{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R4P54TJPL6KBHJN452AXFF4PS7","short_pith_number":"pith:R4P54TJP","schema_version":"1.0","canonical_sha256":"8f1fde4d2f5f9413a5bcee8172978f97dd6cdf86b84af72add90324ac593ead9","source":{"kind":"arxiv","id":"2408.15980","version":2},"attestation_state":"computed","paper":{"title":"In-Context Imitation Learning via Next-Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Fangchen Liu, Gaurav Datta, Huang Huang, Hui Li, Ken Goldberg, Lawrence Yunliang Chen, Letian Fu, William Chung-Ho Panitch","submitted_at":"2024-08-28T17:50:19Z","abstract_excerpt":"We explore how to enhance next-token prediction models to perform in-context imitation learning on a real robot, where the robot executes new tasks by interpreting contextual information provided during the input phase, without updating its underlying policy parameters. We propose In-Context Robot Transformer (ICRT), a causal transformer that performs autoregressive prediction on sensorimotor trajectories without relying on any linguistic data or reward function. This formulation enables flexible and training-free execution of new tasks at test time, achieved by prompting the model with sensor"},"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":"2408.15980","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-08-28T17:50:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fc1708f7c22134a95fbe547dd484c80a5883081bf698b4369f4d90ae0376669e","abstract_canon_sha256":"a92d2f53370836d1abba223c7040a4c6d1404bfa13853c167c3c8155712fefd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:06.938754Z","signature_b64":"E9ycRB4q5hthvyV96DzaHHYG7sB7hAWsIrL+LbdMypy+bYDbBn0tOLBnb9oxAHHbSLHz2P5Oz8uQrIb5DH52Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f1fde4d2f5f9413a5bcee8172978f97dd6cdf86b84af72add90324ac593ead9","last_reissued_at":"2026-07-05T09:13:06.938257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:06.938257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Imitation Learning via Next-Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Fangchen Liu, Gaurav Datta, Huang Huang, Hui Li, Ken Goldberg, Lawrence Yunliang Chen, Letian Fu, William Chung-Ho Panitch","submitted_at":"2024-08-28T17:50:19Z","abstract_excerpt":"We explore how to enhance next-token prediction models to perform in-context imitation learning on a real robot, where the robot executes new tasks by interpreting contextual information provided during the input phase, without updating its underlying policy parameters. We propose In-Context Robot Transformer (ICRT), a causal transformer that performs autoregressive prediction on sensorimotor trajectories without relying on any linguistic data or reward function. This formulation enables flexible and training-free execution of new tasks at test time, achieved by prompting the model with sensor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15980","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/2408.15980/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":"2408.15980","created_at":"2026-07-05T09:13:06.938324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15980v2","created_at":"2026-07-05T09:13:06.938324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15980","created_at":"2026-07-05T09:13:06.938324+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4P54TJPL6KB","created_at":"2026-07-05T09:13:06.938324+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4P54TJPL6KBHJN4","created_at":"2026-07-05T09:13:06.938324+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4P54TJP","created_at":"2026-07-05T09:13:06.938324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09758","citing_title":"Difference-Aware Retrieval Policies for Imitation Learning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04269","citing_title":"Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28320","citing_title":"WARP-RM: A Warp-Augmented Relative Progress Reward Model for Data Curation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30457","citing_title":"Behavior Prompting Policy: Demonstrations as Prompts for Manipulation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15215","citing_title":"A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13193","citing_title":"Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2603.00110","citing_title":"Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23121","citing_title":"Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18933","citing_title":"Gated Memory Policy","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15215","citing_title":"A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4P54TJPL6KBHJN452AXFF4PS7","json":"https://pith.science/pith/R4P54TJPL6KBHJN452AXFF4PS7.json","graph_json":"https://pith.science/api/pith-number/R4P54TJPL6KBHJN452AXFF4PS7/graph.json","events_json":"https://pith.science/api/pith-number/R4P54TJPL6KBHJN452AXFF4PS7/events.json","paper":"https://pith.science/paper/R4P54TJP"},"agent_actions":{"view_html":"https://pith.science/pith/R4P54TJPL6KBHJN452AXFF4PS7","download_json":"https://pith.science/pith/R4P54TJPL6KBHJN452AXFF4PS7.json","view_paper":"https://pith.science/paper/R4P54TJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15980&json=true","fetch_graph":"https://pith.science/api/pith-number/R4P54TJPL6KBHJN452AXFF4PS7/graph.json","fetch_events":"https://pith.science/api/pith-number/R4P54TJPL6KBHJN452AXFF4PS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4P54TJPL6KBHJN452AXFF4PS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4P54TJPL6KBHJN452AXFF4PS7/action/storage_attestation","attest_author":"https://pith.science/pith/R4P54TJPL6KBHJN452AXFF4PS7/action/author_attestation","sign_citation":"https://pith.science/pith/R4P54TJPL6KBHJN452AXFF4PS7/action/citation_signature","submit_replication":"https://pith.science/pith/R4P54TJPL6KBHJN452AXFF4PS7/action/replication_record"}},"created_at":"2026-07-05T09:13:06.938324+00:00","updated_at":"2026-07-05T09:13:06.938324+00:00"}