{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q5JAA7LSLHXV2KWVZS3SH5JWLI","short_pith_number":"pith:Q5JAA7LS","schema_version":"1.0","canonical_sha256":"8752007d7259ef5d2ad5ccb723f5365a2c9d197ca636455ca51de0788a473e0b","source":{"kind":"arxiv","id":"2508.11898","version":1},"attestation_state":"computed","paper":{"title":"OmniD: Generalizable Robot Manipulation Policy via Image-Based BEV Representation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiarui Guan, Jilei Mao, Junjie Yu, Qirui Hu, Shuang Liu, Xiaozhu Ju, Yingjuan Tang, Yongjie Mao, Yunzhe Sun, Zhihang Li","submitted_at":"2025-08-16T04:02:53Z","abstract_excerpt":"The visuomotor policy can easily overfit to its training datasets, such as fixed camera positions and backgrounds. This overfitting makes the policy perform well in the in-distribution scenarios but underperform in the out-of-distribution generalization. Additionally, the existing methods also have difficulty fusing multi-view information to generate an effective 3D representation. To tackle these issues, we propose Omni-Vision Diffusion Policy (OmniD), a multi-view fusion framework that synthesizes image observations into a unified bird's-eye view (BEV) representation. We introduce a deformab"},"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":"2508.11898","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-16T04:02:53Z","cross_cats_sorted":[],"title_canon_sha256":"d319c666d1df12a62566bbc77fadc644c19848489ef22290068dab8b74bcb957","abstract_canon_sha256":"a86fc46b01f9ae6b2878482f09ca7454ba4a37cb78d4a558d92beaf5644a3075"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:56.715504Z","signature_b64":"Mn107yfJat26sHug3HvtVA0kmzVxySGvluwV0BNoxa0Pdn4sq2YhxJEPCf5tnIqvGGLoISPYKoD5rJqudDJOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8752007d7259ef5d2ad5ccb723f5365a2c9d197ca636455ca51de0788a473e0b","last_reissued_at":"2026-07-05T11:54:56.714920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:56.714920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniD: Generalizable Robot Manipulation Policy via Image-Based BEV Representation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiarui Guan, Jilei Mao, Junjie Yu, Qirui Hu, Shuang Liu, Xiaozhu Ju, Yingjuan Tang, Yongjie Mao, Yunzhe Sun, Zhihang Li","submitted_at":"2025-08-16T04:02:53Z","abstract_excerpt":"The visuomotor policy can easily overfit to its training datasets, such as fixed camera positions and backgrounds. This overfitting makes the policy perform well in the in-distribution scenarios but underperform in the out-of-distribution generalization. Additionally, the existing methods also have difficulty fusing multi-view information to generate an effective 3D representation. To tackle these issues, we propose Omni-Vision Diffusion Policy (OmniD), a multi-view fusion framework that synthesizes image observations into a unified bird's-eye view (BEV) representation. We introduce a deformab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11898","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/2508.11898/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":"2508.11898","created_at":"2026-07-05T11:54:56.714986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11898v1","created_at":"2026-07-05T11:54:56.714986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11898","created_at":"2026-07-05T11:54:56.714986+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5JAA7LSLHXV","created_at":"2026-07-05T11:54:56.714986+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5JAA7LSLHXV2KWV","created_at":"2026-07-05T11:54:56.714986+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5JAA7LS","created_at":"2026-07-05T11:54:56.714986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11894","citing_title":"QuarkMed Medical Foundation Model Technical Report","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5JAA7LSLHXV2KWVZS3SH5JWLI","json":"https://pith.science/pith/Q5JAA7LSLHXV2KWVZS3SH5JWLI.json","graph_json":"https://pith.science/api/pith-number/Q5JAA7LSLHXV2KWVZS3SH5JWLI/graph.json","events_json":"https://pith.science/api/pith-number/Q5JAA7LSLHXV2KWVZS3SH5JWLI/events.json","paper":"https://pith.science/paper/Q5JAA7LS"},"agent_actions":{"view_html":"https://pith.science/pith/Q5JAA7LSLHXV2KWVZS3SH5JWLI","download_json":"https://pith.science/pith/Q5JAA7LSLHXV2KWVZS3SH5JWLI.json","view_paper":"https://pith.science/paper/Q5JAA7LS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11898&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5JAA7LSLHXV2KWVZS3SH5JWLI/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5JAA7LSLHXV2KWVZS3SH5JWLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5JAA7LSLHXV2KWVZS3SH5JWLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5JAA7LSLHXV2KWVZS3SH5JWLI/action/storage_attestation","attest_author":"https://pith.science/pith/Q5JAA7LSLHXV2KWVZS3SH5JWLI/action/author_attestation","sign_citation":"https://pith.science/pith/Q5JAA7LSLHXV2KWVZS3SH5JWLI/action/citation_signature","submit_replication":"https://pith.science/pith/Q5JAA7LSLHXV2KWVZS3SH5JWLI/action/replication_record"}},"created_at":"2026-07-05T11:54:56.714986+00:00","updated_at":"2026-07-05T11:54:56.714986+00:00"}