{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3NRW3AODY3AUAQQWG3OMNYZXLP","short_pith_number":"pith:3NRW3AOD","schema_version":"1.0","canonical_sha256":"db636d81c3c6c140421636dcc6e3375be95fcf1fda416d98ab2ad5daec50d46a","source":{"kind":"arxiv","id":"2411.18369","version":3},"attestation_state":"computed","paper":{"title":"G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Hongyuan Zhang, Mingkun Xu, Ping Luo, Qiangyu Chen, Ruizhen Hu, Shijia Peng, Tianxing Chen, Xuelong Li, Yao Mu, Zanxin Chen, Zhixuan Liang","submitted_at":"2024-11-27T14:17:43Z","abstract_excerpt":"Recent advances in imitation learning for 3D robotic manipulation have shown promising results with diffusion-based policies. However, achieving human-level dexterity requires seamless integration of geometric precision and semantic understanding. We present G3Flow, a novel framework that constructs real-time semantic flow, a dynamic, object-centric 3D semantic representation by leveraging foundation models. Our approach uniquely combines 3D generative models for digital twin creation, vision foundation models for semantic feature extraction, and robust pose tracking for continuous semantic fl"},"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":"2411.18369","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T14:17:43Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SY","eess.SY"],"title_canon_sha256":"30d7a00a24a4ea07979d2796e72366816f2dda791dfb82337345bfbeac080cdd","abstract_canon_sha256":"c9fb31bcbd753c453436262d560793e75d87927d619b2630dc70a8472b9e3eb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:05.826081Z","signature_b64":"D+hGEbXMhO3qZd5STJRki+sQMYqi7+e/J4OZUKAIk72iaE65q+/B6pyzb8PPngPE90SCj0vTVhV/fYwMWuHjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db636d81c3c6c140421636dcc6e3375be95fcf1fda416d98ab2ad5daec50d46a","last_reissued_at":"2026-07-05T11:25:05.825600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:05.825600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Hongyuan Zhang, Mingkun Xu, Ping Luo, Qiangyu Chen, Ruizhen Hu, Shijia Peng, Tianxing Chen, Xuelong Li, Yao Mu, Zanxin Chen, Zhixuan Liang","submitted_at":"2024-11-27T14:17:43Z","abstract_excerpt":"Recent advances in imitation learning for 3D robotic manipulation have shown promising results with diffusion-based policies. However, achieving human-level dexterity requires seamless integration of geometric precision and semantic understanding. We present G3Flow, a novel framework that constructs real-time semantic flow, a dynamic, object-centric 3D semantic representation by leveraging foundation models. Our approach uniquely combines 3D generative models for digital twin creation, vision foundation models for semantic feature extraction, and robust pose tracking for continuous semantic fl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18369","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.18369/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":"2411.18369","created_at":"2026-07-05T11:25:05.825657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18369v3","created_at":"2026-07-05T11:25:05.825657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18369","created_at":"2026-07-05T11:25:05.825657+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NRW3AODY3AU","created_at":"2026-07-05T11:25:05.825657+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NRW3AODY3AUAQQW","created_at":"2026-07-05T11:25:05.825657+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NRW3AOD","created_at":"2026-07-05T11:25:05.825657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.14135","citing_title":"GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NRW3AODY3AUAQQWG3OMNYZXLP","json":"https://pith.science/pith/3NRW3AODY3AUAQQWG3OMNYZXLP.json","graph_json":"https://pith.science/api/pith-number/3NRW3AODY3AUAQQWG3OMNYZXLP/graph.json","events_json":"https://pith.science/api/pith-number/3NRW3AODY3AUAQQWG3OMNYZXLP/events.json","paper":"https://pith.science/paper/3NRW3AOD"},"agent_actions":{"view_html":"https://pith.science/pith/3NRW3AODY3AUAQQWG3OMNYZXLP","download_json":"https://pith.science/pith/3NRW3AODY3AUAQQWG3OMNYZXLP.json","view_paper":"https://pith.science/paper/3NRW3AOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18369&json=true","fetch_graph":"https://pith.science/api/pith-number/3NRW3AODY3AUAQQWG3OMNYZXLP/graph.json","fetch_events":"https://pith.science/api/pith-number/3NRW3AODY3AUAQQWG3OMNYZXLP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NRW3AODY3AUAQQWG3OMNYZXLP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NRW3AODY3AUAQQWG3OMNYZXLP/action/storage_attestation","attest_author":"https://pith.science/pith/3NRW3AODY3AUAQQWG3OMNYZXLP/action/author_attestation","sign_citation":"https://pith.science/pith/3NRW3AODY3AUAQQWG3OMNYZXLP/action/citation_signature","submit_replication":"https://pith.science/pith/3NRW3AODY3AUAQQWG3OMNYZXLP/action/replication_record"}},"created_at":"2026-07-05T11:25:05.825657+00:00","updated_at":"2026-07-05T11:25:05.825657+00:00"}