{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LOIQW6MA37YPREZ2D6R7RP3LRD","short_pith_number":"pith:LOIQW6MA","schema_version":"1.0","canonical_sha256":"5b910b7980dff0f8933a1fa3f8bf6b88c183ccc6ffbd2b0bde3c48c3bf6f7ac1","source":{"kind":"arxiv","id":"2407.00451","version":3},"attestation_state":"computed","paper":{"title":"Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alois Knoll, Hang Li, Jianxiang Feng, Qian Feng, Zhaopeng Chen, Zhi Zheng","submitted_at":"2024-06-29T14:35:21Z","abstract_excerpt":"Learning from demonstrations faces challenges in generalizing beyond the training data and often lacks collision awareness. This paper introduces Lan-o3dp, a language-guided object-centric diffusion policy framework that can adapt to unseen situations such as cluttered scenes, shifting camera views, and ambiguous similar objects while offering training-free collision avoidance and achieving a high success rate with few demonstrations. We train a diffusion model conditioned on 3D point clouds of task-relevant objects to predict the robot's end-effector trajectories, enabling it to complete the "},"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":"2407.00451","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-29T14:35:21Z","cross_cats_sorted":[],"title_canon_sha256":"942f711e89e2eea1fedec5d5ee365a24085fe7e92f13038792c68f9183edaac3","abstract_canon_sha256":"7c743e46f848875ba0780e05775498e9e05c20a92d01e80dc4d9afb3b08777ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:44.720522Z","signature_b64":"+CbEU/gabt6F4tA5oZSpwG/+2l1tMkve8+1JpZ899PSngxPrx+5Yb5WCy+ae5Clgyk7T/FCdbvx9pcrzC/ICCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b910b7980dff0f8933a1fa3f8bf6b88c183ccc6ffbd2b0bde3c48c3bf6f7ac1","last_reissued_at":"2026-07-05T10:31:44.719724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:44.719724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alois Knoll, Hang Li, Jianxiang Feng, Qian Feng, Zhaopeng Chen, Zhi Zheng","submitted_at":"2024-06-29T14:35:21Z","abstract_excerpt":"Learning from demonstrations faces challenges in generalizing beyond the training data and often lacks collision awareness. This paper introduces Lan-o3dp, a language-guided object-centric diffusion policy framework that can adapt to unseen situations such as cluttered scenes, shifting camera views, and ambiguous similar objects while offering training-free collision avoidance and achieving a high success rate with few demonstrations. We train a diffusion model conditioned on 3D point clouds of task-relevant objects to predict the robot's end-effector trajectories, enabling it to complete the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00451","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/2407.00451/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":"2407.00451","created_at":"2026-07-05T10:31:44.719819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00451v3","created_at":"2026-07-05T10:31:44.719819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00451","created_at":"2026-07-05T10:31:44.719819+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOIQW6MA37YP","created_at":"2026-07-05T10:31:44.719819+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOIQW6MA37YPREZ2","created_at":"2026-07-05T10:31:44.719819+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOIQW6MA","created_at":"2026-07-05T10:31:44.719819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07608","citing_title":"Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2510.00573","citing_title":"GRITS: A Spillage-Aware Guided Diffusion Policy for Robot Food Scooping Tasks","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOIQW6MA37YPREZ2D6R7RP3LRD","json":"https://pith.science/pith/LOIQW6MA37YPREZ2D6R7RP3LRD.json","graph_json":"https://pith.science/api/pith-number/LOIQW6MA37YPREZ2D6R7RP3LRD/graph.json","events_json":"https://pith.science/api/pith-number/LOIQW6MA37YPREZ2D6R7RP3LRD/events.json","paper":"https://pith.science/paper/LOIQW6MA"},"agent_actions":{"view_html":"https://pith.science/pith/LOIQW6MA37YPREZ2D6R7RP3LRD","download_json":"https://pith.science/pith/LOIQW6MA37YPREZ2D6R7RP3LRD.json","view_paper":"https://pith.science/paper/LOIQW6MA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00451&json=true","fetch_graph":"https://pith.science/api/pith-number/LOIQW6MA37YPREZ2D6R7RP3LRD/graph.json","fetch_events":"https://pith.science/api/pith-number/LOIQW6MA37YPREZ2D6R7RP3LRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOIQW6MA37YPREZ2D6R7RP3LRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOIQW6MA37YPREZ2D6R7RP3LRD/action/storage_attestation","attest_author":"https://pith.science/pith/LOIQW6MA37YPREZ2D6R7RP3LRD/action/author_attestation","sign_citation":"https://pith.science/pith/LOIQW6MA37YPREZ2D6R7RP3LRD/action/citation_signature","submit_replication":"https://pith.science/pith/LOIQW6MA37YPREZ2D6R7RP3LRD/action/replication_record"}},"created_at":"2026-07-05T10:31:44.719819+00:00","updated_at":"2026-07-05T10:31:44.719819+00:00"}