{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QPEH64OYXYTWZO25YW5TCT6RAP","short_pith_number":"pith:QPEH64OY","schema_version":"1.0","canonical_sha256":"83c87f71d8be276cbb5dc5bb314fd103fd627023ff48f9af559a1de3428c5b9d","source":{"kind":"arxiv","id":"2606.06476","version":1},"attestation_state":"computed","paper":{"title":"Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenming Zhu, Jiangmiao Pang, Jingli Lin, Peizhou Cao, Tai Wang, Xihui Liu, Yilin Long","submitted_at":"2026-06-04T17:56:36Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.06476","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T17:56:36Z","cross_cats_sorted":[],"title_canon_sha256":"8629644112524db20eb2c96a7ed78ef33afaca1caf83b3f71928cf658103036f","abstract_canon_sha256":"6299e9d21ad336694ed888b70d16f95e5dd8ccab6343286bef5af6706528c1dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:46.718481Z","signature_b64":"TgezygAXR/yjwtToodHNHjru3fZifA02pxJzHyb9QoIw9JW415CcBKD+aAlCUhSL4CstLGqPoW4jM8jx5BUhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83c87f71d8be276cbb5dc5bb314fd103fd627023ff48f9af559a1de3428c5b9d","last_reissued_at":"2026-06-05T01:15:46.718093Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:46.718093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenming Zhu, Jiangmiao Pang, Jingli Lin, Peizhou Cao, Tai Wang, Xihui Liu, Yilin Long","submitted_at":"2026-06-04T17:56:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06476","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.06476/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.06476","created_at":"2026-06-05T01:15:46.718154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06476v1","created_at":"2026-06-05T01:15:46.718154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06476","created_at":"2026-06-05T01:15:46.718154+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPEH64OYXYTW","created_at":"2026-06-05T01:15:46.718154+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPEH64OYXYTWZO25","created_at":"2026-06-05T01:15:46.718154+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPEH64OY","created_at":"2026-06-05T01:15:46.718154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP","json":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP.json","graph_json":"https://pith.science/api/pith-number/QPEH64OYXYTWZO25YW5TCT6RAP/graph.json","events_json":"https://pith.science/api/pith-number/QPEH64OYXYTWZO25YW5TCT6RAP/events.json","paper":"https://pith.science/paper/QPEH64OY"},"agent_actions":{"view_html":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP","download_json":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP.json","view_paper":"https://pith.science/paper/QPEH64OY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06476&json=true","fetch_graph":"https://pith.science/api/pith-number/QPEH64OYXYTWZO25YW5TCT6RAP/graph.json","fetch_events":"https://pith.science/api/pith-number/QPEH64OYXYTWZO25YW5TCT6RAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP/action/storage_attestation","attest_author":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP/action/author_attestation","sign_citation":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP/action/citation_signature","submit_replication":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP/action/replication_record"}},"created_at":"2026-06-05T01:15:46.718154+00:00","updated_at":"2026-06-05T01:15:46.718154+00:00"}