{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ERNQCBLFFJI4DLC22B46IY5BAB","short_pith_number":"pith:ERNQCBLF","schema_version":"1.0","canonical_sha256":"245b0105652a51c1ac5ad079e463a1005eefbf8b90577051f5eafee50afb235f","source":{"kind":"arxiv","id":"2104.01542","version":2},"attestation_state":"computed","paper":{"title":"Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Kuan Fang, Maxwell Svetlik, Yifeng Zhu, Yuke Zhu, Zhenyu Jiang","submitted_at":"2021-04-04T05:46:37Z","abstract_excerpt":"Grasp detection in clutter requires the robot to reason about the 3D scene from incomplete and noisy perception. In this work, we draw insight that 3D reconstruction and grasp learning are two intimately connected tasks, both of which require a fine-grained understanding of local geometry details. We thus propose to utilize the synergies between grasp affordance and 3D reconstruction through multi-task learning of a shared representation. Our model takes advantage of deep implicit functions, a continuous and memory-efficient representation, to enable differentiable training of both tasks. We t"},"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":"2104.01542","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-04-04T05:46:37Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"5ed42cb1e3949f54a974a0fae1a3760f1215bc17b2d9e9751bf854f465c8afce","abstract_canon_sha256":"1227a9fe8db2a32f9a5e98182ad4532854d9bb960ce3627e2598ce810712affc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:47.852783Z","signature_b64":"VoXahcgT0qw2GbakaK4wxs13Q2CfU09QmnUFxY1kYn3dHGNYg2ZMhmJZScRt9M0oVEEZrJOD4iiJA959JYQZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"245b0105652a51c1ac5ad079e463a1005eefbf8b90577051f5eafee50afb235f","last_reissued_at":"2026-07-05T02:59:47.852362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:47.852362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Kuan Fang, Maxwell Svetlik, Yifeng Zhu, Yuke Zhu, Zhenyu Jiang","submitted_at":"2021-04-04T05:46:37Z","abstract_excerpt":"Grasp detection in clutter requires the robot to reason about the 3D scene from incomplete and noisy perception. In this work, we draw insight that 3D reconstruction and grasp learning are two intimately connected tasks, both of which require a fine-grained understanding of local geometry details. We thus propose to utilize the synergies between grasp affordance and 3D reconstruction through multi-task learning of a shared representation. Our model takes advantage of deep implicit functions, a continuous and memory-efficient representation, to enable differentiable training of both tasks. We t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01542","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/2104.01542/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":"2104.01542","created_at":"2026-07-05T02:59:47.852420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01542v2","created_at":"2026-07-05T02:59:47.852420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01542","created_at":"2026-07-05T02:59:47.852420+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERNQCBLFFJI4","created_at":"2026-07-05T02:59:47.852420+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERNQCBLFFJI4DLC2","created_at":"2026-07-05T02:59:47.852420+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERNQCBLF","created_at":"2026-07-05T02:59:47.852420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25503","citing_title":"AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30474","citing_title":"Grasp-Oriented Non-Prehensile Manipulation via Learning a Graspability Field","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2507.18847","citing_title":"Equivariant Volumetric Grasping","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07866","citing_title":"Viewpoint-Agnostic Grasp Pipeline using VLM and Partial Observations","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERNQCBLFFJI4DLC22B46IY5BAB","json":"https://pith.science/pith/ERNQCBLFFJI4DLC22B46IY5BAB.json","graph_json":"https://pith.science/api/pith-number/ERNQCBLFFJI4DLC22B46IY5BAB/graph.json","events_json":"https://pith.science/api/pith-number/ERNQCBLFFJI4DLC22B46IY5BAB/events.json","paper":"https://pith.science/paper/ERNQCBLF"},"agent_actions":{"view_html":"https://pith.science/pith/ERNQCBLFFJI4DLC22B46IY5BAB","download_json":"https://pith.science/pith/ERNQCBLFFJI4DLC22B46IY5BAB.json","view_paper":"https://pith.science/paper/ERNQCBLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01542&json=true","fetch_graph":"https://pith.science/api/pith-number/ERNQCBLFFJI4DLC22B46IY5BAB/graph.json","fetch_events":"https://pith.science/api/pith-number/ERNQCBLFFJI4DLC22B46IY5BAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERNQCBLFFJI4DLC22B46IY5BAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERNQCBLFFJI4DLC22B46IY5BAB/action/storage_attestation","attest_author":"https://pith.science/pith/ERNQCBLFFJI4DLC22B46IY5BAB/action/author_attestation","sign_citation":"https://pith.science/pith/ERNQCBLFFJI4DLC22B46IY5BAB/action/citation_signature","submit_replication":"https://pith.science/pith/ERNQCBLFFJI4DLC22B46IY5BAB/action/replication_record"}},"created_at":"2026-07-05T02:59:47.852420+00:00","updated_at":"2026-07-05T02:59:47.852420+00:00"}