{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LPDF3Z6EHHHRIVGC327XL5IKIK","short_pith_number":"pith:LPDF3Z6E","schema_version":"1.0","canonical_sha256":"5bc65de7c439cf1454c2debf75f50a4280a717d21f4184213e9076eaa31f2409","source":{"kind":"arxiv","id":"2606.08154","version":1},"attestation_state":"computed","paper":{"title":"SynthICL: Scalable In-context Imitation Learning with Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Cheng Qian, Edward Johns, Ruomeng Fan, Yifei Ren, Yilong Wang","submitted_at":"2026-06-06T13:09:47Z","abstract_excerpt":"In-context imitation learning (ICIL) enables robots to learn new tasks from a small number of demonstrations by conditioning a pre-trained policy on task-specific examples, without retraining at test time. Despite this promise, training generalizable and scalable in-context imitation policies remains an open challenge. We present SynthICL, a scalable framework that trains ICIL policies entirely from RGB-only synthetic data. Specifically, we build a data generation pipeline to produce high-fidelity ICIL data and train a flow-matching transformer policy on the resulting dataset. SynthICL avoids "},"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":"2606.08154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-06T13:09:47Z","cross_cats_sorted":[],"title_canon_sha256":"440b483d16218538220129df967f26c4256a580577ce0cc9f6f7aa686d818402","abstract_canon_sha256":"4d958413decd2f41beae9fb7d190a513db4203400f1b2b637b1b1db50feaa87e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:28.371098Z","signature_b64":"GOe7B6jEj7rRP81Y6FsiRpTeGgOX68ZGwtb9zNC0l0HoIjFWljC5Xjf9XPCt3kRz7hk/3nwhj9GYl0TxYEPMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bc65de7c439cf1454c2debf75f50a4280a717d21f4184213e9076eaa31f2409","last_reissued_at":"2026-06-09T01:05:28.368487Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:28.368487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynthICL: Scalable In-context Imitation Learning with Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Cheng Qian, Edward Johns, Ruomeng Fan, Yifei Ren, Yilong Wang","submitted_at":"2026-06-06T13:09:47Z","abstract_excerpt":"In-context imitation learning (ICIL) enables robots to learn new tasks from a small number of demonstrations by conditioning a pre-trained policy on task-specific examples, without retraining at test time. Despite this promise, training generalizable and scalable in-context imitation policies remains an open challenge. We present SynthICL, a scalable framework that trains ICIL policies entirely from RGB-only synthetic data. Specifically, we build a data generation pipeline to produce high-fidelity ICIL data and train a flow-matching transformer policy on the resulting dataset. SynthICL avoids "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08154","kind":"arxiv","version":1},"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/2606.08154/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":"2606.08154","created_at":"2026-06-09T01:05:28.370441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08154v1","created_at":"2026-06-09T01:05:28.370441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08154","created_at":"2026-06-09T01:05:28.370441+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPDF3Z6EHHHR","created_at":"2026-06-09T01:05:28.370441+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPDF3Z6EHHHRIVGC","created_at":"2026-06-09T01:05:28.370441+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPDF3Z6E","created_at":"2026-06-09T01:05:28.370441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPDF3Z6EHHHRIVGC327XL5IKIK","json":"https://pith.science/pith/LPDF3Z6EHHHRIVGC327XL5IKIK.json","graph_json":"https://pith.science/api/pith-number/LPDF3Z6EHHHRIVGC327XL5IKIK/graph.json","events_json":"https://pith.science/api/pith-number/LPDF3Z6EHHHRIVGC327XL5IKIK/events.json","paper":"https://pith.science/paper/LPDF3Z6E"},"agent_actions":{"view_html":"https://pith.science/pith/LPDF3Z6EHHHRIVGC327XL5IKIK","download_json":"https://pith.science/pith/LPDF3Z6EHHHRIVGC327XL5IKIK.json","view_paper":"https://pith.science/paper/LPDF3Z6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08154&json=true","fetch_graph":"https://pith.science/api/pith-number/LPDF3Z6EHHHRIVGC327XL5IKIK/graph.json","fetch_events":"https://pith.science/api/pith-number/LPDF3Z6EHHHRIVGC327XL5IKIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPDF3Z6EHHHRIVGC327XL5IKIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPDF3Z6EHHHRIVGC327XL5IKIK/action/storage_attestation","attest_author":"https://pith.science/pith/LPDF3Z6EHHHRIVGC327XL5IKIK/action/author_attestation","sign_citation":"https://pith.science/pith/LPDF3Z6EHHHRIVGC327XL5IKIK/action/citation_signature","submit_replication":"https://pith.science/pith/LPDF3Z6EHHHRIVGC327XL5IKIK/action/replication_record"}},"created_at":"2026-06-09T01:05:28.370441+00:00","updated_at":"2026-06-09T01:05:28.370441+00:00"}