{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QPEH64OYXYTWZO25YW5TCT6RAP","short_pith_number":"pith:QPEH64OY","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"},"canonical_sha256":"83c87f71d8be276cbb5dc5bb314fd103fd627023ff48f9af559a1de3428c5b9d","source":{"kind":"arxiv","id":"2606.06476","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QPEH64OYXYTWZO25YW5TCT6RAP","target":"record","payload":{"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"},"canonical_sha256":"83c87f71d8be276cbb5dc5bb314fd103fd627023ff48f9af559a1de3428c5b9d","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"},"source_kind":"arxiv","source_id":"2606.06476","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOt8bztgLkT0lzACfnlG3m0NrUI8CXYpgsHp4P1KCOGpKiMaMRaUGip6UgiJNWIz+E3QuOP8ZLABAMkPid8DDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:38:08.867648Z"},"content_sha256":"0e0ad4c58af625120d54e29661d15dba266fab0719a9a6fe7ebb16a47b89b6fa","schema_version":"1.0","event_id":"sha256:0e0ad4c58af625120d54e29661d15dba266fab0719a9a6fe7ebb16a47b89b6fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QPEH64OYXYTWZO25YW5TCT6RAP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"unvPf0FpNJw/arot9MKromm4alTRiJ6x+GN2zMJbbmJZKBGtOaGjxPQdNkrP5FvxKt24M4eYssalUVueFbodCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:38:08.868024Z"},"content_sha256":"0b2cfc0d929d1cabbbfe163be8c5ac7a2887826c1b32344df82729f25dd089e8","schema_version":"1.0","event_id":"sha256:0b2cfc0d929d1cabbbfe163be8c5ac7a2887826c1b32344df82729f25dd089e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP/bundle.json","state_url":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPEH64OYXYTWZO25YW5TCT6RAP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T19:38:08Z","links":{"resolver":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP","bundle":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP/bundle.json","state":"https://pith.science/pith/QPEH64OYXYTWZO25YW5TCT6RAP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPEH64OYXYTWZO25YW5TCT6RAP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HZ26Al/c21CDUJ/8R4wI5RhsWxSDUizQRR04efMJS9EfFLdUkPPaJyh7z7wzFQ/FJes8Fbq0YtQdMBk+9UnRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T19:38:08.870049Z","bundle_sha256":"d21edcfeb1c7a1416337429331c938a87f3047461b0baed736dc0564ef4cb193"}}