{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IKI67XGSCV7LOJWYQF56FZFNOG","short_pith_number":"pith:IKI67XGS","schema_version":"1.0","canonical_sha256":"4291efdcd2157eb726d8817be2e4ad718cb23b21cedb5d544a920cf792e0783b","source":{"kind":"arxiv","id":"2407.18902","version":2},"attestation_state":"computed","paper":{"title":"Lessons from Learning to Spin \"Pens\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Haichuan Che, Haozhi Qi, Jitendra Malik, Jun Wang, Xiaolong Wang, Yi Ma, Ying Yuan","submitted_at":"2024-07-26T17:56:01Z","abstract_excerpt":"In-hand manipulation of pen-like objects is an important skill in our daily lives, as many tools such as hammers and screwdrivers are similarly shaped. However, current learning-based methods struggle with this task due to a lack of high-quality demonstrations and the significant gap between simulation and the real world. In this work, we push the boundaries of learning-based in-hand manipulation systems by demonstrating the capability to spin pen-like objects. We first use reinforcement learning to train an oracle policy with privileged information and generate a high-fidelity trajectory data"},"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":"2407.18902","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-07-26T17:56:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e299e0ff27f7767197fd852f0255a9229d84d003e65452310430963f1956e5ac","abstract_canon_sha256":"1b83a91c1eee2f2bc893052f461b112b420bccc671571d20df4197d813dfa702"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:00.156703Z","signature_b64":"hlaSGOCy4o2ZP2XZ/azqLUeIfjHQswRYeA9nT0+pENfU8aanoin3i3xsIWEEMLjhhsZfqQJ7FBGp6K5h2sg9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4291efdcd2157eb726d8817be2e4ad718cb23b21cedb5d544a920cf792e0783b","last_reissued_at":"2026-07-05T09:25:00.156219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:00.156219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lessons from Learning to Spin \"Pens\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Haichuan Che, Haozhi Qi, Jitendra Malik, Jun Wang, Xiaolong Wang, Yi Ma, Ying Yuan","submitted_at":"2024-07-26T17:56:01Z","abstract_excerpt":"In-hand manipulation of pen-like objects is an important skill in our daily lives, as many tools such as hammers and screwdrivers are similarly shaped. However, current learning-based methods struggle with this task due to a lack of high-quality demonstrations and the significant gap between simulation and the real world. In this work, we push the boundaries of learning-based in-hand manipulation systems by demonstrating the capability to spin pen-like objects. We first use reinforcement learning to train an oracle policy with privileged information and generate a high-fidelity trajectory data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18902","kind":"arxiv","version":2},"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/2407.18902/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":"2407.18902","created_at":"2026-07-05T09:25:00.156281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18902v2","created_at":"2026-07-05T09:25:00.156281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18902","created_at":"2026-07-05T09:25:00.156281+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKI67XGSCV7L","created_at":"2026-07-05T09:25:00.156281+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKI67XGSCV7LOJWY","created_at":"2026-07-05T09:25:00.156281+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKI67XGS","created_at":"2026-07-05T09:25:00.156281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.16272","citing_title":"TopoRetarget: Interaction-Preserving Retargeting for Dexterous Manipulation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2503.15481","citing_title":"Learning to Play Piano in the Real World","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2602.16712","citing_title":"One Hand to Rule Them All: Canonical Representations for Unified Dexterous Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04539","citing_title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04539","citing_title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20295","citing_title":"ETac: A Lightweight and Efficient Tactile Simulation Framework for Learning Dexterous Manipulation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IKI67XGSCV7LOJWYQF56FZFNOG","json":"https://pith.science/pith/IKI67XGSCV7LOJWYQF56FZFNOG.json","graph_json":"https://pith.science/api/pith-number/IKI67XGSCV7LOJWYQF56FZFNOG/graph.json","events_json":"https://pith.science/api/pith-number/IKI67XGSCV7LOJWYQF56FZFNOG/events.json","paper":"https://pith.science/paper/IKI67XGS"},"agent_actions":{"view_html":"https://pith.science/pith/IKI67XGSCV7LOJWYQF56FZFNOG","download_json":"https://pith.science/pith/IKI67XGSCV7LOJWYQF56FZFNOG.json","view_paper":"https://pith.science/paper/IKI67XGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18902&json=true","fetch_graph":"https://pith.science/api/pith-number/IKI67XGSCV7LOJWYQF56FZFNOG/graph.json","fetch_events":"https://pith.science/api/pith-number/IKI67XGSCV7LOJWYQF56FZFNOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKI67XGSCV7LOJWYQF56FZFNOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKI67XGSCV7LOJWYQF56FZFNOG/action/storage_attestation","attest_author":"https://pith.science/pith/IKI67XGSCV7LOJWYQF56FZFNOG/action/author_attestation","sign_citation":"https://pith.science/pith/IKI67XGSCV7LOJWYQF56FZFNOG/action/citation_signature","submit_replication":"https://pith.science/pith/IKI67XGSCV7LOJWYQF56FZFNOG/action/replication_record"}},"created_at":"2026-07-05T09:25:00.156281+00:00","updated_at":"2026-07-05T09:25:00.156281+00:00"}