{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U774CFTYHRJHFFLXWVX5HP3UNG","short_pith_number":"pith:U774CFTY","schema_version":"1.0","canonical_sha256":"a7ffc116783c52729577b56fd3bf74699516d4a99e28fe465c2c5ee15aed760c","source":{"kind":"arxiv","id":"2504.17207","version":1},"attestation_state":"computed","paper":{"title":"Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chanho Park, Jihyeon Je, Leonidas Guibas, Mikaela Angelina Uy, Minhyuk Sung, Phillip Y. Lee","submitted_at":"2025-04-24T02:41:34Z","abstract_excerpt":"We present a framework for perspective-aware reasoning in vision-language models (VLMs) through mental imagery simulation. Perspective-taking, the ability to perceive an environment or situation from an alternative viewpoint, is a key benchmark for human-level visual understanding, essential for environmental interaction and collaboration with autonomous agents. Despite advancements in spatial reasoning within VLMs, recent research has shown that modern VLMs significantly lack perspective-aware reasoning capabilities and exhibit a strong bias toward egocentric interpretations. To bridge the ga"},"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":"2504.17207","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T02:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"cbc5bbcec41d21422f1ce11a034c6087c56fb8a81fc96d106e17f45cab5eac97","abstract_canon_sha256":"9f6c0c8d37698d7f01b70aedead51be9c42496d8e7ca5d03e66ce43e184a7f4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:24.267141Z","signature_b64":"xEGWxii0tk2hU7DnUaYmNt5/MdOJYvKZtg0VTKueCBb4OGnbDq8Q5LuiQlbASLiw0Q3uHMDGdGlgd4HEYOQQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7ffc116783c52729577b56fd3bf74699516d4a99e28fe465c2c5ee15aed760c","last_reissued_at":"2026-07-05T10:53:24.266661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:24.266661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chanho Park, Jihyeon Je, Leonidas Guibas, Mikaela Angelina Uy, Minhyuk Sung, Phillip Y. Lee","submitted_at":"2025-04-24T02:41:34Z","abstract_excerpt":"We present a framework for perspective-aware reasoning in vision-language models (VLMs) through mental imagery simulation. Perspective-taking, the ability to perceive an environment or situation from an alternative viewpoint, is a key benchmark for human-level visual understanding, essential for environmental interaction and collaboration with autonomous agents. Despite advancements in spatial reasoning within VLMs, recent research has shown that modern VLMs significantly lack perspective-aware reasoning capabilities and exhibit a strong bias toward egocentric interpretations. To bridge the ga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17207","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/2504.17207/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":"2504.17207","created_at":"2026-07-05T10:53:24.266723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17207v1","created_at":"2026-07-05T10:53:24.266723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17207","created_at":"2026-07-05T10:53:24.266723+00:00"},{"alias_kind":"pith_short_12","alias_value":"U774CFTYHRJH","created_at":"2026-07-05T10:53:24.266723+00:00"},{"alias_kind":"pith_short_16","alias_value":"U774CFTYHRJHFFLX","created_at":"2026-07-05T10:53:24.266723+00:00"},{"alias_kind":"pith_short_8","alias_value":"U774CFTY","created_at":"2026-07-05T10:53:24.266723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17539","citing_title":"Reinforcing Dual-Path Reasoning in Spatial Vision Language Models","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U774CFTYHRJHFFLXWVX5HP3UNG","json":"https://pith.science/pith/U774CFTYHRJHFFLXWVX5HP3UNG.json","graph_json":"https://pith.science/api/pith-number/U774CFTYHRJHFFLXWVX5HP3UNG/graph.json","events_json":"https://pith.science/api/pith-number/U774CFTYHRJHFFLXWVX5HP3UNG/events.json","paper":"https://pith.science/paper/U774CFTY"},"agent_actions":{"view_html":"https://pith.science/pith/U774CFTYHRJHFFLXWVX5HP3UNG","download_json":"https://pith.science/pith/U774CFTYHRJHFFLXWVX5HP3UNG.json","view_paper":"https://pith.science/paper/U774CFTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17207&json=true","fetch_graph":"https://pith.science/api/pith-number/U774CFTYHRJHFFLXWVX5HP3UNG/graph.json","fetch_events":"https://pith.science/api/pith-number/U774CFTYHRJHFFLXWVX5HP3UNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U774CFTYHRJHFFLXWVX5HP3UNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U774CFTYHRJHFFLXWVX5HP3UNG/action/storage_attestation","attest_author":"https://pith.science/pith/U774CFTYHRJHFFLXWVX5HP3UNG/action/author_attestation","sign_citation":"https://pith.science/pith/U774CFTYHRJHFFLXWVX5HP3UNG/action/citation_signature","submit_replication":"https://pith.science/pith/U774CFTYHRJHFFLXWVX5HP3UNG/action/replication_record"}},"created_at":"2026-07-05T10:53:24.266723+00:00","updated_at":"2026-07-05T10:53:24.266723+00:00"}