{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GADUKDWMPMTNI72BW4Y7YSKMC6","short_pith_number":"pith:GADUKDWM","canonical_record":{"source":{"id":"2403.19578","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-28T17:04:00Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"b6d801b782626f5559130fd017c58fa743caf317a5e0cf0c3a1f73164b1fc590","abstract_canon_sha256":"64f54971b6489b4c55fef0a51c7cb5350eba01fad1a34a703a505f2ae3f22037"},"schema_version":"1.0"},"canonical_sha256":"3007450ecc7b26d47f41b731fc494c17a743d5581f6a9883d9511db71bac14a5","source":{"kind":"arxiv","id":"2403.19578","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19578","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19578v3","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19578","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"GADUKDWMPMTN","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"GADUKDWMPMTNI72B","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"GADUKDWM","created_at":"2026-07-05T09:22:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GADUKDWMPMTNI72BW4Y7YSKMC6","target":"record","payload":{"canonical_record":{"source":{"id":"2403.19578","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-28T17:04:00Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"b6d801b782626f5559130fd017c58fa743caf317a5e0cf0c3a1f73164b1fc590","abstract_canon_sha256":"64f54971b6489b4c55fef0a51c7cb5350eba01fad1a34a703a505f2ae3f22037"},"schema_version":"1.0"},"canonical_sha256":"3007450ecc7b26d47f41b731fc494c17a743d5581f6a9883d9511db71bac14a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:17.083630Z","signature_b64":"Hcxjz1Dcg3U+PqcQWim2EjGqeEEVFEGIKamgv1wNNuUg66fJHCfcQ1OIQBzwxKMcbLrruLLil+hLdCEoRPmzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3007450ecc7b26d47f41b731fc494c17a743d5581f6a9883d9511db71bac14a5","last_reissued_at":"2026-07-05T09:22:17.083147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:17.083147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.19578","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e3FruE/nXGOQOy+JgYdxMCT3dQcEqq1RgLm2U2PutEoh5xpoiSLrYgVexGquHe+WcA5LBod37CbT8gVnwtLQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:39:03.862347Z"},"content_sha256":"1ef7161dc484adcadd664c03e1281e5dbcaeaf5aaabdb9b048e3045fe0947d3a","schema_version":"1.0","event_id":"sha256:1ef7161dc484adcadd664c03e1281e5dbcaeaf5aaabdb9b048e3045fe0947d3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GADUKDWMPMTNI72BW4Y7YSKMC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.RO","authors_text":"Edward Johns, Norman Di Palo","submitted_at":"2024-03-28T17:04:00Z","abstract_excerpt":"We show that off-the-shelf text-based Transformers, with no additional training, can perform few-shot in-context visual imitation learning, mapping visual observations to action sequences that emulate the demonstrator's behaviour. We achieve this by transforming visual observations (inputs) and trajectories of actions (outputs) into sequences of tokens that a text-pretrained Transformer (GPT-4 Turbo) can ingest and generate, via a framework we call Keypoint Action Tokens (KAT). Despite being trained only on language, we show that these Transformers excel at translating tokenised visual keypoin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19578","kind":"arxiv","version":3},"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/2403.19578/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":"2026-07-05T09:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MeeF6rBisEM+NygzytlMH65bm/9rfDLn8ia7wXOpFapVyFtgWWYhd3Eu8xnWvXybyIUdC6gefUNI4WLBwGUrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:39:03.862860Z"},"content_sha256":"7cd16f64362b77f8f3ce96ed01044a1442fd285740a94c6ca4265fdd6f520b39","schema_version":"1.0","event_id":"sha256:7cd16f64362b77f8f3ce96ed01044a1442fd285740a94c6ca4265fdd6f520b39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GADUKDWMPMTNI72BW4Y7YSKMC6/bundle.json","state_url":"https://pith.science/pith/GADUKDWMPMTNI72BW4Y7YSKMC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GADUKDWMPMTNI72BW4Y7YSKMC6/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":"2026-08-08T17:39:03Z","links":{"resolver":"https://pith.science/pith/GADUKDWMPMTNI72BW4Y7YSKMC6","bundle":"https://pith.science/pith/GADUKDWMPMTNI72BW4Y7YSKMC6/bundle.json","state":"https://pith.science/pith/GADUKDWMPMTNI72BW4Y7YSKMC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GADUKDWMPMTNI72BW4Y7YSKMC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GADUKDWMPMTNI72BW4Y7YSKMC6","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":"64f54971b6489b4c55fef0a51c7cb5350eba01fad1a34a703a505f2ae3f22037","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-28T17:04:00Z","title_canon_sha256":"b6d801b782626f5559130fd017c58fa743caf317a5e0cf0c3a1f73164b1fc590"},"schema_version":"1.0","source":{"id":"2403.19578","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19578","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19578v3","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19578","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"GADUKDWMPMTN","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"GADUKDWMPMTNI72B","created_at":"2026-07-05T09:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"GADUKDWM","created_at":"2026-07-05T09:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:7cd16f64362b77f8f3ce96ed01044a1442fd285740a94c6ca4265fdd6f520b39","target":"graph","created_at":"2026-07-05T09:22:17Z","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/2403.19578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show that off-the-shelf text-based Transformers, with no additional training, can perform few-shot in-context visual imitation learning, mapping visual observations to action sequences that emulate the demonstrator's behaviour. We achieve this by transforming visual observations (inputs) and trajectories of actions (outputs) into sequences of tokens that a text-pretrained Transformer (GPT-4 Turbo) can ingest and generate, via a framework we call Keypoint Action Tokens (KAT). Despite being trained only on language, we show that these Transformers excel at translating tokenised visual keypoin","authors_text":"Edward Johns, Norman Di Palo","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-28T17:04:00Z","title":"Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19578","kind":"arxiv","version":3},"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":"sha256:1ef7161dc484adcadd664c03e1281e5dbcaeaf5aaabdb9b048e3045fe0947d3a","target":"record","created_at":"2026-07-05T09:22:17Z","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":"64f54971b6489b4c55fef0a51c7cb5350eba01fad1a34a703a505f2ae3f22037","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-28T17:04:00Z","title_canon_sha256":"b6d801b782626f5559130fd017c58fa743caf317a5e0cf0c3a1f73164b1fc590"},"schema_version":"1.0","source":{"id":"2403.19578","kind":"arxiv","version":3}},"canonical_sha256":"3007450ecc7b26d47f41b731fc494c17a743d5581f6a9883d9511db71bac14a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3007450ecc7b26d47f41b731fc494c17a743d5581f6a9883d9511db71bac14a5","first_computed_at":"2026-07-05T09:22:17.083147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:17.083147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hcxjz1Dcg3U+PqcQWim2EjGqeEEVFEGIKamgv1wNNuUg66fJHCfcQ1OIQBzwxKMcbLrruLLil+hLdCEoRPmzCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:17.083630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19578","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ef7161dc484adcadd664c03e1281e5dbcaeaf5aaabdb9b048e3045fe0947d3a","sha256:7cd16f64362b77f8f3ce96ed01044a1442fd285740a94c6ca4265fdd6f520b39"],"state_sha256":"e375eade24fdde9d8044618eb7bbba12057b254845a230d7ee14a146bc4b260b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7OARKN9HX6lvnCSUheai2Ickpad7Oo25JvDzR9R05RrWJ6hhZctLXRXOuC2k1lKePhP1BV0K4AyPV8kRgMaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:39:03.868383Z","bundle_sha256":"5361e581b71bcfb694b6a9a18dee2993c17ce4da1a3be9abf903cd517bd1652f"}}