{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JVDOBDNXNRV2CBQWWSCR73D3G2","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":"727ee2070b98af14c4efc6c45b34cc07c816b9bdcb4aeb07f47ba8f304a6ac4e","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-20T13:49:09Z","title_canon_sha256":"2ce4b9e43d886e933d35fe512c7fa9e5107b68d1569381a9c985dec6d443484f"},"schema_version":"1.0","source":{"id":"2505.14366","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14366","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14366v1","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14366","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"JVDOBDNXNRV2","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"JVDOBDNXNRV2CBQW","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"JVDOBDNX","created_at":"2026-07-05T11:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:29ed4030fdef71cdf66fa11ba3e5ae02644e2fdff41812e39f5bb94810f2cea3","target":"graph","created_at":"2026-07-05T11:06:00Z","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/2505.14366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a conceptual framework for training Vision-Language Models (VLMs) to perform Visual Perspective Taking (VPT), a core capability for embodied cognition essential for Human-Robot Interaction (HRI). As a first step toward this goal, we introduce a synthetic dataset, generated in NVIDIA Omniverse, that enables supervised learning for spatial reasoning tasks. Each instance includes an RGB image, a natural language description, and a ground-truth 4X4 transformation matrix representing object pose. We focus on inferring Z-axis distance as a foundational skill, with future extensions target","authors_text":"Agnieszka Wykowska, Davide De Tommaso, Enrico Piacenti, Gioele Migno, Joel Currie, Maria Elena Giannaccini, Patric Bach","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-20T13:49:09Z","title":"Towards Embodied Cognition in Robots via Spatially Grounded Synthetic Worlds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14366","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:b126ed00c6e18e0bbc1588c3f49aa9ef888991ec33a55c6ffea618a2403fc778","target":"record","created_at":"2026-07-05T11:06:00Z","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":"727ee2070b98af14c4efc6c45b34cc07c816b9bdcb4aeb07f47ba8f304a6ac4e","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-20T13:49:09Z","title_canon_sha256":"2ce4b9e43d886e933d35fe512c7fa9e5107b68d1569381a9c985dec6d443484f"},"schema_version":"1.0","source":{"id":"2505.14366","kind":"arxiv","version":1}},"canonical_sha256":"4d46e08db76c6ba10616b4851fec7b36a9c571824ba802e03c8ae34b1a001fe9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d46e08db76c6ba10616b4851fec7b36a9c571824ba802e03c8ae34b1a001fe9","first_computed_at":"2026-07-05T11:06:00.406093Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:00.406093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RFNCpXeFobGymPLhty94FngErifmGMIdc8UsN9oKi4/QBhFoFcu1vKFnt/B+Wxafao/uY+dRMWzaVTAlFY1dCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:00.406568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14366","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b126ed00c6e18e0bbc1588c3f49aa9ef888991ec33a55c6ffea618a2403fc778","sha256:29ed4030fdef71cdf66fa11ba3e5ae02644e2fdff41812e39f5bb94810f2cea3"],"state_sha256":"6b41a0dc8df0cf4dcae19a012445d84b8970de9fcdb93c1b5d23542ace34b6b5"}