{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M35CMNHQ2RUK6XFBG3BEKLGTTM","short_pith_number":"pith:M35CMNHQ","schema_version":"1.0","canonical_sha256":"66fa2634f0d468af5ca136c2452cd39b3a2ff8f028445cdca3ff73c1a39d5545","source":{"kind":"arxiv","id":"2305.03942","version":5},"attestation_state":"computed","paper":{"title":"HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Bowen Jiang, Chris Paxton, David Held, Fan Yang, Wenxuan Zhou","submitted_at":"2023-05-06T05:55:27Z","abstract_excerpt":"Manipulating objects without grasping them is an essential component of human dexterity, referred to as non-prehensile manipulation. Non-prehensile manipulation may enable more complex interactions with the objects, but also presents challenges in reasoning about gripper-object interactions. In this work, we introduce Hybrid Actor-Critic Maps for Manipulation (HACMan), a reinforcement learning approach for 6D non-prehensile manipulation of objects using point cloud observations. HACMan proposes a temporally-abstracted and spatially-grounded object-centric action representation that consists of"},"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":"2305.03942","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-05-06T05:55:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2abccca031dde168966f1507cc6faacf2348cb97b95cbd8675f523c5be5b5469","abstract_canon_sha256":"f1613bb217995b7c8115c6212b4918e3128bc82c1a38baf681002d894e0d0c69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:49.571841Z","signature_b64":"pblOfLNDr/tVqhQbDwniC5YyleZH4Kmc+S0PchL2Cg2F+qesxg40LgOcbDgxNddQm6Cc42xSx1fIxumLxiWTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66fa2634f0d468af5ca136c2452cd39b3a2ff8f028445cdca3ff73c1a39d5545","last_reissued_at":"2026-07-05T08:43:49.571356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:49.571356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Bowen Jiang, Chris Paxton, David Held, Fan Yang, Wenxuan Zhou","submitted_at":"2023-05-06T05:55:27Z","abstract_excerpt":"Manipulating objects without grasping them is an essential component of human dexterity, referred to as non-prehensile manipulation. Non-prehensile manipulation may enable more complex interactions with the objects, but also presents challenges in reasoning about gripper-object interactions. In this work, we introduce Hybrid Actor-Critic Maps for Manipulation (HACMan), a reinforcement learning approach for 6D non-prehensile manipulation of objects using point cloud observations. HACMan proposes a temporally-abstracted and spatially-grounded object-centric action representation that consists of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03942","kind":"arxiv","version":5},"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/2305.03942/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":"2305.03942","created_at":"2026-07-05T08:43:49.571417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03942v5","created_at":"2026-07-05T08:43:49.571417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03942","created_at":"2026-07-05T08:43:49.571417+00:00"},{"alias_kind":"pith_short_12","alias_value":"M35CMNHQ2RUK","created_at":"2026-07-05T08:43:49.571417+00:00"},{"alias_kind":"pith_short_16","alias_value":"M35CMNHQ2RUK6XFB","created_at":"2026-07-05T08:43:49.571417+00:00"},{"alias_kind":"pith_short_8","alias_value":"M35CMNHQ","created_at":"2026-07-05T08:43:49.571417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21788","citing_title":"Rotation-Aware Point-Cloud Embeddings for Vision-Based In-Hand Reorientation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00937","citing_title":"CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17833","citing_title":"DART: Learning-Enhanced Model Predictive Control for Dual-Arm Non-Prehensile Manipulation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M35CMNHQ2RUK6XFBG3BEKLGTTM","json":"https://pith.science/pith/M35CMNHQ2RUK6XFBG3BEKLGTTM.json","graph_json":"https://pith.science/api/pith-number/M35CMNHQ2RUK6XFBG3BEKLGTTM/graph.json","events_json":"https://pith.science/api/pith-number/M35CMNHQ2RUK6XFBG3BEKLGTTM/events.json","paper":"https://pith.science/paper/M35CMNHQ"},"agent_actions":{"view_html":"https://pith.science/pith/M35CMNHQ2RUK6XFBG3BEKLGTTM","download_json":"https://pith.science/pith/M35CMNHQ2RUK6XFBG3BEKLGTTM.json","view_paper":"https://pith.science/paper/M35CMNHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03942&json=true","fetch_graph":"https://pith.science/api/pith-number/M35CMNHQ2RUK6XFBG3BEKLGTTM/graph.json","fetch_events":"https://pith.science/api/pith-number/M35CMNHQ2RUK6XFBG3BEKLGTTM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M35CMNHQ2RUK6XFBG3BEKLGTTM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M35CMNHQ2RUK6XFBG3BEKLGTTM/action/storage_attestation","attest_author":"https://pith.science/pith/M35CMNHQ2RUK6XFBG3BEKLGTTM/action/author_attestation","sign_citation":"https://pith.science/pith/M35CMNHQ2RUK6XFBG3BEKLGTTM/action/citation_signature","submit_replication":"https://pith.science/pith/M35CMNHQ2RUK6XFBG3BEKLGTTM/action/replication_record"}},"created_at":"2026-07-05T08:43:49.571417+00:00","updated_at":"2026-07-05T08:43:49.571417+00:00"}