{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IOYHG2TWNZLJXXDOOZPWSZJHAX","short_pith_number":"pith:IOYHG2TW","canonical_record":{"source":{"id":"2506.00123","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T18:00:34Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"71f204e3a5670b147f579ebf31d9e384d79d3e56389d14bcffe21874e7c05742","abstract_canon_sha256":"03fc39b5571b198c37d0b9d7dcba5f22fc71d9bc15c4748d0294982154dd4ffb"},"schema_version":"1.0"},"canonical_sha256":"43b0736a766e569bdc6e765f69652705cb473a403906660d0adf1000034dacfc","source":{"kind":"arxiv","id":"2506.00123","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00123","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00123v1","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00123","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"IOYHG2TWNZLJ","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"IOYHG2TWNZLJXXDO","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"IOYHG2TW","created_at":"2026-07-05T11:13:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IOYHG2TWNZLJXXDOOZPWSZJHAX","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00123","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T18:00:34Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"71f204e3a5670b147f579ebf31d9e384d79d3e56389d14bcffe21874e7c05742","abstract_canon_sha256":"03fc39b5571b198c37d0b9d7dcba5f22fc71d9bc15c4748d0294982154dd4ffb"},"schema_version":"1.0"},"canonical_sha256":"43b0736a766e569bdc6e765f69652705cb473a403906660d0adf1000034dacfc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:29.310022Z","signature_b64":"PV9yFzrQIvc8tQ2Wtrh+Fbc1THN+tIi/QBUuGr0hnAfWhmQlc8klB3WUw3ghR1klTTsgYTkBOrArR99ezVXyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43b0736a766e569bdc6e765f69652705cb473a403906660d0adf1000034dacfc","last_reissued_at":"2026-07-05T11:13:29.309564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:29.309564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00123","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tvkmkqxm9Fg+/JsXc/SIGYS7xcjI3BTjsqEJiX+Q8kBXC51Fv9m1ZM/LeNglBojb/9DASFcJyaiWLH5d+NRnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:54:36.057904Z"},"content_sha256":"c10260be50f87113b05027fac0ff46859c190b76768156fa75120b082be7313d","schema_version":"1.0","event_id":"sha256:c10260be50f87113b05027fac0ff46859c190b76768156fa75120b082be7313d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IOYHG2TWNZLJXXDOOZPWSZJHAX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Erfei Cui, Ganlin Yang, Gen Luo, Guanzhou Chen, Haonan Duan, Jifeng Dai, Jingbo Wang, Lewei Lu, Ronglei Tong, Rongrong Ji, Shenglong Ye, Tianyi Zhang, Wenhai Wang, Xizhou Zhu, Yu Qiao, Zhe Chen, Zhi Hou, Ziyang Gong","submitted_at":"2025-05-30T18:00:34Z","abstract_excerpt":"The remarkable progress of Multimodal Large Language Models (MLLMs) has attracted increasing attention to extend them to physical entities like legged robot. This typically requires MLLMs to not only grasp multimodal understanding abilities, but also integrate visual-spatial reasoning and physical interaction capabilities. Nevertheless,existing methods struggle to unify these capabilities due to their fundamental differences.In this paper, we present the Visual Embodied Brain (VeBrain), a unified framework for perception, reasoning, and control in real world. VeBrain reformulates robotic contr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00123","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/2506.00123/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TGEtM5L7NkaWw7Uf7g5vh3z2E4yHjVb0APBBus1nXMF4zUrHTWQrasHyRAzFcm2tqekowIbDZojKQDvaUge1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:54:36.059042Z"},"content_sha256":"f8118b8347f127c2b2d05c03f05e6399ee4ca82112dc9d3022b1bad23f9c1b4e","schema_version":"1.0","event_id":"sha256:f8118b8347f127c2b2d05c03f05e6399ee4ca82112dc9d3022b1bad23f9c1b4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IOYHG2TWNZLJXXDOOZPWSZJHAX/bundle.json","state_url":"https://pith.science/pith/IOYHG2TWNZLJXXDOOZPWSZJHAX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IOYHG2TWNZLJXXDOOZPWSZJHAX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T02:54:36Z","links":{"resolver":"https://pith.science/pith/IOYHG2TWNZLJXXDOOZPWSZJHAX","bundle":"https://pith.science/pith/IOYHG2TWNZLJXXDOOZPWSZJHAX/bundle.json","state":"https://pith.science/pith/IOYHG2TWNZLJXXDOOZPWSZJHAX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IOYHG2TWNZLJXXDOOZPWSZJHAX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IOYHG2TWNZLJXXDOOZPWSZJHAX","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":"03fc39b5571b198c37d0b9d7dcba5f22fc71d9bc15c4748d0294982154dd4ffb","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T18:00:34Z","title_canon_sha256":"71f204e3a5670b147f579ebf31d9e384d79d3e56389d14bcffe21874e7c05742"},"schema_version":"1.0","source":{"id":"2506.00123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00123","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00123v1","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00123","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"IOYHG2TWNZLJ","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"IOYHG2TWNZLJXXDO","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"IOYHG2TW","created_at":"2026-07-05T11:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:f8118b8347f127c2b2d05c03f05e6399ee4ca82112dc9d3022b1bad23f9c1b4e","target":"graph","created_at":"2026-07-05T11:13:29Z","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/2506.00123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable progress of Multimodal Large Language Models (MLLMs) has attracted increasing attention to extend them to physical entities like legged robot. This typically requires MLLMs to not only grasp multimodal understanding abilities, but also integrate visual-spatial reasoning and physical interaction capabilities. Nevertheless,existing methods struggle to unify these capabilities due to their fundamental differences.In this paper, we present the Visual Embodied Brain (VeBrain), a unified framework for perception, reasoning, and control in real world. VeBrain reformulates robotic contr","authors_text":"Erfei Cui, Ganlin Yang, Gen Luo, Guanzhou Chen, Haonan Duan, Jifeng Dai, Jingbo Wang, Lewei Lu, Ronglei Tong, Rongrong Ji, Shenglong Ye, Tianyi Zhang, Wenhai Wang, Xizhou Zhu, Yu Qiao, Zhe Chen, Zhi Hou, Ziyang Gong","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T18:00:34Z","title":"Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00123","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:c10260be50f87113b05027fac0ff46859c190b76768156fa75120b082be7313d","target":"record","created_at":"2026-07-05T11:13:29Z","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":"03fc39b5571b198c37d0b9d7dcba5f22fc71d9bc15c4748d0294982154dd4ffb","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T18:00:34Z","title_canon_sha256":"71f204e3a5670b147f579ebf31d9e384d79d3e56389d14bcffe21874e7c05742"},"schema_version":"1.0","source":{"id":"2506.00123","kind":"arxiv","version":1}},"canonical_sha256":"43b0736a766e569bdc6e765f69652705cb473a403906660d0adf1000034dacfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43b0736a766e569bdc6e765f69652705cb473a403906660d0adf1000034dacfc","first_computed_at":"2026-07-05T11:13:29.309564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:29.309564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PV9yFzrQIvc8tQ2Wtrh+Fbc1THN+tIi/QBUuGr0hnAfWhmQlc8klB3WUw3ghR1klTTsgYTkBOrArR99ezVXyCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:29.310022Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c10260be50f87113b05027fac0ff46859c190b76768156fa75120b082be7313d","sha256:f8118b8347f127c2b2d05c03f05e6399ee4ca82112dc9d3022b1bad23f9c1b4e"],"state_sha256":"00e71858a4e9b4b42b2286c9dd809d4dc2d6735acd3a2eb9f677d3c5bf8aef66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ahiV1PVLzr0MN4+wOyVzzL/fdf+WAKiY9N+DmDeIccw6H19CMAqLE2DCUcG7tjKMkikm4dv7V1zRpw/8yD4NDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T02:54:36.062405Z","bundle_sha256":"24d8e2af5d140e0ec39b918d6667ba99783a6798a3165229d242ddd620695863"}}