{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QKBD6KHNN7QQOLU6KF42MZ6GXQ","short_pith_number":"pith:QKBD6KHN","schema_version":"1.0","canonical_sha256":"82823f28ed6fe1072e9e5179a667c6bc2be3edbe4e0e1163385793ce3bb1895a","source":{"kind":"arxiv","id":"2411.12633","version":2},"attestation_state":"computed","paper":{"title":"Instant Policy: In-Context Imitation Learning via Graph Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Edward Johns, Vitalis Vosylius","submitted_at":"2024-11-19T16:45:52Z","abstract_excerpt":"Following the impressive capabilities of in-context learning with large transformers, In-Context Imitation Learning (ICIL) is a promising opportunity for robotics. We introduce Instant Policy, which learns new tasks instantly (without further training) from just one or two demonstrations, achieving ICIL through two key components. First, we introduce inductive biases through a graph representation and model ICIL as a graph generation problem with a learned diffusion process, enabling structured reasoning over demonstrations, observations, and actions. Second, we show that such a model can be t"},"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":"2411.12633","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-19T16:45:52Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"e8eb9c2a5efd18026b6fcad54fbd29ab7d883096d621b9d136e9cb054a28d2d6","abstract_canon_sha256":"ef144c8bc6b8f5dc57639835ce27637671d563d5f7dfd64438833ec430dfb729"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:49.285707Z","signature_b64":"OdHEVP3T5HSx0+agj4khazfyi0f++lm9/9hSYuo2IPOWCThv8ofQzByD1PBn8CFne6swrI9gu44WDW/AcxmUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82823f28ed6fe1072e9e5179a667c6bc2be3edbe4e0e1163385793ce3bb1895a","last_reissued_at":"2026-07-05T10:53:49.285138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:49.285138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instant Policy: In-Context Imitation Learning via Graph Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Edward Johns, Vitalis Vosylius","submitted_at":"2024-11-19T16:45:52Z","abstract_excerpt":"Following the impressive capabilities of in-context learning with large transformers, In-Context Imitation Learning (ICIL) is a promising opportunity for robotics. We introduce Instant Policy, which learns new tasks instantly (without further training) from just one or two demonstrations, achieving ICIL through two key components. First, we introduce inductive biases through a graph representation and model ICIL as a graph generation problem with a learned diffusion process, enabling structured reasoning over demonstrations, observations, and actions. Second, we show that such a model can be t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12633","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/2411.12633/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":"2411.12633","created_at":"2026-07-05T10:53:49.285202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12633v2","created_at":"2026-07-05T10:53:49.285202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12633","created_at":"2026-07-05T10:53:49.285202+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKBD6KHNN7QQ","created_at":"2026-07-05T10:53:49.285202+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKBD6KHNN7QQOLU6","created_at":"2026-07-05T10:53:49.285202+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKBD6KHN","created_at":"2026-07-05T10:53:49.285202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08154","citing_title":"SynthICL: Scalable In-context Imitation Learning with Synthetic Data","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14135","citing_title":"GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20978","citing_title":"Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulators","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKBD6KHNN7QQOLU6KF42MZ6GXQ","json":"https://pith.science/pith/QKBD6KHNN7QQOLU6KF42MZ6GXQ.json","graph_json":"https://pith.science/api/pith-number/QKBD6KHNN7QQOLU6KF42MZ6GXQ/graph.json","events_json":"https://pith.science/api/pith-number/QKBD6KHNN7QQOLU6KF42MZ6GXQ/events.json","paper":"https://pith.science/paper/QKBD6KHN"},"agent_actions":{"view_html":"https://pith.science/pith/QKBD6KHNN7QQOLU6KF42MZ6GXQ","download_json":"https://pith.science/pith/QKBD6KHNN7QQOLU6KF42MZ6GXQ.json","view_paper":"https://pith.science/paper/QKBD6KHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12633&json=true","fetch_graph":"https://pith.science/api/pith-number/QKBD6KHNN7QQOLU6KF42MZ6GXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QKBD6KHNN7QQOLU6KF42MZ6GXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKBD6KHNN7QQOLU6KF42MZ6GXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKBD6KHNN7QQOLU6KF42MZ6GXQ/action/storage_attestation","attest_author":"https://pith.science/pith/QKBD6KHNN7QQOLU6KF42MZ6GXQ/action/author_attestation","sign_citation":"https://pith.science/pith/QKBD6KHNN7QQOLU6KF42MZ6GXQ/action/citation_signature","submit_replication":"https://pith.science/pith/QKBD6KHNN7QQOLU6KF42MZ6GXQ/action/replication_record"}},"created_at":"2026-07-05T10:53:49.285202+00:00","updated_at":"2026-07-05T10:53:49.285202+00:00"}