{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4JXPGGJZNEJYM5MN36PUOYMJOF","short_pith_number":"pith:4JXPGGJZ","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"},"canonical_sha256":"e26ef31939691386758ddf9f47618971448db5cd16eaa260f9d2c698d33221b0","source":{"kind":"arxiv","id":"2407.12957","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4JXPGGJZNEJYM5MN36PUOYMJOF","target":"record","payload":{"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"},"canonical_sha256":"e26ef31939691386758ddf9f47618971448db5cd16eaa260f9d2c698d33221b0","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"},"source_kind":"arxiv","source_id":"2407.12957","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s3WoGopUecQAK9jzuHG0WGP9T0UlSF1iSTMivQEqtjyNHQpV7Qw49N8lGtofXqT0o+K7anTjOJv5V2aeTm9zDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:38:40.843308Z"},"content_sha256":"4aa0132d49f38acddd900ac34b8d3d915ab31e45a87418fd1a443d89772cf2e4","schema_version":"1.0","event_id":"sha256:4aa0132d49f38acddd900ac34b8d3d915ab31e45a87418fd1a443d89772cf2e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4JXPGGJZNEJYM5MN36PUOYMJOF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7A2hTK9vC3DehX8/psrbXX9jcdvzdjoypwBfbezSxYu6+0gJNfW/my3Xp5CXDmY3/h0T6YioKrRHO8jFkpCaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:38:40.843802Z"},"content_sha256":"d47cf69e63724aed016dea898ee8accfa0c3c7fc73634e456987c2d11de59188","schema_version":"1.0","event_id":"sha256:d47cf69e63724aed016dea898ee8accfa0c3c7fc73634e456987c2d11de59188"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/bundle.json","state_url":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T05:38:40Z","links":{"resolver":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF","bundle":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/bundle.json","state":"https://pith.science/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4JXPGGJZNEJYM5MN36PUOYMJOF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B0gsM6TX+36/iR2R6MEvLL9/5YWAlfsS/5HpMTCnpVC/nmZjtC1NvwJShRHW+bN9XUUI8J2sDde2rGI8IPyvBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:38:40.847051Z","bundle_sha256":"893c24bde987ecc2deb371e8c46cc5c62f51ffddf59aa69463330e85baaf0dfc"}}