{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y4L3DECDQ6DTGPBGGLF44GPTNK","short_pith_number":"pith:Y4L3DECD","schema_version":"1.0","canonical_sha256":"c717b190438787333c2632cbce19f36aa0e5557fb7884bb65c1ac5aa0491f3df","source":{"kind":"arxiv","id":"2407.13432","version":3},"attestation_state":"computed","paper":{"title":"The Art of Imitation: Learning Long-Horizon Manipulation Tasks from Few Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhinav Valada, Jan Ole von Hartz, Joschka Boedecker, Tim Welschehold","submitted_at":"2024-07-18T12:01:09Z","abstract_excerpt":"Task Parametrized Gaussian Mixture Models (TP-GMM) are a sample-efficient method for learning object-centric robot manipulation tasks. However, there are several open challenges to applying TP-GMMs in the wild. In this work, we tackle three crucial challenges synergistically. First, end-effector velocities are non-Euclidean and thus hard to model using standard GMMs. We thus propose to factorize the robot's end-effector velocity into its direction and magnitude, and model them using Riemannian GMMs. Second, we leverage the factorized velocities to segment and sequence skills from complex demon"},"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":"2407.13432","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-07-18T12:01:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eefe37ee4269f55dbe6e4675cfbb5c3a6d238e1bb8ee2a6bc134ddb8ee7129f4","abstract_canon_sha256":"7cad12fb0a37f1674943f68d1c1b3ffb9703fb9aef25cdc074b020de0777f652"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:36.915661Z","signature_b64":"L8JVW/VMOzai8wwSP7/gHD+VcDo+knqZborcS7yTbp6d4Y4SNY10EBsCKcVGXCJt5Ze6xqYji/ExFB1fQeEnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c717b190438787333c2632cbce19f36aa0e5557fb7884bb65c1ac5aa0491f3df","last_reissued_at":"2026-07-05T09:24:36.915069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:36.915069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Art of Imitation: Learning Long-Horizon Manipulation Tasks from Few Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhinav Valada, Jan Ole von Hartz, Joschka Boedecker, Tim Welschehold","submitted_at":"2024-07-18T12:01:09Z","abstract_excerpt":"Task Parametrized Gaussian Mixture Models (TP-GMM) are a sample-efficient method for learning object-centric robot manipulation tasks. However, there are several open challenges to applying TP-GMMs in the wild. In this work, we tackle three crucial challenges synergistically. First, end-effector velocities are non-Euclidean and thus hard to model using standard GMMs. We thus propose to factorize the robot's end-effector velocity into its direction and magnitude, and model them using Riemannian GMMs. Second, we leverage the factorized velocities to segment and sequence skills from complex demon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13432","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/2407.13432/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":"2407.13432","created_at":"2026-07-05T09:24:36.915130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13432v3","created_at":"2026-07-05T09:24:36.915130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13432","created_at":"2026-07-05T09:24:36.915130+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4L3DECDQ6DT","created_at":"2026-07-05T09:24:36.915130+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4L3DECDQ6DTGPBG","created_at":"2026-07-05T09:24:36.915130+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4L3DECD","created_at":"2026-07-05T09:24:36.915130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03296","citing_title":"The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y4L3DECDQ6DTGPBGGLF44GPTNK","json":"https://pith.science/pith/Y4L3DECDQ6DTGPBGGLF44GPTNK.json","graph_json":"https://pith.science/api/pith-number/Y4L3DECDQ6DTGPBGGLF44GPTNK/graph.json","events_json":"https://pith.science/api/pith-number/Y4L3DECDQ6DTGPBGGLF44GPTNK/events.json","paper":"https://pith.science/paper/Y4L3DECD"},"agent_actions":{"view_html":"https://pith.science/pith/Y4L3DECDQ6DTGPBGGLF44GPTNK","download_json":"https://pith.science/pith/Y4L3DECDQ6DTGPBGGLF44GPTNK.json","view_paper":"https://pith.science/paper/Y4L3DECD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13432&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4L3DECDQ6DTGPBGGLF44GPTNK/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4L3DECDQ6DTGPBGGLF44GPTNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4L3DECDQ6DTGPBGGLF44GPTNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4L3DECDQ6DTGPBGGLF44GPTNK/action/storage_attestation","attest_author":"https://pith.science/pith/Y4L3DECDQ6DTGPBGGLF44GPTNK/action/author_attestation","sign_citation":"https://pith.science/pith/Y4L3DECDQ6DTGPBGGLF44GPTNK/action/citation_signature","submit_replication":"https://pith.science/pith/Y4L3DECDQ6DTGPBGGLF44GPTNK/action/replication_record"}},"created_at":"2026-07-05T09:24:36.915130+00:00","updated_at":"2026-07-05T09:24:36.915130+00:00"}