{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BMDKUVF2EDAOS4E53FCUWJ5IB6","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":"c6599e5ff69a42c04c7afc5c3efaa4187b8f108f8996dd9b1d48444397c1a45f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T06:16:11Z","title_canon_sha256":"ae582487fd8885f25b9b82c53e1b56aaf3e8b70ee4ff6be949dfe3bec04af7a0"},"schema_version":"1.0","source":{"id":"2504.12680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12680","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12680v1","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12680","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"BMDKUVF2EDAO","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"BMDKUVF2EDAOS4E5","created_at":"2026-07-05T10:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"BMDKUVF2","created_at":"2026-07-05T10:50:20Z"}],"graph_snapshots":[{"event_id":"sha256:aef62097b961b0a7e4a550203bdfc542372e7e313f05b22c287932be8528f216","target":"graph","created_at":"2026-07-05T10:50:20Z","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/2504.12680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This paper introduces Embodied-R, a collaborative framework combining large-scale Vision-Language Models (VLMs) for perception and small-scale Language Models (LMs) for reasoning. Using Reinforcement Learning (RL) with a novel reward system considering think-answer logical consistency, the model achieves slow-thinking capabilities with limited computational resou","authors_text":"Baining Zhao, Chen Gao, Fanhang Man, Jianjie Fang, Jinqiang Cui, Wenwu Zhu, Xinlei Chen, Xin Wang, Yong Li, Ziyou Wang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T06:16:11Z","title":"Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12680","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":"sha256:9219644af9e09787dc0a222f32ffd33e5f17a1f7200ecc8f38971ac8400fdc0e","target":"record","created_at":"2026-07-05T10:50:20Z","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":"c6599e5ff69a42c04c7afc5c3efaa4187b8f108f8996dd9b1d48444397c1a45f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T06:16:11Z","title_canon_sha256":"ae582487fd8885f25b9b82c53e1b56aaf3e8b70ee4ff6be949dfe3bec04af7a0"},"schema_version":"1.0","source":{"id":"2504.12680","kind":"arxiv","version":1}},"canonical_sha256":"0b06aa54ba20c0e9709dd9454b27a80f803ebae58a2b84bb339829e469a0fad5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b06aa54ba20c0e9709dd9454b27a80f803ebae58a2b84bb339829e469a0fad5","first_computed_at":"2026-07-05T10:50:20.507013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:20.507013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pm6wWyLZHi6PgTshda/BqnjUXW4JtKiakvDcMNR0umdqb5zoh3SZh99lK3t6wzS/rQEhW4UIAX/JzFskBEHnAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:20.507521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9219644af9e09787dc0a222f32ffd33e5f17a1f7200ecc8f38971ac8400fdc0e","sha256:aef62097b961b0a7e4a550203bdfc542372e7e313f05b22c287932be8528f216"],"state_sha256":"74af46d78d87a578fa196d2bc00d907e01f21d832be1c0bf20fc72a3b67f3f7f"}