{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2NBL3WW5GABW4BM257BHI7FK6N","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":"99904d81ec4b75617a00c1690809b624bc28b8be3cdf034f32e42c5cf6799bbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T07:54:42Z","title_canon_sha256":"42cea0ce0682de35349d4e66d03c7646991a91eee78ed0147e1fbabee89b999f"},"schema_version":"1.0","source":{"id":"2606.11770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11770","created_at":"2026-06-11T01:10:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11770v1","created_at":"2026-06-11T01:10:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11770","created_at":"2026-06-11T01:10:07Z"},{"alias_kind":"pith_short_12","alias_value":"2NBL3WW5GABW","created_at":"2026-06-11T01:10:07Z"},{"alias_kind":"pith_short_16","alias_value":"2NBL3WW5GABW4BM2","created_at":"2026-06-11T01:10:07Z"},{"alias_kind":"pith_short_8","alias_value":"2NBL3WW5","created_at":"2026-06-11T01:10:07Z"}],"graph_snapshots":[{"event_id":"sha256:f37769a4ca32ac8909ac00e16761112d5a6165e19b6fe65e54e37b1d61b7f65b","target":"graph","created_at":"2026-06-11T01:10:07Z","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/2606.11770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial reasoning remains a challenge for Multimodal Large Language Models (MLLMs), as it requires reliable multi-hop inference over both intermediate states and state transitions. Current studies often leave intermediate states unverified and treat state transitions as implicit processes, which limits reliability in multi-hop spatial reasoning. To address this, we propose State-aware Visualization-of-Thought (SVoT), a reinforcement learning framework that generates interleaved, verifiable intermediate states and visualizations. SVoT integrates transition reasoning chains into the generation p","authors_text":"Chao Lei, Krista A. Ehinger, Markus Hiller, Nir Lipovetzky, Xunye Tian, Yanbei Jiang, Zhijian Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T07:54:42Z","title":"SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11770","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":"sha256:8a4ae68f3fe516ff34eb48a19c87e4b1d42ab56535c53013cd11b3c75a8a3e75","target":"record","created_at":"2026-06-11T01:10:07Z","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":"99904d81ec4b75617a00c1690809b624bc28b8be3cdf034f32e42c5cf6799bbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T07:54:42Z","title_canon_sha256":"42cea0ce0682de35349d4e66d03c7646991a91eee78ed0147e1fbabee89b999f"},"schema_version":"1.0","source":{"id":"2606.11770","kind":"arxiv","version":1}},"canonical_sha256":"d342bddadd30036e059aefc2747caaf3572f29fc511e0b11489afba3db9a496c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d342bddadd30036e059aefc2747caaf3572f29fc511e0b11489afba3db9a496c","first_computed_at":"2026-06-11T01:10:07.049105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:07.049105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u3XAdxe5ltzN290mckKvPfOrYVCsRfpwJPqR1lt74a8EOUag3sdsyW9HgxtfL9f71gTp8tKLfvRvXhaF/EOAAA==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:07.049883Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a4ae68f3fe516ff34eb48a19c87e4b1d42ab56535c53013cd11b3c75a8a3e75","sha256:f37769a4ca32ac8909ac00e16761112d5a6165e19b6fe65e54e37b1d61b7f65b"],"state_sha256":"a43ab27e32831845fc3ff21147dd33b336d678bacc935ab838c0a0caf38bf291"}