{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:B3LDLFPRF2PAY2D3M54LWW7JSV","short_pith_number":"pith:B3LDLFPR","schema_version":"1.0","canonical_sha256":"0ed63595f12e9e0c687b6778bb5be9954a3cf5d2ab8eca0870bd9c4846e116c6","source":{"kind":"arxiv","id":"1803.09956","version":3},"attestation_state":"computed","paper":{"title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Alberto Rodriguez, Andy Zeng, Johnny Lee, Shuran Song, Stefan Welker, Thomas Funkhouser","submitted_at":"2018-03-27T08:31:28Z","abstract_excerpt":"Skilled robotic manipulation benefits from complex synergies between non-prehensile (e.g. pushing) and prehensile (e.g. grasping) actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping can help displace objects to make pushing movements more precise and collision-free. In this work, we demonstrate that it is possible to discover and learn these synergies from scratch through model-free deep reinforcement learning. Our method involves training two fully convolutional networks that map from visual observations to actions: one infers the utili"},"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":"1803.09956","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-27T08:31:28Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"f2a593e6694890048e7d4972246c4676d1f98e5f89054e4a4df9b17d0fc02ad3","abstract_canon_sha256":"ddd2c4281a340ba51fad27eb6e75b8e3c0040305847fb857cefe14164615e9b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:30.176596Z","signature_b64":"bRwkPrNdyH+ZK+M9q8cG/LjgJfBUF9uUttOgZpJcKyaVerrvnvKF8FCgsmCd2BqYYoVbSpFbnlEeM0W2DgCLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ed63595f12e9e0c687b6778bb5be9954a3cf5d2ab8eca0870bd9c4846e116c6","last_reissued_at":"2026-05-18T00:04:30.176121Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:30.176121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Alberto Rodriguez, Andy Zeng, Johnny Lee, Shuran Song, Stefan Welker, Thomas Funkhouser","submitted_at":"2018-03-27T08:31:28Z","abstract_excerpt":"Skilled robotic manipulation benefits from complex synergies between non-prehensile (e.g. pushing) and prehensile (e.g. grasping) actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping can help displace objects to make pushing movements more precise and collision-free. In this work, we demonstrate that it is possible to discover and learn these synergies from scratch through model-free deep reinforcement learning. Our method involves training two fully convolutional networks that map from visual observations to actions: one infers the utili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09956","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":"1803.09956","created_at":"2026-05-18T00:04:30.176190+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.09956v3","created_at":"2026-05-18T00:04:30.176190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09956","created_at":"2026-05-18T00:04:30.176190+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3LDLFPRF2PA","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3LDLFPRF2PAY2D3","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3LDLFPR","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1910.11215","citing_title":"RoboNet: Large-Scale Multi-Robot Learning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3LDLFPRF2PAY2D3M54LWW7JSV","json":"https://pith.science/pith/B3LDLFPRF2PAY2D3M54LWW7JSV.json","graph_json":"https://pith.science/api/pith-number/B3LDLFPRF2PAY2D3M54LWW7JSV/graph.json","events_json":"https://pith.science/api/pith-number/B3LDLFPRF2PAY2D3M54LWW7JSV/events.json","paper":"https://pith.science/paper/B3LDLFPR"},"agent_actions":{"view_html":"https://pith.science/pith/B3LDLFPRF2PAY2D3M54LWW7JSV","download_json":"https://pith.science/pith/B3LDLFPRF2PAY2D3M54LWW7JSV.json","view_paper":"https://pith.science/paper/B3LDLFPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.09956&json=true","fetch_graph":"https://pith.science/api/pith-number/B3LDLFPRF2PAY2D3M54LWW7JSV/graph.json","fetch_events":"https://pith.science/api/pith-number/B3LDLFPRF2PAY2D3M54LWW7JSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3LDLFPRF2PAY2D3M54LWW7JSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3LDLFPRF2PAY2D3M54LWW7JSV/action/storage_attestation","attest_author":"https://pith.science/pith/B3LDLFPRF2PAY2D3M54LWW7JSV/action/author_attestation","sign_citation":"https://pith.science/pith/B3LDLFPRF2PAY2D3M54LWW7JSV/action/citation_signature","submit_replication":"https://pith.science/pith/B3LDLFPRF2PAY2D3M54LWW7JSV/action/replication_record"}},"created_at":"2026-05-18T00:04:30.176190+00:00","updated_at":"2026-05-18T00:04:30.176190+00:00"}