yating Wang","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:59:51Z","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08208","kind":"arxiv","version":3},"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:fea7fc12854e1ad89adb8fe3382de5ab58111572b888ba06d5cdf1282f99dd43","target":"record","created_at":"2026-07-05T10:22:07Z","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":"4ccb732210b118ccbc072553c713e5087b4ae6484149c0e11482afcfa864fc40","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:59:51Z","title_canon_sha256":"63b768f5641cd480dbada33da2ca9782807600608c3d2c35404f5499edc2f198"},"schema_version":"1.0","source":{"id":"2410.08208","kind":"arxiv","version":3}},"canonical_sha256":"69b7fa0f1c3ae18b35259cf7730bbf7c312ce7c1839f9c81a182bb3ca1f2332b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69b7fa0f1c3ae18b35259cf7730bbf7c312ce7c1839f9c81a182bb3ca1f2332b","first_computed_at":"2026-07-05T10:22:07.284250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:07.284250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GE3XJDcK02IHHz28dXtYfJDIxYy/3akYKgRWLvKIeBHyZrbzJqf2TvdbK0U8y9ujBRZQYdLnF5ZHU5rpaLNHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:07.284815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08208","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fea7fc12854e1ad89adb8fe3382de5ab58111572b888ba06d5cdf1282f99dd43","sha256:8d5c975aca5399ce1abd4c06373fbd1630fa54361254025164b4d78b1b42b06e"],"state_sha256":"61b1adbf9321afaeb56bb57eb6802104dd0b60d5d3fa2152bd5a22063f2f85b9"}