{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SOJXSBAVMZDKUC4SXROEVR765Y","short_pith_number":"pith:SOJXSBAV","schema_version":"1.0","canonical_sha256":"93937904156646aa0b92bc5c4ac7feee3f5f6ed33a3ad8ad4ddb8f2be9f6a1d8","source":{"kind":"arxiv","id":"2403.12835","version":1},"attestation_state":"computed","paper":{"title":"AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Jieming Cui, Nian Liu, Siyuan Huang, Tengyu Liu, Yaodong Yang, Yixin Zhu","submitted_at":"2024-03-19T15:41:39Z","abstract_excerpt":"Traditional approaches in physics-based motion generation, centered around imitation learning and reward shaping, often struggle to adapt to new scenarios. To tackle this limitation, we propose AnySkill, a novel hierarchical method that learns physically plausible interactions following open-vocabulary instructions. Our approach begins by developing a set of atomic actions via a low-level controller trained via imitation learning. Upon receiving an open-vocabulary textual instruction, AnySkill employs a high-level policy that selects and integrates these atomic actions to maximize the CLIP sim"},"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":"2403.12835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T15:41:39Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"c7b950b6c151e8096fa7a6e28d3024c13e4eac96b26ff918d68f0c298a03aeb4","abstract_canon_sha256":"2b35002fed8ff9a9ddbefe9d06e249548631f03d813fcad4e3d8bdf2b5a613ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:08.426658Z","signature_b64":"B+axfiC8x0kRjA9aYTV6gEBaX4nMcURYRpFqVCBR/OjAFDdhWnnCneszuJclIqY2EFXJz/wHrZ52+IoW2rzHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93937904156646aa0b92bc5c4ac7feee3f5f6ed33a3ad8ad4ddb8f2be9f6a1d8","last_reissued_at":"2026-07-05T07:58:08.426203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:08.426203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Jieming Cui, Nian Liu, Siyuan Huang, Tengyu Liu, Yaodong Yang, Yixin Zhu","submitted_at":"2024-03-19T15:41:39Z","abstract_excerpt":"Traditional approaches in physics-based motion generation, centered around imitation learning and reward shaping, often struggle to adapt to new scenarios. To tackle this limitation, we propose AnySkill, a novel hierarchical method that learns physically plausible interactions following open-vocabulary instructions. Our approach begins by developing a set of atomic actions via a low-level controller trained via imitation learning. Upon receiving an open-vocabulary textual instruction, AnySkill employs a high-level policy that selects and integrates these atomic actions to maximize the CLIP sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12835","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/2403.12835/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":"2403.12835","created_at":"2026-07-05T07:58:08.426260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12835v1","created_at":"2026-07-05T07:58:08.426260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12835","created_at":"2026-07-05T07:58:08.426260+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOJXSBAVMZDK","created_at":"2026-07-05T07:58:08.426260+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOJXSBAVMZDKUC4S","created_at":"2026-07-05T07:58:08.426260+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOJXSBAV","created_at":"2026-07-05T07:58:08.426260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOJXSBAVMZDKUC4SXROEVR765Y","json":"https://pith.science/pith/SOJXSBAVMZDKUC4SXROEVR765Y.json","graph_json":"https://pith.science/api/pith-number/SOJXSBAVMZDKUC4SXROEVR765Y/graph.json","events_json":"https://pith.science/api/pith-number/SOJXSBAVMZDKUC4SXROEVR765Y/events.json","paper":"https://pith.science/paper/SOJXSBAV"},"agent_actions":{"view_html":"https://pith.science/pith/SOJXSBAVMZDKUC4SXROEVR765Y","download_json":"https://pith.science/pith/SOJXSBAVMZDKUC4SXROEVR765Y.json","view_paper":"https://pith.science/paper/SOJXSBAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12835&json=true","fetch_graph":"https://pith.science/api/pith-number/SOJXSBAVMZDKUC4SXROEVR765Y/graph.json","fetch_events":"https://pith.science/api/pith-number/SOJXSBAVMZDKUC4SXROEVR765Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOJXSBAVMZDKUC4SXROEVR765Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOJXSBAVMZDKUC4SXROEVR765Y/action/storage_attestation","attest_author":"https://pith.science/pith/SOJXSBAVMZDKUC4SXROEVR765Y/action/author_attestation","sign_citation":"https://pith.science/pith/SOJXSBAVMZDKUC4SXROEVR765Y/action/citation_signature","submit_replication":"https://pith.science/pith/SOJXSBAVMZDKUC4SXROEVR765Y/action/replication_record"}},"created_at":"2026-07-05T07:58:08.426260+00:00","updated_at":"2026-07-05T07:58:08.426260+00:00"}