{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q5GVA6WS5LALUT76JS3YX62RK4","short_pith_number":"pith:Q5GVA6WS","schema_version":"1.0","canonical_sha256":"874d507ad2eac0ba4ffe4cb78bfb5157125a13d554094db1edd82314526ebde5","source":{"kind":"arxiv","id":"2607.24744","version":1},"attestation_state":"computed","paper":{"title":"Data Pyramid for Embodied Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bohan Hou, Duo Zheng, Jiaming Liu, Jianfei Yang, Jun Cen, Kuangzhi Ge, Lingdong Kong, Michael Yu Wang, Ping Luo, Qifeng Chen, Shanghang Zhang, Sirui Han, Tianxing Chen, Wei Chow, Weihao Yuan, Xian Sun, Xiaowei Chi, Xidong Zhang, Yankai Fu, Yao Mu, Yaoxu Lv, Yifan Ye, Yingshuo Wang, Yiwu Zhong, Yunfan Lou, Zhibo Pang, Zhihe Lu, Ziang Cao, Ziwei Liu","submitted_at":"2026-07-27T17:59:58Z","abstract_excerpt":"Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require data that couple observations with physical states and actions. These signals can be provided, to varying degrees, by multiple data sources. In this work, we organize the embodied data ecosystem as a \"pyramid\" spanning five complementary sources: real-robot data, UMI-style data, egocentric and exocentric data, simulation data, and general vision-language data. We organize the pyramid around the tension between scalability and robot alignment, and "},"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":"2607.24744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-27T17:59:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f6cd258da69eef5a56153df61d4458054cbcba647af5598362731a8eb29b1d72","abstract_canon_sha256":"d21f03c017088c6237eb1ce197e9bb4398fe53fb0fb9e61a8112a45a33820ec5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:25.783026Z","signature_b64":"vFD99svdiysKty92bRYiGfQvu6xLXeEkbCmp/fI1xHyIyktrdCrRFyotA0EUOtlmPk0emxcWTXTQ2IKgry+nBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"874d507ad2eac0ba4ffe4cb78bfb5157125a13d554094db1edd82314526ebde5","last_reissued_at":"2026-07-28T02:24:25.781367Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:25.781367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Pyramid for Embodied Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bohan Hou, Duo Zheng, Jiaming Liu, Jianfei Yang, Jun Cen, Kuangzhi Ge, Lingdong Kong, Michael Yu Wang, Ping Luo, Qifeng Chen, Shanghang Zhang, Sirui Han, Tianxing Chen, Wei Chow, Weihao Yuan, Xian Sun, Xiaowei Chi, Xidong Zhang, Yankai Fu, Yao Mu, Yaoxu Lv, Yifan Ye, Yingshuo Wang, Yiwu Zhong, Yunfan Lou, Zhibo Pang, Zhihe Lu, Ziang Cao, Ziwei Liu","submitted_at":"2026-07-27T17:59:58Z","abstract_excerpt":"Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require data that couple observations with physical states and actions. These signals can be provided, to varying degrees, by multiple data sources. In this work, we organize the embodied data ecosystem as a \"pyramid\" spanning five complementary sources: real-robot data, UMI-style data, egocentric and exocentric data, simulation data, and general vision-language data. We organize the pyramid around the tension between scalability and robot alignment, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24744","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/2607.24744/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":"2607.24744","created_at":"2026-07-28T02:24:25.782618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24744v1","created_at":"2026-07-28T02:24:25.782618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24744","created_at":"2026-07-28T02:24:25.782618+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5GVA6WS5LAL","created_at":"2026-07-28T02:24:25.782618+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5GVA6WS5LALUT76","created_at":"2026-07-28T02:24:25.782618+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5GVA6WS","created_at":"2026-07-28T02:24:25.782618+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/Q5GVA6WS5LALUT76JS3YX62RK4","json":"https://pith.science/pith/Q5GVA6WS5LALUT76JS3YX62RK4.json","graph_json":"https://pith.science/api/pith-number/Q5GVA6WS5LALUT76JS3YX62RK4/graph.json","events_json":"https://pith.science/api/pith-number/Q5GVA6WS5LALUT76JS3YX62RK4/events.json","paper":"https://pith.science/paper/Q5GVA6WS"},"agent_actions":{"view_html":"https://pith.science/pith/Q5GVA6WS5LALUT76JS3YX62RK4","download_json":"https://pith.science/pith/Q5GVA6WS5LALUT76JS3YX62RK4.json","view_paper":"https://pith.science/paper/Q5GVA6WS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24744&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5GVA6WS5LALUT76JS3YX62RK4/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5GVA6WS5LALUT76JS3YX62RK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5GVA6WS5LALUT76JS3YX62RK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5GVA6WS5LALUT76JS3YX62RK4/action/storage_attestation","attest_author":"https://pith.science/pith/Q5GVA6WS5LALUT76JS3YX62RK4/action/author_attestation","sign_citation":"https://pith.science/pith/Q5GVA6WS5LALUT76JS3YX62RK4/action/citation_signature","submit_replication":"https://pith.science/pith/Q5GVA6WS5LALUT76JS3YX62RK4/action/replication_record"}},"created_at":"2026-07-28T02:24:25.782618+00:00","updated_at":"2026-07-28T02:24:25.782618+00:00"}