{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FQWQDELTSPB6U25NKWBGRADT4O","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":"fb979947687b1c5d25b2d80f1f261209d701bdcc6c633457a9eff1dc0c1979bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T22:20:07Z","title_canon_sha256":"28e4351e271b4041c56f71955ee6dba8648f04571fa221e2e27883777dd3d946"},"schema_version":"1.0","source":{"id":"2608.10278","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10278","created_at":"2026-08-12T00:23:45Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10278v1","created_at":"2026-08-12T00:23:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10278","created_at":"2026-08-12T00:23:45Z"},{"alias_kind":"pith_short_12","alias_value":"FQWQDELTSPB6","created_at":"2026-08-12T00:23:45Z"},{"alias_kind":"pith_short_16","alias_value":"FQWQDELTSPB6U25N","created_at":"2026-08-12T00:23:45Z"},{"alias_kind":"pith_short_8","alias_value":"FQWQDELT","created_at":"2026-08-12T00:23:45Z"}],"graph_snapshots":[{"event_id":"sha256:84243f7a381bb0b5dab8199ed6d8188abf50db2d08c17eafe4741c517fee0180","target":"graph","created_at":"2026-08-12T00:23:45Z","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/2608.10278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial understanding is fundamental to embodied intelligence, underpinning applications such as robotic manipulation, embodied navigation, and autonomous driving. Although recent vision-language models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, state-of-the-art approaches typically rely on additional spatial encoders or architectural modifications during inference, increasing computational cost. We introduce Space Tokens, a lightweight, architecture-agnostic framework that equips VLMs with explicit continuous spatial representations without requiring addition","authors_text":"Amir Rasouli, Dongfeng Bai, Hunter Schofield, Jinjun Shan, Mohammad Mahdavian, Mohammed Elmahgiubi, Richard Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T22:20:07Z","title":"Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10278","kind":"arxiv","version":1},"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":"sha256:9517b80d4295a90931a38605927f546a59e2b675ac596dd3ac5fc6d567806148","target":"record","created_at":"2026-08-12T00:23:45Z","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":"fb979947687b1c5d25b2d80f1f261209d701bdcc6c633457a9eff1dc0c1979bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T22:20:07Z","title_canon_sha256":"28e4351e271b4041c56f71955ee6dba8648f04571fa221e2e27883777dd3d946"},"schema_version":"1.0","source":{"id":"2608.10278","kind":"arxiv","version":1}},"canonical_sha256":"2c2d01917393c3ea6bad5582688073e39da4733d3baae6dcb6166aed65543fd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c2d01917393c3ea6bad5582688073e39da4733d3baae6dcb6166aed65543fd5","first_computed_at":"2026-08-12T00:23:45.378380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T00:23:45.378380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HWy6wm92Blu5a+iciCUKGj7HchHDvSsis3NJImrdR7tfIh9SqWhPOciACMPxsWppfzZkrQONKLlKF0Oca9fBAg==","signature_status":"signed_v1","signed_at":"2026-08-12T00:23:45.380288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10278","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9517b80d4295a90931a38605927f546a59e2b675ac596dd3ac5fc6d567806148","sha256:84243f7a381bb0b5dab8199ed6d8188abf50db2d08c17eafe4741c517fee0180"],"state_sha256":"54e0b6d58099bb063b3e6e3db176e82da1d21df9a3e29ff27ebab3825cbf3b62"}