{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7RIQWGAD6EOXYTDLV4UMGIB4XO","short_pith_number":"pith:7RIQWGAD","schema_version":"1.0","canonical_sha256":"fc510b1803f11d7c4c6baf28c3203cbb87b6364f56995193067a3ff607ec3c52","source":{"kind":"arxiv","id":"2605.26649","version":1},"attestation_state":"computed","paper":{"title":"On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Danica Kragic, Francis wyffels, Marco Moletta, Michael C. Welle, Thomas Lips","submitted_at":"2026-05-26T07:31:43Z","abstract_excerpt":"RGB-based imitation learning requires many demonstrations to generalize to unseen objects or scenes, motivating research into intermediate representations to improve generalization for robotic manipulation. Visual foundation models enable one-shot extraction of keypoints to provide such representation. However, it remains unclear how to integrate them into imitation learning optimally and when they outperform alternative representations. We combine approaches from previous works on keypoint imitation learning (KIL) and investigate several design choices to provide practical guidelines. Using o"},"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":"2605.26649","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-26T07:31:43Z","cross_cats_sorted":[],"title_canon_sha256":"aac08b560bffc8d86ef8ce2f7d91edf5f9018ea5d943c8275d45486bdd4a519b","abstract_canon_sha256":"e8d95de9c7eb0ae899a23013aba4141b55dbad1135c1afd7e4943d7d81700e4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:04.071932Z","signature_b64":"fyKj3RSLLoi6Zrlq6mxmjuSggrjI8Kt9jRAiBjcOlgq3qxBr6ekZ5/2zLQxV+Cg1aSyFyG7RXVfKY+X3wYVYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc510b1803f11d7c4c6baf28c3203cbb87b6364f56995193067a3ff607ec3c52","last_reissued_at":"2026-05-27T01:06:04.071012Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:04.071012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Danica Kragic, Francis wyffels, Marco Moletta, Michael C. Welle, Thomas Lips","submitted_at":"2026-05-26T07:31:43Z","abstract_excerpt":"RGB-based imitation learning requires many demonstrations to generalize to unseen objects or scenes, motivating research into intermediate representations to improve generalization for robotic manipulation. Visual foundation models enable one-shot extraction of keypoints to provide such representation. However, it remains unclear how to integrate them into imitation learning optimally and when they outperform alternative representations. We combine approaches from previous works on keypoint imitation learning (KIL) and investigate several design choices to provide practical guidelines. Using o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26649","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/2605.26649/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":"2605.26649","created_at":"2026-05-27T01:06:04.071164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26649v1","created_at":"2026-05-27T01:06:04.071164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26649","created_at":"2026-05-27T01:06:04.071164+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RIQWGAD6EOX","created_at":"2026-05-27T01:06:04.071164+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RIQWGAD6EOXYTDL","created_at":"2026-05-27T01:06:04.071164+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RIQWGAD","created_at":"2026-05-27T01:06:04.071164+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/7RIQWGAD6EOXYTDLV4UMGIB4XO","json":"https://pith.science/pith/7RIQWGAD6EOXYTDLV4UMGIB4XO.json","graph_json":"https://pith.science/api/pith-number/7RIQWGAD6EOXYTDLV4UMGIB4XO/graph.json","events_json":"https://pith.science/api/pith-number/7RIQWGAD6EOXYTDLV4UMGIB4XO/events.json","paper":"https://pith.science/paper/7RIQWGAD"},"agent_actions":{"view_html":"https://pith.science/pith/7RIQWGAD6EOXYTDLV4UMGIB4XO","download_json":"https://pith.science/pith/7RIQWGAD6EOXYTDLV4UMGIB4XO.json","view_paper":"https://pith.science/paper/7RIQWGAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26649&json=true","fetch_graph":"https://pith.science/api/pith-number/7RIQWGAD6EOXYTDLV4UMGIB4XO/graph.json","fetch_events":"https://pith.science/api/pith-number/7RIQWGAD6EOXYTDLV4UMGIB4XO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RIQWGAD6EOXYTDLV4UMGIB4XO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RIQWGAD6EOXYTDLV4UMGIB4XO/action/storage_attestation","attest_author":"https://pith.science/pith/7RIQWGAD6EOXYTDLV4UMGIB4XO/action/author_attestation","sign_citation":"https://pith.science/pith/7RIQWGAD6EOXYTDLV4UMGIB4XO/action/citation_signature","submit_replication":"https://pith.science/pith/7RIQWGAD6EOXYTDLV4UMGIB4XO/action/replication_record"}},"created_at":"2026-05-27T01:06:04.071164+00:00","updated_at":"2026-05-27T01:06:04.071164+00:00"}