{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KWFSWEU3S6F5VQSS5NZ6CIT6EW","short_pith_number":"pith:KWFSWEU3","schema_version":"1.0","canonical_sha256":"558b2b129b978bdac252eb73e1227e25aa331bf9f19e0b8e8faaa1d0d4737553","source":{"kind":"arxiv","id":"2503.07017","version":1},"attestation_state":"computed","paper":{"title":"How to Train Your Robots? The Impact of Demonstration Modality on Imitation Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dorsa Sadigh, Haozhuo Li, Yuchen Cui","submitted_at":"2025-03-10T07:57:26Z","abstract_excerpt":"Imitation learning is a promising approach for learning robot policies with user-provided data. The way demonstrations are provided, i.e., demonstration modality, influences the quality of the data. While existing research shows that kinesthetic teaching (physically guiding the robot) is preferred by users for the intuitiveness and ease of use, the majority of existing manipulation datasets were collected through teleoperation via a VR controller or spacemouse. In this work, we investigate how different demonstration modalities impact downstream learning performance as well as user experience."},"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":"2503.07017","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-10T07:57:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4ead6c4c8f6dde822e4298d8b8d5c87fc5f2f9f2524ab346d7d0fc413fbc6120","abstract_canon_sha256":"e286d1b698c62080d2201ebeace9060d00a97cb7a6a38f559fadb3b704a063b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:47.901117Z","signature_b64":"b5rdYxVXW5XQNy/gdZO2gcuY2y7SMbSUmQEW2l57J6NGHTleMjuhQaAqANw+qwoE9DVmim1mDPWkLZNmkYQVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"558b2b129b978bdac252eb73e1227e25aa331bf9f19e0b8e8faaa1d0d4737553","last_reissued_at":"2026-07-05T10:27:47.900501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:47.900501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Train Your Robots? The Impact of Demonstration Modality on Imitation Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dorsa Sadigh, Haozhuo Li, Yuchen Cui","submitted_at":"2025-03-10T07:57:26Z","abstract_excerpt":"Imitation learning is a promising approach for learning robot policies with user-provided data. The way demonstrations are provided, i.e., demonstration modality, influences the quality of the data. While existing research shows that kinesthetic teaching (physically guiding the robot) is preferred by users for the intuitiveness and ease of use, the majority of existing manipulation datasets were collected through teleoperation via a VR controller or spacemouse. In this work, we investigate how different demonstration modalities impact downstream learning performance as well as user experience."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07017","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/2503.07017/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":"2503.07017","created_at":"2026-07-05T10:27:47.900574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07017v1","created_at":"2026-07-05T10:27:47.900574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07017","created_at":"2026-07-05T10:27:47.900574+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWFSWEU3S6F5","created_at":"2026-07-05T10:27:47.900574+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWFSWEU3S6F5VQSS","created_at":"2026-07-05T10:27:47.900574+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWFSWEU3","created_at":"2026-07-05T10:27:47.900574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26349","citing_title":"Closing the Loop in Teleoperation: Episode-Level Data Quality Assessment and Feedback for High-Quality Demonstration Collection","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18722","citing_title":"Dexora: Open-source VLA for High-DoF Bimanual Dexterity","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23000","citing_title":"Learning from the Best: Smoothness-Driven Metrics for Data Quality in Imitation Learning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWFSWEU3S6F5VQSS5NZ6CIT6EW","json":"https://pith.science/pith/KWFSWEU3S6F5VQSS5NZ6CIT6EW.json","graph_json":"https://pith.science/api/pith-number/KWFSWEU3S6F5VQSS5NZ6CIT6EW/graph.json","events_json":"https://pith.science/api/pith-number/KWFSWEU3S6F5VQSS5NZ6CIT6EW/events.json","paper":"https://pith.science/paper/KWFSWEU3"},"agent_actions":{"view_html":"https://pith.science/pith/KWFSWEU3S6F5VQSS5NZ6CIT6EW","download_json":"https://pith.science/pith/KWFSWEU3S6F5VQSS5NZ6CIT6EW.json","view_paper":"https://pith.science/paper/KWFSWEU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07017&json=true","fetch_graph":"https://pith.science/api/pith-number/KWFSWEU3S6F5VQSS5NZ6CIT6EW/graph.json","fetch_events":"https://pith.science/api/pith-number/KWFSWEU3S6F5VQSS5NZ6CIT6EW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWFSWEU3S6F5VQSS5NZ6CIT6EW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWFSWEU3S6F5VQSS5NZ6CIT6EW/action/storage_attestation","attest_author":"https://pith.science/pith/KWFSWEU3S6F5VQSS5NZ6CIT6EW/action/author_attestation","sign_citation":"https://pith.science/pith/KWFSWEU3S6F5VQSS5NZ6CIT6EW/action/citation_signature","submit_replication":"https://pith.science/pith/KWFSWEU3S6F5VQSS5NZ6CIT6EW/action/replication_record"}},"created_at":"2026-07-05T10:27:47.900574+00:00","updated_at":"2026-07-05T10:27:47.900574+00:00"}