{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QPUEYN5EOECRDOVFX3ZFXJAECY","short_pith_number":"pith:QPUEYN5E","schema_version":"1.0","canonical_sha256":"83e84c37a4710511baa5bef25ba404163aaca4a3babd1cb21d5723d5a7e91b22","source":{"kind":"arxiv","id":"2606.03988","version":1},"attestation_state":"computed","paper":{"title":"Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2026-06-02T17:59:17Z","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"},"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":"2606.03988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T17:59:17Z","cross_cats_sorted":[],"title_canon_sha256":"9ce6d5d15c3d402a6b27d6c6624cc94381fa337dc875962e0a41116bfbbc96ba","abstract_canon_sha256":"4c2a90d037719e78a43f702a562d79a62f38ea5dbd86d00de002fdc5a8141d9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:08.855067Z","signature_b64":"WgYjTDK8+O4OMb0dZY0eVT+UjBBxmkJchAyGK80FZ1UQT1a+E3PikoNvI2LL147eXIFtMsl7jk7Tg/79eTjmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83e84c37a4710511baa5bef25ba404163aaca4a3babd1cb21d5723d5a7e91b22","last_reissued_at":"2026-06-03T02:06:08.854656Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:08.854656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2026-06-02T17:59:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03988","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/2606.03988/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":"2606.03988","created_at":"2026-06-03T02:06:08.854717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03988v1","created_at":"2026-06-03T02:06:08.854717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03988","created_at":"2026-06-03T02:06:08.854717+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPUEYN5EOECR","created_at":"2026-06-03T02:06:08.854717+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPUEYN5EOECRDOVF","created_at":"2026-06-03T02:06:08.854717+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPUEYN5E","created_at":"2026-06-03T02:06:08.854717+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/QPUEYN5EOECRDOVFX3ZFXJAECY","json":"https://pith.science/pith/QPUEYN5EOECRDOVFX3ZFXJAECY.json","graph_json":"https://pith.science/api/pith-number/QPUEYN5EOECRDOVFX3ZFXJAECY/graph.json","events_json":"https://pith.science/api/pith-number/QPUEYN5EOECRDOVFX3ZFXJAECY/events.json","paper":"https://pith.science/paper/QPUEYN5E"},"agent_actions":{"view_html":"https://pith.science/pith/QPUEYN5EOECRDOVFX3ZFXJAECY","download_json":"https://pith.science/pith/QPUEYN5EOECRDOVFX3ZFXJAECY.json","view_paper":"https://pith.science/paper/QPUEYN5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03988&json=true","fetch_graph":"https://pith.science/api/pith-number/QPUEYN5EOECRDOVFX3ZFXJAECY/graph.json","fetch_events":"https://pith.science/api/pith-number/QPUEYN5EOECRDOVFX3ZFXJAECY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPUEYN5EOECRDOVFX3ZFXJAECY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPUEYN5EOECRDOVFX3ZFXJAECY/action/storage_attestation","attest_author":"https://pith.science/pith/QPUEYN5EOECRDOVFX3ZFXJAECY/action/author_attestation","sign_citation":"https://pith.science/pith/QPUEYN5EOECRDOVFX3ZFXJAECY/action/citation_signature","submit_replication":"https://pith.science/pith/QPUEYN5EOECRDOVFX3ZFXJAECY/action/replication_record"}},"created_at":"2026-06-03T02:06:08.854717+00:00","updated_at":"2026-06-03T02:06:08.854717+00:00"}