{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QPEH64OYXYTWZO25YW5TCT6RAP","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":"6299e9d21ad336694ed888b70d16f95e5dd8ccab6343286bef5af6706528c1dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T17:56:36Z","title_canon_sha256":"8629644112524db20eb2c96a7ed78ef33afaca1caf83b3f71928cf658103036f"},"schema_version":"1.0","source":{"id":"2606.06476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06476","created_at":"2026-06-05T01:15:46Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06476v1","created_at":"2026-06-05T01:15:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06476","created_at":"2026-06-05T01:15:46Z"},{"alias_kind":"pith_short_12","alias_value":"QPEH64OYXYTW","created_at":"2026-06-05T01:15:46Z"},{"alias_kind":"pith_short_16","alias_value":"QPEH64OYXYTWZO25","created_at":"2026-06-05T01:15:46Z"},{"alias_kind":"pith_short_8","alias_value":"QPEH64OY","created_at":"2026-06-05T01:15:46Z"}],"graph_snapshots":[{"event_id":"sha256:0b2cfc0d929d1cabbbfe163be8c5ac7a2887826c1b32344df82729f25dd089e8","target":"graph","created_at":"2026-06-05T01:15:46Z","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/2606.06476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Vision-Language Models (VLMs) have shown strong visual reasoning capabilities, their spatial reasoning abilities remain largely constrained to the observed images and text-oriented chain-of-thought. They often struggle to infer unobserved layouts, maintain cross-view consistency, and reason from alternative viewpoints when only limited egocentric observations are available. In this work, we study this problem as thinking with imagination, where a VLM actively acquires imagined visual evidence by interacting with a world simulator during reasoning. We propose Astra, an agentic spatial rea","authors_text":"Chenming Zhu, Jiangmiao Pang, Jingli Lin, Peizhou Cao, Tai Wang, Xihui Liu, Yilin Long","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T17:56:36Z","title":"Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06476","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":"sha256:0e0ad4c58af625120d54e29661d15dba266fab0719a9a6fe7ebb16a47b89b6fa","target":"record","created_at":"2026-06-05T01:15:46Z","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":"6299e9d21ad336694ed888b70d16f95e5dd8ccab6343286bef5af6706528c1dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T17:56:36Z","title_canon_sha256":"8629644112524db20eb2c96a7ed78ef33afaca1caf83b3f71928cf658103036f"},"schema_version":"1.0","source":{"id":"2606.06476","kind":"arxiv","version":1}},"canonical_sha256":"83c87f71d8be276cbb5dc5bb314fd103fd627023ff48f9af559a1de3428c5b9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83c87f71d8be276cbb5dc5bb314fd103fd627023ff48f9af559a1de3428c5b9d","first_computed_at":"2026-06-05T01:15:46.718093Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:46.718093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TgezygAXR/yjwtToodHNHjru3fZifA02pxJzHyb9QoIw9JW415CcBKD+aAlCUhSL4CstLGqPoW4jM8jx5BUhCw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:46.718481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e0ad4c58af625120d54e29661d15dba266fab0719a9a6fe7ebb16a47b89b6fa","sha256:0b2cfc0d929d1cabbbfe163be8c5ac7a2887826c1b32344df82729f25dd089e8"],"state_sha256":"741ab5ea9dfeb235bf249134a3f3c785384df700e7f5238ff58f03d8cf5d116d"}