{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4JXPGGJZNEJYM5MN36PUOYMJOF","short_pith_number":"pith:4JXPGGJZ","schema_version":"1.0","canonical_sha256":"e26ef31939691386758ddf9f47618971448db5cd16eaa260f9d2c698d33221b0","source":{"kind":"arxiv","id":"2407.12957","version":2},"attestation_state":"computed","paper":{"title":"R+X: Retrieval and Execution from Everyday Human Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Edward Johns, Georgios Papagiannis, Norman Di Palo, Pietro Vitiello","submitted_at":"2024-07-17T18:59:56Z","abstract_excerpt":"We present R+X, a framework which enables robots to learn skills from long, unlabelled, first-person videos of humans performing everyday tasks. Given a language command from a human, R+X first retrieves short video clips containing relevant behaviour, and then executes the skill by conditioning an in-context imitation learning method (KAT) on this behaviour. By leveraging a Vision Language Model (VLM) for retrieval, R+X does not require any manual annotation of the videos, and by leveraging in-context learning for execution, robots can perform commanded skills immediately, without requiring a"},"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":"2407.12957","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-17T18:59:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ed0fc8fa9d91157f8d01c7e36915e203c4dd4eb1e6ba154a87454b878661f16b","abstract_canon_sha256":"e5fee22ec0f2f64c33989ebf8e982a7863b074dbd078ef6ce70bb79c471b7fb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:36.931943Z","signature_b64":"9BO75UafAb5pWmxbkiGBJ6cHLUW8AUhfv5KwCHR0nuc4NBEU8fbw3gaNoPVIW2lMApaBO0KtqkHYlzW07nPTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e26ef31939691386758ddf9f47618971448db5cd16eaa260f9d2c698d33221b0","last_reissued_at":"2026-07-05T10:43:36.931417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:36.931417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R+X: Retrieval and Execution from Everyday Human Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Edward Johns, Georgios Papagiannis, Norman Di Palo, Pietro Vitiello","submitted_at":"2024-07-17T18:59:56Z","abstract_excerpt":"We present R+X, a framework which enables robots to learn skills from long, unlabelled, first-person videos of humans performing everyday tasks. Given a language command from a human, R+X first retrieves short video clips containing relevant behaviour, and then executes the skill by conditioning an in-context imitation learning method (KAT) on this behaviour. By leveraging a Vision Language Model (VLM) for retrieval, R+X does not require any manual annotation of the videos, and by leveraging in-context learning for execution, robots can perform commanded skills immediately, without requiring a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12957","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/2407.12957/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":"2407.12957","created_at":"2026-07-05T10:43:36.931485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12957v2","created_at":"2026-07-05T10:43:36.931485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12957","created_at":"2026-07-05T10:43:36.931485+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JXPGGJZNEJY","created_at":"2026-07-05T10:43:36.931485+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JXPGGJZNEJYM5MN","created_at":"2026-07-05T10:43:36.931485+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JXPGGJZ","created_at":"2026-07-05T10:43:36.931485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15215","citing_title":"A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21723","citing_title":"VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2409.16283","citing_title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03637","citing_title":"Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10809","citing_title":"WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15215","citing_title":"A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF","json":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF.json","graph_json":"https://pith.science/api/pith-number/4JXPGGJZNEJYM5MN36PUOYMJOF/graph.json","events_json":"https://pith.science/api/pith-number/4JXPGGJZNEJYM5MN36PUOYMJOF/events.json","paper":"https://pith.science/paper/4JXPGGJZ"},"agent_actions":{"view_html":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF","download_json":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF.json","view_paper":"https://pith.science/paper/4JXPGGJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12957&json=true","fetch_graph":"https://pith.science/api/pith-number/4JXPGGJZNEJYM5MN36PUOYMJOF/graph.json","fetch_events":"https://pith.science/api/pith-number/4JXPGGJZNEJYM5MN36PUOYMJOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/action/storage_attestation","attest_author":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/action/author_attestation","sign_citation":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/action/citation_signature","submit_replication":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/action/replication_record"}},"created_at":"2026-07-05T10:43:36.931485+00:00","updated_at":"2026-07-05T10:43:36.931485+00:00"}