{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7KMITY63WSHBZSVUARHLOHVD4H","short_pith_number":"pith:7KMITY63","schema_version":"1.0","canonical_sha256":"fa9889e3dbb48e1ccab4044eb71ea3e1cd05445fcab9c5783320f8ba9bf6855f","source":{"kind":"arxiv","id":"2506.19269","version":2},"attestation_state":"computed","paper":{"title":"AnchorDP3: 3D Affordance Guided Sparse Diffusion Policy for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bo Peng, Dongjiang Li, He-Yang Xu, Hui Shen, Ke Fan, Ning Qiao, Wenlong Gao, Ziyan Zhao","submitted_at":"2025-06-24T03:03:26Z","abstract_excerpt":"We present AnchorDP3, a diffusion policy framework for dual-arm robotic manipulation that achieves state-of-the-art performance in highly randomized environments. AnchorDP3 integrates three key innovations: (1) Simulator-Supervised Semantic Segmentation, using rendered ground truth to explicitly segment task-critical objects within the point cloud, which provides strong affordance priors; (2) Task-Conditioned Feature Encoders, lightweight modules processing augmented point clouds per task, enabling efficient multi-task learning through a shared diffusion-based action expert; (3) Affordance-Anc"},"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":"2506.19269","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-24T03:03:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85d1c9c5b5a13959b740eee610bf08445f76caeda8ec78bf4f4ea70f96a88c68","abstract_canon_sha256":"169de7b107324ef1bbc383ec11c56cb6f3cabef2bb85756052531a7bdfee48d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:53.920615Z","signature_b64":"bMAxKaIoW/3q9GNvfTX8tEn4DdPyQyjkQb+0nPvFjkTcbE1dsB6MWOTFPB784yYmiC5V2AKU2uARE94l+sWnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa9889e3dbb48e1ccab4044eb71ea3e1cd05445fcab9c5783320f8ba9bf6855f","last_reissued_at":"2026-07-05T11:26:53.920117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:53.920117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnchorDP3: 3D Affordance Guided Sparse Diffusion Policy for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bo Peng, Dongjiang Li, He-Yang Xu, Hui Shen, Ke Fan, Ning Qiao, Wenlong Gao, Ziyan Zhao","submitted_at":"2025-06-24T03:03:26Z","abstract_excerpt":"We present AnchorDP3, a diffusion policy framework for dual-arm robotic manipulation that achieves state-of-the-art performance in highly randomized environments. AnchorDP3 integrates three key innovations: (1) Simulator-Supervised Semantic Segmentation, using rendered ground truth to explicitly segment task-critical objects within the point cloud, which provides strong affordance priors; (2) Task-Conditioned Feature Encoders, lightweight modules processing augmented point clouds per task, enabling efficient multi-task learning through a shared diffusion-based action expert; (3) Affordance-Anc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19269","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/2506.19269/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":"2506.19269","created_at":"2026-07-05T11:26:53.920176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19269v2","created_at":"2026-07-05T11:26:53.920176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19269","created_at":"2026-07-05T11:26:53.920176+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KMITY63WSHB","created_at":"2026-07-05T11:26:53.920176+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KMITY63WSHBZSVU","created_at":"2026-07-05T11:26:53.920176+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KMITY63","created_at":"2026-07-05T11:26:53.920176+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15281","citing_title":"R3D: Revisiting 3D Policy Learning","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7KMITY63WSHBZSVUARHLOHVD4H","json":"https://pith.science/pith/7KMITY63WSHBZSVUARHLOHVD4H.json","graph_json":"https://pith.science/api/pith-number/7KMITY63WSHBZSVUARHLOHVD4H/graph.json","events_json":"https://pith.science/api/pith-number/7KMITY63WSHBZSVUARHLOHVD4H/events.json","paper":"https://pith.science/paper/7KMITY63"},"agent_actions":{"view_html":"https://pith.science/pith/7KMITY63WSHBZSVUARHLOHVD4H","download_json":"https://pith.science/pith/7KMITY63WSHBZSVUARHLOHVD4H.json","view_paper":"https://pith.science/paper/7KMITY63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19269&json=true","fetch_graph":"https://pith.science/api/pith-number/7KMITY63WSHBZSVUARHLOHVD4H/graph.json","fetch_events":"https://pith.science/api/pith-number/7KMITY63WSHBZSVUARHLOHVD4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KMITY63WSHBZSVUARHLOHVD4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KMITY63WSHBZSVUARHLOHVD4H/action/storage_attestation","attest_author":"https://pith.science/pith/7KMITY63WSHBZSVUARHLOHVD4H/action/author_attestation","sign_citation":"https://pith.science/pith/7KMITY63WSHBZSVUARHLOHVD4H/action/citation_signature","submit_replication":"https://pith.science/pith/7KMITY63WSHBZSVUARHLOHVD4H/action/replication_record"}},"created_at":"2026-07-05T11:26:53.920176+00:00","updated_at":"2026-07-05T11:26:53.920176+00:00"}