{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E5AHN2NUWPNF5Z67OXCOYSXKD7","short_pith_number":"pith:E5AHN2NU","schema_version":"1.0","canonical_sha256":"274076e9b4b3da5ee7df75c4ec4aea1fdf6f48bb34fa882ab7fe1b6d3349f292","source":{"kind":"arxiv","id":"2405.13178","version":2},"attestation_state":"computed","paper":{"title":"One-Shot Imitation Learning with Invariance Matching for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abdeslam Boularias, Xinyu Zhang","submitted_at":"2024-05-21T20:01:03Z","abstract_excerpt":"Learning a single universal policy that can perform a diverse set of manipulation tasks is a promising new direction in robotics. However, existing techniques are limited to learning policies that can only perform tasks that are encountered during training, and require a large number of demonstrations to learn new tasks. Humans, on the other hand, often can learn a new task from a single unannotated demonstration. In this work, we propose the Invariance-Matching One-shot Policy Learning (IMOP) algorithm. In contrast to the standard practice of learning the end-effector's pose directly, IMOP fi"},"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":"2405.13178","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-21T20:01:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"def019c010d4ac90c26d29708d13e439729ee58b44f6a9beea138ba02f891a7f","abstract_canon_sha256":"a20e993a0bfecb627ab6d59f4f58ad10131ca804b9f064ebd2efb6e4dfaf9923"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:40.866554Z","signature_b64":"Fl/cK/R0fJGZ9hQHgj7frIIFBzsTHf00FrjT5eRYzNX8Nk+Hn5/34r3UU45XPkd29/rYEUCldVDKLyimM2emBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"274076e9b4b3da5ee7df75c4ec4aea1fdf6f48bb34fa882ab7fe1b6d3349f292","last_reissued_at":"2026-07-05T08:32:40.865977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:40.865977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Shot Imitation Learning with Invariance Matching for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abdeslam Boularias, Xinyu Zhang","submitted_at":"2024-05-21T20:01:03Z","abstract_excerpt":"Learning a single universal policy that can perform a diverse set of manipulation tasks is a promising new direction in robotics. However, existing techniques are limited to learning policies that can only perform tasks that are encountered during training, and require a large number of demonstrations to learn new tasks. Humans, on the other hand, often can learn a new task from a single unannotated demonstration. In this work, we propose the Invariance-Matching One-shot Policy Learning (IMOP) algorithm. In contrast to the standard practice of learning the end-effector's pose directly, IMOP fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13178","kind":"arxiv","version":2},"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/2405.13178/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":"2405.13178","created_at":"2026-07-05T08:32:40.866048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13178v2","created_at":"2026-07-05T08:32:40.866048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13178","created_at":"2026-07-05T08:32:40.866048+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5AHN2NUWPNF","created_at":"2026-07-05T08:32:40.866048+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5AHN2NUWPNF5Z67","created_at":"2026-07-05T08:32:40.866048+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5AHN2NU","created_at":"2026-07-05T08:32:40.866048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07217","citing_title":"Robotic Policy Adaptation via Weight-Space Meta-Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30457","citing_title":"Behavior Prompting Policy: Demonstrations as Prompts for Manipulation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03637","citing_title":"Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E5AHN2NUWPNF5Z67OXCOYSXKD7","json":"https://pith.science/pith/E5AHN2NUWPNF5Z67OXCOYSXKD7.json","graph_json":"https://pith.science/api/pith-number/E5AHN2NUWPNF5Z67OXCOYSXKD7/graph.json","events_json":"https://pith.science/api/pith-number/E5AHN2NUWPNF5Z67OXCOYSXKD7/events.json","paper":"https://pith.science/paper/E5AHN2NU"},"agent_actions":{"view_html":"https://pith.science/pith/E5AHN2NUWPNF5Z67OXCOYSXKD7","download_json":"https://pith.science/pith/E5AHN2NUWPNF5Z67OXCOYSXKD7.json","view_paper":"https://pith.science/paper/E5AHN2NU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13178&json=true","fetch_graph":"https://pith.science/api/pith-number/E5AHN2NUWPNF5Z67OXCOYSXKD7/graph.json","fetch_events":"https://pith.science/api/pith-number/E5AHN2NUWPNF5Z67OXCOYSXKD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5AHN2NUWPNF5Z67OXCOYSXKD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5AHN2NUWPNF5Z67OXCOYSXKD7/action/storage_attestation","attest_author":"https://pith.science/pith/E5AHN2NUWPNF5Z67OXCOYSXKD7/action/author_attestation","sign_citation":"https://pith.science/pith/E5AHN2NUWPNF5Z67OXCOYSXKD7/action/citation_signature","submit_replication":"https://pith.science/pith/E5AHN2NUWPNF5Z67OXCOYSXKD7/action/replication_record"}},"created_at":"2026-07-05T08:32:40.866048+00:00","updated_at":"2026-07-05T08:32:40.866048+00:00"}