{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:R2OHHUETN24GW424OQACJM7PO3","short_pith_number":"pith:R2OHHUET","schema_version":"1.0","canonical_sha256":"8e9c73d0936eb86b735c740024b3ef76cf18d4ca589a026b1971e885974ecf29","source":{"kind":"arxiv","id":"1703.09312","version":3},"attestation_state":"computed","paper":{"title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jacky Liang, Jeffrey Mahler, Juan Aparicio Ojea, Ken Goldberg, Michael Laskey, Richard Doan, Sherdil Niyaz, Xinyu Liu","submitted_at":"2017-03-27T21:16:30Z","abstract_excerpt":"To reduce data collection time for deep learning of robust robotic grasp plans, we explore training from a synthetic dataset of 6.7 million point clouds, grasps, and analytic grasp metrics generated from thousands of 3D models from Dex-Net 1.0 in randomized poses on a table. We use the resulting dataset, Dex-Net 2.0, to train a Grasp Quality Convolutional Neural Network (GQ-CNN) model that rapidly predicts the probability of success of grasps from depth images, where grasps are specified as the planar position, angle, and depth of a gripper relative to an RGB-D sensor. Experiments with over 1,"},"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":"1703.09312","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-27T21:16:30Z","cross_cats_sorted":[],"title_canon_sha256":"a00e761f962e8ac7485141fbbcc4038b0bfe262904c8b964e509015f86263a61","abstract_canon_sha256":"95f332fd95626587dab3c8a727bb26c2f3b03839c72340f4077b797c117ec36a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:20.839645Z","signature_b64":"Y9grM6M8Kt2esojvZs+z57+VFWhy2xpSHjRYY4ddI8Iu4MYq4myO3hGCxa1xhhPRYqQrS7v8kWaC/Xo0JmgnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e9c73d0936eb86b735c740024b3ef76cf18d4ca589a026b1971e885974ecf29","last_reissued_at":"2026-05-18T00:38:20.838786Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:20.838786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jacky Liang, Jeffrey Mahler, Juan Aparicio Ojea, Ken Goldberg, Michael Laskey, Richard Doan, Sherdil Niyaz, Xinyu Liu","submitted_at":"2017-03-27T21:16:30Z","abstract_excerpt":"To reduce data collection time for deep learning of robust robotic grasp plans, we explore training from a synthetic dataset of 6.7 million point clouds, grasps, and analytic grasp metrics generated from thousands of 3D models from Dex-Net 1.0 in randomized poses on a table. We use the resulting dataset, Dex-Net 2.0, to train a Grasp Quality Convolutional Neural Network (GQ-CNN) model that rapidly predicts the probability of success of grasps from depth images, where grasps are specified as the planar position, angle, and depth of a gripper relative to an RGB-D sensor. Experiments with over 1,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.09312","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":""},"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":"1703.09312","created_at":"2026-05-18T00:38:20.838895+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.09312v3","created_at":"2026-05-18T00:38:20.838895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.09312","created_at":"2026-05-18T00:38:20.838895+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2OHHUETN24G","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2OHHUETN24GW424","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2OHHUET","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1907.10932","citing_title":"Object Perception and Grasping in Open-Ended Domains","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2210.00379","citing_title":"NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)","ref_index":155,"is_internal_anchor":true},{"citing_arxiv_id":"2504.16054","citing_title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21414","citing_title":"PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21460","citing_title":"HITL-D: Human In The Loop Diffusion Assisted Shared Control","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2505.03233","citing_title":"GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2OHHUETN24GW424OQACJM7PO3","json":"https://pith.science/pith/R2OHHUETN24GW424OQACJM7PO3.json","graph_json":"https://pith.science/api/pith-number/R2OHHUETN24GW424OQACJM7PO3/graph.json","events_json":"https://pith.science/api/pith-number/R2OHHUETN24GW424OQACJM7PO3/events.json","paper":"https://pith.science/paper/R2OHHUET"},"agent_actions":{"view_html":"https://pith.science/pith/R2OHHUETN24GW424OQACJM7PO3","download_json":"https://pith.science/pith/R2OHHUETN24GW424OQACJM7PO3.json","view_paper":"https://pith.science/paper/R2OHHUET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.09312&json=true","fetch_graph":"https://pith.science/api/pith-number/R2OHHUETN24GW424OQACJM7PO3/graph.json","fetch_events":"https://pith.science/api/pith-number/R2OHHUETN24GW424OQACJM7PO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2OHHUETN24GW424OQACJM7PO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2OHHUETN24GW424OQACJM7PO3/action/storage_attestation","attest_author":"https://pith.science/pith/R2OHHUETN24GW424OQACJM7PO3/action/author_attestation","sign_citation":"https://pith.science/pith/R2OHHUETN24GW424OQACJM7PO3/action/citation_signature","submit_replication":"https://pith.science/pith/R2OHHUETN24GW424OQACJM7PO3/action/replication_record"}},"created_at":"2026-05-18T00:38:20.838895+00:00","updated_at":"2026-05-18T00:38:20.838895+00:00"}