{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PIRXM6NW2YI4T37WZB32XVD762","short_pith_number":"pith:PIRXM6NW","schema_version":"1.0","canonical_sha256":"7a237679b6d611c9eff6c877abd47ff6a3ed580f24daf4be039398597f06435a","source":{"kind":"arxiv","id":"2410.22325","version":2},"attestation_state":"computed","paper":{"title":"Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Guangqi Jiang, Huanyu Li, Huazhe Xu, Tao Huang, Yifei Sun, Yongyuan Liang","submitted_at":"2024-10-29T17:58:13Z","abstract_excerpt":"The pre-training of visual representations has enhanced the efficiency of robot learning. Due to the lack of large-scale in-domain robotic datasets, prior works utilize in-the-wild human videos to pre-train robotic visual representation. Despite their promising results, representations from human videos are inevitably subject to distribution shifts and lack the dynamics information crucial for task completion. We first evaluate various pre-trained representations in terms of their correlation to the downstream robotic manipulation tasks (i.e., manipulation centricity). Interestingly, we find t"},"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":"2410.22325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-29T17:58:13Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"798c8bb4acb2f794858bd148f70192679c1b8a0b78152010225cccdfe069fadd","abstract_canon_sha256":"0ab41836cc1a85d4f486b8feaefecfedd6d5f027968f3e011d77de6ec95a8d4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:14.911989Z","signature_b64":"6XsdclH/N9rPeAkbQ4xofpoCCWrjcx1oFSMlIq73DffQUMgPdvvBd8WEpBiFkjwW/3voKva4Y3WLQ4uSjkewAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a237679b6d611c9eff6c877abd47ff6a3ed580f24daf4be039398597f06435a","last_reissued_at":"2026-07-05T09:28:14.911578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:14.911578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Guangqi Jiang, Huanyu Li, Huazhe Xu, Tao Huang, Yifei Sun, Yongyuan Liang","submitted_at":"2024-10-29T17:58:13Z","abstract_excerpt":"The pre-training of visual representations has enhanced the efficiency of robot learning. Due to the lack of large-scale in-domain robotic datasets, prior works utilize in-the-wild human videos to pre-train robotic visual representation. Despite their promising results, representations from human videos are inevitably subject to distribution shifts and lack the dynamics information crucial for task completion. We first evaluate various pre-trained representations in terms of their correlation to the downstream robotic manipulation tasks (i.e., manipulation centricity). Interestingly, we find t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22325","kind":"arxiv","version":2},"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/2410.22325/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":"2410.22325","created_at":"2026-07-05T09:28:14.911634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22325v2","created_at":"2026-07-05T09:28:14.911634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22325","created_at":"2026-07-05T09:28:14.911634+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIRXM6NW2YI4","created_at":"2026-07-05T09:28:14.911634+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIRXM6NW2YI4T37W","created_at":"2026-07-05T09:28:14.911634+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIRXM6NW","created_at":"2026-07-05T09:28:14.911634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17256","citing_title":"Contrastive Action-Image Pre-training for Visuomotor Control","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12499","citing_title":"Action-Effect Memory Pretraining for Robot Manipulation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2504.14820","citing_title":"A Visual Reinforcement Learning-Based Separate Primitive Policy for Peg-in-Hole Tasks","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09180","citing_title":"Multimodal Fusion for Sim2real Transfer in Visual Reinforcement Learning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10345","citing_title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17800","citing_title":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIRXM6NW2YI4T37WZB32XVD762","json":"https://pith.science/pith/PIRXM6NW2YI4T37WZB32XVD762.json","graph_json":"https://pith.science/api/pith-number/PIRXM6NW2YI4T37WZB32XVD762/graph.json","events_json":"https://pith.science/api/pith-number/PIRXM6NW2YI4T37WZB32XVD762/events.json","paper":"https://pith.science/paper/PIRXM6NW"},"agent_actions":{"view_html":"https://pith.science/pith/PIRXM6NW2YI4T37WZB32XVD762","download_json":"https://pith.science/pith/PIRXM6NW2YI4T37WZB32XVD762.json","view_paper":"https://pith.science/paper/PIRXM6NW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22325&json=true","fetch_graph":"https://pith.science/api/pith-number/PIRXM6NW2YI4T37WZB32XVD762/graph.json","fetch_events":"https://pith.science/api/pith-number/PIRXM6NW2YI4T37WZB32XVD762/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIRXM6NW2YI4T37WZB32XVD762/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIRXM6NW2YI4T37WZB32XVD762/action/storage_attestation","attest_author":"https://pith.science/pith/PIRXM6NW2YI4T37WZB32XVD762/action/author_attestation","sign_citation":"https://pith.science/pith/PIRXM6NW2YI4T37WZB32XVD762/action/citation_signature","submit_replication":"https://pith.science/pith/PIRXM6NW2YI4T37WZB32XVD762/action/replication_record"}},"created_at":"2026-07-05T09:28:14.911634+00:00","updated_at":"2026-07-05T09:28:14.911634+00:00"}