{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CWK6KBKFDVDOK5FMWPDFEKTNBU","short_pith_number":"pith:CWK6KBKF","schema_version":"1.0","canonical_sha256":"1595e505451d46e574acb3c6522a6d0d0c524a4d70178322ddbfd44da7381965","source":{"kind":"arxiv","id":"2510.10642","version":3},"attestation_state":"computed","paper":{"title":"UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chaochao Lu, Jianke Zhang, Jianyu Chen, Wenna Chen, Xiaoyu Chen, Yanjiang Guo, Yichen Liu, Yucheng Hu","submitted_at":"2025-10-12T14:54:19Z","abstract_excerpt":"Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work (VLA) has typically built generalist policies either on top of vision-language understanding models (VLMs) or generative models. However, both semantic understanding from vision-language pretraining and visual dynamics modeling from visual-generation pretraining are crucial for embodied robots. Recent unified models of generation and understanding have demonstrated strong capabilities in both comprehension"},"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":"2510.10642","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-10-12T14:54:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a77607b5fbd7b79e24927a5f0ac95f602d4e33e7613fee65e9955852ee647d01","abstract_canon_sha256":"0c5514559295f6d132b77736e50682468ec0d47495f47e48fec5ac8d15d45851"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:33.983831Z","signature_b64":"rF4TPmm3h07k7nIHa2gIHKDzQLhrtSub+LjR5zt8Kr3PLMM21MeS3zV0AExBZwvD5eoFT/cnD+iffT4q+2HJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1595e505451d46e574acb3c6522a6d0d0c524a4d70178322ddbfd44da7381965","last_reissued_at":"2026-05-18T03:09:33.982972Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:33.982972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chaochao Lu, Jianke Zhang, Jianyu Chen, Wenna Chen, Xiaoyu Chen, Yanjiang Guo, Yichen Liu, Yucheng Hu","submitted_at":"2025-10-12T14:54:19Z","abstract_excerpt":"Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work (VLA) has typically built generalist policies either on top of vision-language understanding models (VLMs) or generative models. However, both semantic understanding from vision-language pretraining and visual dynamics modeling from visual-generation pretraining are crucial for embodied robots. Recent unified models of generation and understanding have demonstrated strong capabilities in both comprehension"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10642","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2510.10642","created_at":"2026-05-18T03:09:33.983110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.10642v3","created_at":"2026-05-18T03:09:33.983110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10642","created_at":"2026-05-18T03:09:33.983110+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWK6KBKFDVDO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWK6KBKFDVDOK5FM","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWK6KBKF","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.15735","citing_title":"UAM: A Dual-Stream Perspective on Forgetting in VLA Training","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04502","citing_title":"Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWK6KBKFDVDOK5FMWPDFEKTNBU","json":"https://pith.science/pith/CWK6KBKFDVDOK5FMWPDFEKTNBU.json","graph_json":"https://pith.science/api/pith-number/CWK6KBKFDVDOK5FMWPDFEKTNBU/graph.json","events_json":"https://pith.science/api/pith-number/CWK6KBKFDVDOK5FMWPDFEKTNBU/events.json","paper":"https://pith.science/paper/CWK6KBKF"},"agent_actions":{"view_html":"https://pith.science/pith/CWK6KBKFDVDOK5FMWPDFEKTNBU","download_json":"https://pith.science/pith/CWK6KBKFDVDOK5FMWPDFEKTNBU.json","view_paper":"https://pith.science/paper/CWK6KBKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.10642&json=true","fetch_graph":"https://pith.science/api/pith-number/CWK6KBKFDVDOK5FMWPDFEKTNBU/graph.json","fetch_events":"https://pith.science/api/pith-number/CWK6KBKFDVDOK5FMWPDFEKTNBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWK6KBKFDVDOK5FMWPDFEKTNBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWK6KBKFDVDOK5FMWPDFEKTNBU/action/storage_attestation","attest_author":"https://pith.science/pith/CWK6KBKFDVDOK5FMWPDFEKTNBU/action/author_attestation","sign_citation":"https://pith.science/pith/CWK6KBKFDVDOK5FMWPDFEKTNBU/action/citation_signature","submit_replication":"https://pith.science/pith/CWK6KBKFDVDOK5FMWPDFEKTNBU/action/replication_record"}},"created_at":"2026-05-18T03:09:33.983110+00:00","updated_at":"2026-05-18T03:09:33.983110+00:00"}