{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4JXPGGJZNEJYM5MN36PUOYMJOF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e5fee22ec0f2f64c33989ebf8e982a7863b074dbd078ef6ce70bb79c471b7fb5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-17T18:59:56Z","title_canon_sha256":"ed0fc8fa9d91157f8d01c7e36915e203c4dd4eb1e6ba154a87454b878661f16b"},"schema_version":"1.0","source":{"id":"2407.12957","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12957","created_at":"2026-07-05T10:43:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12957v2","created_at":"2026-07-05T10:43:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12957","created_at":"2026-07-05T10:43:36Z"},{"alias_kind":"pith_short_12","alias_value":"4JXPGGJZNEJY","created_at":"2026-07-05T10:43:36Z"},{"alias_kind":"pith_short_16","alias_value":"4JXPGGJZNEJYM5MN","created_at":"2026-07-05T10:43:36Z"},{"alias_kind":"pith_short_8","alias_value":"4JXPGGJZ","created_at":"2026-07-05T10:43:36Z"}],"graph_snapshots":[{"event_id":"sha256:d47cf69e63724aed016dea898ee8accfa0c3c7fc73634e456987c2d11de59188","target":"graph","created_at":"2026-07-05T10:43:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.12957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Edward Johns, Georgios Papagiannis, Norman Di Palo, Pietro Vitiello","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-17T18:59:56Z","title":"R+X: Retrieval and Execution from Everyday Human Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12957","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4aa0132d49f38acddd900ac34b8d3d915ab31e45a87418fd1a443d89772cf2e4","target":"record","created_at":"2026-07-05T10:43:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e5fee22ec0f2f64c33989ebf8e982a7863b074dbd078ef6ce70bb79c471b7fb5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-17T18:59:56Z","title_canon_sha256":"ed0fc8fa9d91157f8d01c7e36915e203c4dd4eb1e6ba154a87454b878661f16b"},"schema_version":"1.0","source":{"id":"2407.12957","kind":"arxiv","version":2}},"canonical_sha256":"e26ef31939691386758ddf9f47618971448db5cd16eaa260f9d2c698d33221b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e26ef31939691386758ddf9f47618971448db5cd16eaa260f9d2c698d33221b0","first_computed_at":"2026-07-05T10:43:36.931417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:36.931417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9BO75UafAb5pWmxbkiGBJ6cHLUW8AUhfv5KwCHR0nuc4NBEU8fbw3gaNoPVIW2lMApaBO0KtqkHYlzW07nPTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:36.931943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12957","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aa0132d49f38acddd900ac34b8d3d915ab31e45a87418fd1a443d89772cf2e4","sha256:d47cf69e63724aed016dea898ee8accfa0c3c7fc73634e456987c2d11de59188"],"state_sha256":"1616a5427692a4cba58b103446d900fac5f9ea9daffb62f5ce4d0c1176a26522"}