{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EO3GOGK7FPFPMA6WA6AWGMG5W6","short_pith_number":"pith:EO3GOGK7","schema_version":"1.0","canonical_sha256":"23b667195f2bcaf603d607816330ddb7867d92b20d6f091e7056e57e8e0b4458","source":{"kind":"arxiv","id":"2307.12074","version":1},"attestation_state":"computed","paper":{"title":"Multi-Stage Reinforcement Learning for Non-Prehensile Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chunsheng Liu, Dexin Wang, Faliang Chang","submitted_at":"2023-07-22T13:29:40Z","abstract_excerpt":"Manipulating objects without grasping them enables more complex tasks, known as non-prehensile manipulation. Most previous methods only learn one manipulation skill, such as reach or push, and cannot achieve flexible object manipulation.In this work, we introduce MRLM, a Multi-stage Reinforcement Learning approach for non-prehensile Manipulation of objects.MRLM divides the task into multiple stages according to the switching of object poses and contact points.At each stage, the policy takes the point cloud-based state-goal fusion representation as input, and proposes a spatially-continuous act"},"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":"2307.12074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-22T13:29:40Z","cross_cats_sorted":[],"title_canon_sha256":"49095ecbd2fe8941eaea080c05d9f4ba3cd97ba40ba76679ed635e1f16b15c53","abstract_canon_sha256":"d25e594fb279f8c3bda8f35d0d1b0642780024c865da4b2f9b5eacd3528a58d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:49.225034Z","signature_b64":"23afoH+zdjnZKP/78BehXYuoQSf8o5fg0+CZDh0ktSVe2Bh4oV/+2IzdCcDXIN1ZRW+uJgSGBZb1XdvO3oEeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23b667195f2bcaf603d607816330ddb7867d92b20d6f091e7056e57e8e0b4458","last_reissued_at":"2026-07-05T06:33:49.224566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:49.224566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Stage Reinforcement Learning for Non-Prehensile Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chunsheng Liu, Dexin Wang, Faliang Chang","submitted_at":"2023-07-22T13:29:40Z","abstract_excerpt":"Manipulating objects without grasping them enables more complex tasks, known as non-prehensile manipulation. Most previous methods only learn one manipulation skill, such as reach or push, and cannot achieve flexible object manipulation.In this work, we introduce MRLM, a Multi-stage Reinforcement Learning approach for non-prehensile Manipulation of objects.MRLM divides the task into multiple stages according to the switching of object poses and contact points.At each stage, the policy takes the point cloud-based state-goal fusion representation as input, and proposes a spatially-continuous act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12074","kind":"arxiv","version":1},"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/2307.12074/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":"2307.12074","created_at":"2026-07-05T06:33:49.224623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12074v1","created_at":"2026-07-05T06:33:49.224623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12074","created_at":"2026-07-05T06:33:49.224623+00:00"},{"alias_kind":"pith_short_12","alias_value":"EO3GOGK7FPFP","created_at":"2026-07-05T06:33:49.224623+00:00"},{"alias_kind":"pith_short_16","alias_value":"EO3GOGK7FPFPMA6W","created_at":"2026-07-05T06:33:49.224623+00:00"},{"alias_kind":"pith_short_8","alias_value":"EO3GOGK7","created_at":"2026-07-05T06:33:49.224623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02976","citing_title":"Physics-informed Neural Time Fields for Prehensile Object Manipulation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EO3GOGK7FPFPMA6WA6AWGMG5W6","json":"https://pith.science/pith/EO3GOGK7FPFPMA6WA6AWGMG5W6.json","graph_json":"https://pith.science/api/pith-number/EO3GOGK7FPFPMA6WA6AWGMG5W6/graph.json","events_json":"https://pith.science/api/pith-number/EO3GOGK7FPFPMA6WA6AWGMG5W6/events.json","paper":"https://pith.science/paper/EO3GOGK7"},"agent_actions":{"view_html":"https://pith.science/pith/EO3GOGK7FPFPMA6WA6AWGMG5W6","download_json":"https://pith.science/pith/EO3GOGK7FPFPMA6WA6AWGMG5W6.json","view_paper":"https://pith.science/paper/EO3GOGK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12074&json=true","fetch_graph":"https://pith.science/api/pith-number/EO3GOGK7FPFPMA6WA6AWGMG5W6/graph.json","fetch_events":"https://pith.science/api/pith-number/EO3GOGK7FPFPMA6WA6AWGMG5W6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EO3GOGK7FPFPMA6WA6AWGMG5W6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EO3GOGK7FPFPMA6WA6AWGMG5W6/action/storage_attestation","attest_author":"https://pith.science/pith/EO3GOGK7FPFPMA6WA6AWGMG5W6/action/author_attestation","sign_citation":"https://pith.science/pith/EO3GOGK7FPFPMA6WA6AWGMG5W6/action/citation_signature","submit_replication":"https://pith.science/pith/EO3GOGK7FPFPMA6WA6AWGMG5W6/action/replication_record"}},"created_at":"2026-07-05T06:33:49.224623+00:00","updated_at":"2026-07-05T06:33:49.224623+00:00"}