{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LV2QZL25L4HHBYA3YZ7E6ZR247","short_pith_number":"pith:LV2QZL25","schema_version":"1.0","canonical_sha256":"5d750caf5d5f0e70e01bc67e4f663ae7f4584f16cfbdfdb59aa991c423143f9b","source":{"kind":"arxiv","id":"2209.07899","version":3},"attestation_state":"computed","paper":{"title":"Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenhao Li, Georg Martius, Jonas Frey, Marin Vlastelica, Pavel Kolev, Sebastian Blaes","submitted_at":"2022-09-16T12:49:04Z","abstract_excerpt":"Learning diverse skills is one of the main challenges in robotics. To this end, imitation learning approaches have achieved impressive results. These methods require explicitly labeled datasets or assume consistent skill execution to enable learning and active control of individual behaviors, which limits their applicability. In this work, we propose a cooperative adversarial method for obtaining single versatile policies with controllable skill sets from unlabeled datasets containing diverse state transition patterns by maximizing their discriminability. Moreover, we show that by utilizing un"},"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":"2209.07899","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-09-16T12:49:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"65774f2a7f955943b292eaa1f471a984945856914da0ea334b2ea710ce83c9ff","abstract_canon_sha256":"8349f3f4c5b1529ad30afe7d2e4d1b5ea105430ef417396ab298713fcefe41b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:49.356118Z","signature_b64":"B5bsJCx8ADq6AOSPpmA2VUEog5pKZorbu1RFmuIppyPUG6cUOUvwE9TFojUowisA2oyoLflsEW6THWaCM3tTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d750caf5d5f0e70e01bc67e4f663ae7f4584f16cfbdfdb59aa991c423143f9b","last_reissued_at":"2026-07-05T05:40:49.355638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:49.355638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenhao Li, Georg Martius, Jonas Frey, Marin Vlastelica, Pavel Kolev, Sebastian Blaes","submitted_at":"2022-09-16T12:49:04Z","abstract_excerpt":"Learning diverse skills is one of the main challenges in robotics. To this end, imitation learning approaches have achieved impressive results. These methods require explicitly labeled datasets or assume consistent skill execution to enable learning and active control of individual behaviors, which limits their applicability. In this work, we propose a cooperative adversarial method for obtaining single versatile policies with controllable skill sets from unlabeled datasets containing diverse state transition patterns by maximizing their discriminability. Moreover, we show that by utilizing un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07899","kind":"arxiv","version":3},"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/2209.07899/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":"2209.07899","created_at":"2026-07-05T05:40:49.355702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07899v3","created_at":"2026-07-05T05:40:49.355702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07899","created_at":"2026-07-05T05:40:49.355702+00:00"},{"alias_kind":"pith_short_12","alias_value":"LV2QZL25L4HH","created_at":"2026-07-05T05:40:49.355702+00:00"},{"alias_kind":"pith_short_16","alias_value":"LV2QZL25L4HHBYA3","created_at":"2026-07-05T05:40:49.355702+00:00"},{"alias_kind":"pith_short_8","alias_value":"LV2QZL25","created_at":"2026-07-05T05:40:49.355702+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13058","citing_title":"MUJICA: Multi-skill Unified Joint Integration of Control Architecture for Wheeled-Legged Robots","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LV2QZL25L4HHBYA3YZ7E6ZR247","json":"https://pith.science/pith/LV2QZL25L4HHBYA3YZ7E6ZR247.json","graph_json":"https://pith.science/api/pith-number/LV2QZL25L4HHBYA3YZ7E6ZR247/graph.json","events_json":"https://pith.science/api/pith-number/LV2QZL25L4HHBYA3YZ7E6ZR247/events.json","paper":"https://pith.science/paper/LV2QZL25"},"agent_actions":{"view_html":"https://pith.science/pith/LV2QZL25L4HHBYA3YZ7E6ZR247","download_json":"https://pith.science/pith/LV2QZL25L4HHBYA3YZ7E6ZR247.json","view_paper":"https://pith.science/paper/LV2QZL25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07899&json=true","fetch_graph":"https://pith.science/api/pith-number/LV2QZL25L4HHBYA3YZ7E6ZR247/graph.json","fetch_events":"https://pith.science/api/pith-number/LV2QZL25L4HHBYA3YZ7E6ZR247/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LV2QZL25L4HHBYA3YZ7E6ZR247/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LV2QZL25L4HHBYA3YZ7E6ZR247/action/storage_attestation","attest_author":"https://pith.science/pith/LV2QZL25L4HHBYA3YZ7E6ZR247/action/author_attestation","sign_citation":"https://pith.science/pith/LV2QZL25L4HHBYA3YZ7E6ZR247/action/citation_signature","submit_replication":"https://pith.science/pith/LV2QZL25L4HHBYA3YZ7E6ZR247/action/replication_record"}},"created_at":"2026-07-05T05:40:49.355702+00:00","updated_at":"2026-07-05T05:40:49.355702+00:00"}