{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QPUEYN5EOECRDOVFX3ZFXJAECY","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":"4c2a90d037719e78a43f702a562d79a62f38ea5dbd86d00de002fdc5a8141d9d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T17:59:17Z","title_canon_sha256":"9ce6d5d15c3d402a6b27d6c6624cc94381fa337dc875962e0a41116bfbbc96ba"},"schema_version":"1.0","source":{"id":"2606.03988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03988","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03988v1","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03988","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"QPUEYN5EOECR","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"QPUEYN5EOECRDOVF","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"QPUEYN5E","created_at":"2026-06-03T02:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:abe654bb756ba0f0446d6cabd6e0d769655758630ff663e84be2274fbf681f49","target":"graph","created_at":"2026-06-03T02:06:08Z","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/2606.03988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable. Many such problems require imaginative perception: inferring what would be seen from an unseen viewpoint, tracing paths through occluded spaces, or integrating partial observations into a coherent spatial representation. We introduce Imaginative Perception Tokens (IPT), intermediate perceptual representations that externalize what a VLM would perceive under alternative spatial configurations while remaining consistent with the observed input.\n  To st","authors_text":"Chris Dangjoo Kim, Jaemin Cho, Jieyu Zhang, Linda Shapiro, Lindsey Li, Mahtab Bigverdi, Ranjay Krishna, Tuhin Kundu, Weikai Huang, Yiming Liu, Zelun Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T17:59:17Z","title":"Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03988","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:e3ba0d2cb5e5ee1ac8ff6889e92142059680afabef54abdfc7c2340b767a2208","target":"record","created_at":"2026-06-03T02:06:08Z","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":"4c2a90d037719e78a43f702a562d79a62f38ea5dbd86d00de002fdc5a8141d9d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T17:59:17Z","title_canon_sha256":"9ce6d5d15c3d402a6b27d6c6624cc94381fa337dc875962e0a41116bfbbc96ba"},"schema_version":"1.0","source":{"id":"2606.03988","kind":"arxiv","version":1}},"canonical_sha256":"83e84c37a4710511baa5bef25ba404163aaca4a3babd1cb21d5723d5a7e91b22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83e84c37a4710511baa5bef25ba404163aaca4a3babd1cb21d5723d5a7e91b22","first_computed_at":"2026-06-03T02:06:08.854656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:08.854656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WgYjTDK8+O4OMb0dZY0eVT+UjBBxmkJchAyGK80FZ1UQT1a+E3PikoNvI2LL147eXIFtMsl7jk7Tg/79eTjmBA==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:08.855067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3ba0d2cb5e5ee1ac8ff6889e92142059680afabef54abdfc7c2340b767a2208","sha256:abe654bb756ba0f0446d6cabd6e0d769655758630ff663e84be2274fbf681f49"],"state_sha256":"4ddf6f755acd2dc8b17564dd7a8e271daf480ce608db0630c4abfd1241f4936f"}