{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4HPYHLO5T2QRUJ47WFHXU2JBXV","short_pith_number":"pith:4HPYHLO5","schema_version":"1.0","canonical_sha256":"e1df83addd9ea11a279fb14f7a6921bd61b92512f0fa228bb2c1ab8ad2732aa5","source":{"kind":"arxiv","id":"2408.15270","version":2},"attestation_state":"computed","paper":{"title":"SkillMimic: Learning Basketball Interaction Skills from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Hok Wai Tsui, Jian Zhang, Jing Lin, Jiwen Yu, Lei Zhang, Ping Tan, Qifeng Chen, Qihan Zhao, Runyi Yu, Xiu Li, Yinhuai Wang, Zhengyi Luo","submitted_at":"2024-08-12T15:19:04Z","abstract_excerpt":"Traditional reinforcement learning methods for human-object interaction (HOI) rely on labor-intensive, manually designed skill rewards that do not generalize well across different interactions. We introduce SkillMimic, a unified data-driven framework that fundamentally changes how agents learn interaction skills by eliminating the need for skill-specific rewards. Our key insight is that a unified HOI imitation reward can effectively capture the essence of diverse interaction patterns from HOI datasets. This enables SkillMimic to learn a single policy that not only masters multiple interaction "},"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":"2408.15270","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-12T15:19:04Z","cross_cats_sorted":["cs.GR","cs.LG","cs.RO"],"title_canon_sha256":"dcffe9e5b87216db7fe1eac3662d452234c1f7382dafc29715591c7c677fbd12","abstract_canon_sha256":"7383ca97a366a751ea4fe867b04caea52d57843626c0c0693fd509675c5bce3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:35.338755Z","signature_b64":"uxfuPpdIMzQpXIH3bcGzByO4z6pkVarHBexX2lSH2mBKBbrU9h6bIRfiIdotuIR1KCcWy/zyNgn7BgN29qXZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1df83addd9ea11a279fb14f7a6921bd61b92512f0fa228bb2c1ab8ad2732aa5","last_reissued_at":"2026-07-05T10:40:35.338212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:35.338212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkillMimic: Learning Basketball Interaction Skills from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Hok Wai Tsui, Jian Zhang, Jing Lin, Jiwen Yu, Lei Zhang, Ping Tan, Qifeng Chen, Qihan Zhao, Runyi Yu, Xiu Li, Yinhuai Wang, Zhengyi Luo","submitted_at":"2024-08-12T15:19:04Z","abstract_excerpt":"Traditional reinforcement learning methods for human-object interaction (HOI) rely on labor-intensive, manually designed skill rewards that do not generalize well across different interactions. We introduce SkillMimic, a unified data-driven framework that fundamentally changes how agents learn interaction skills by eliminating the need for skill-specific rewards. Our key insight is that a unified HOI imitation reward can effectively capture the essence of diverse interaction patterns from HOI datasets. This enables SkillMimic to learn a single policy that not only masters multiple interaction "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15270","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/2408.15270/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":"2408.15270","created_at":"2026-07-05T10:40:35.338278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15270v2","created_at":"2026-07-05T10:40:35.338278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15270","created_at":"2026-07-05T10:40:35.338278+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HPYHLO5T2QR","created_at":"2026-07-05T10:40:35.338278+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HPYHLO5T2QRUJ47","created_at":"2026-07-05T10:40:35.338278+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HPYHLO5","created_at":"2026-07-05T10:40:35.338278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09366","citing_title":"SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HPYHLO5T2QRUJ47WFHXU2JBXV","json":"https://pith.science/pith/4HPYHLO5T2QRUJ47WFHXU2JBXV.json","graph_json":"https://pith.science/api/pith-number/4HPYHLO5T2QRUJ47WFHXU2JBXV/graph.json","events_json":"https://pith.science/api/pith-number/4HPYHLO5T2QRUJ47WFHXU2JBXV/events.json","paper":"https://pith.science/paper/4HPYHLO5"},"agent_actions":{"view_html":"https://pith.science/pith/4HPYHLO5T2QRUJ47WFHXU2JBXV","download_json":"https://pith.science/pith/4HPYHLO5T2QRUJ47WFHXU2JBXV.json","view_paper":"https://pith.science/paper/4HPYHLO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15270&json=true","fetch_graph":"https://pith.science/api/pith-number/4HPYHLO5T2QRUJ47WFHXU2JBXV/graph.json","fetch_events":"https://pith.science/api/pith-number/4HPYHLO5T2QRUJ47WFHXU2JBXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HPYHLO5T2QRUJ47WFHXU2JBXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HPYHLO5T2QRUJ47WFHXU2JBXV/action/storage_attestation","attest_author":"https://pith.science/pith/4HPYHLO5T2QRUJ47WFHXU2JBXV/action/author_attestation","sign_citation":"https://pith.science/pith/4HPYHLO5T2QRUJ47WFHXU2JBXV/action/citation_signature","submit_replication":"https://pith.science/pith/4HPYHLO5T2QRUJ47WFHXU2JBXV/action/replication_record"}},"created_at":"2026-07-05T10:40:35.338278+00:00","updated_at":"2026-07-05T10:40:35.338278+00:00"}