{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LTHXE24VRTZD7YYRY7SZKGLJQ4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5013fa3a006244aa1f9c3b7117ee3b5a951b8f539b6dcc50b181ca7772a6dcf3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-21T02:53:17Z","title_canon_sha256":"48ffa0c8d2b1c7c0fca2bca523a3b86d1ecb0508e6327773789483f48cdb2669"},"schema_version":"1.0","source":{"id":"2504.14820","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14820","created_at":"2026-05-20T00:02:49Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14820v2","created_at":"2026-05-20T00:02:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14820","created_at":"2026-05-20T00:02:49Z"},{"alias_kind":"pith_short_12","alias_value":"LTHXE24VRTZD","created_at":"2026-05-20T00:02:49Z"},{"alias_kind":"pith_short_16","alias_value":"LTHXE24VRTZD7YYR","created_at":"2026-05-20T00:02:49Z"},{"alias_kind":"pith_short_8","alias_value":"LTHXE24V","created_at":"2026-05-20T00:02:49Z"}],"graph_snapshots":[{"event_id":"sha256:93bc1e55f9c08f6d858f2ff6f7b9a505be6512861fb5c83bb675fdf9870a175e","target":"graph","created_at":"2026-05-20T00:02:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.14820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For peg-in-hole tasks, humans rely on binocular visual perception to locate the peg above the hole surface and then proceed with insertion. This paper draws insights from this behavior to enable agents to learn efficient assembly strategies through visual reinforcement learning. Hence, we propose a Separate Primitive Policy (S2P) to learn how to derive location and insertion actions simultaneously. S2P is compatible with model-free reinforcement learning algorithms. Ten insertion tasks featuring different polygons are developed as benchmarks for evaluations. Simulation experiments show that S2","authors_text":"Guocai Yang, Jingdong Zhao, Lei Zhuang, Yuntao Li, Zhaomin Wang, Zhiyuan Zhao, Zichun Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-21T02:53:17Z","title":"A Visual Reinforcement Learning-Based Separate Primitive Policy for Peg-in-Hole Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14820","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:42bc432f5f5d228a7a64d28d7fb469e2483cff8eb4879e29a3b9886df9ba9279","target":"record","created_at":"2026-05-20T00:02:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5013fa3a006244aa1f9c3b7117ee3b5a951b8f539b6dcc50b181ca7772a6dcf3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-21T02:53:17Z","title_canon_sha256":"48ffa0c8d2b1c7c0fca2bca523a3b86d1ecb0508e6327773789483f48cdb2669"},"schema_version":"1.0","source":{"id":"2504.14820","kind":"arxiv","version":2}},"canonical_sha256":"5ccf726b958cf23fe311c7e5951969871d29c488366e54cbc61cef5b8e565923","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ccf726b958cf23fe311c7e5951969871d29c488366e54cbc61cef5b8e565923","first_computed_at":"2026-05-20T00:02:49.651875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:49.651875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h4KHGoXWIidwX675XnegPUFh5Un+0DFXTKHLTyfIVEToHnkhm1CKKhZjUypro9QmFanHWi3oVIQPbD1hEYsVDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:49.652691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14820","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42bc432f5f5d228a7a64d28d7fb469e2483cff8eb4879e29a3b9886df9ba9279","sha256:93bc1e55f9c08f6d858f2ff6f7b9a505be6512861fb5c83bb675fdf9870a175e"],"state_sha256":"e5cb5346aa9a63f61a09b996fc52206475e7fddb9b35983ea2259303e6a7d4d5"}