{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OOMNIGUSU542CY6TNYGXG6CSCW","short_pith_number":"pith:OOMNIGUS","schema_version":"1.0","canonical_sha256":"7398d41a92a779a163d36e0d73785215aa5cca5724f39bf74f5e348b14d51f24","source":{"kind":"arxiv","id":"2410.12782","version":2},"attestation_state":"computed","paper":{"title":"In-Context Learning Enables Robot Action Prediction in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.RO","authors_text":"Dantong Niu, Roei Herzig, Trevor Darrell, Yida Yin, Yuvan Sharma, Zekai Wang","submitted_at":"2024-10-16T17:56:49Z","abstract_excerpt":"Recently, Large Language Models (LLMs) have achieved remarkable success using in-context learning (ICL) in the language domain. However, leveraging the ICL capabilities within LLMs to directly predict robot actions remains largely unexplored. In this paper, we introduce RoboPrompt, a framework that enables off-the-shelf text-only LLMs to directly predict robot actions through ICL without training. Our approach first heuristically identifies keyframes that capture important moments from an episode. Next, we extract end-effector actions from these keyframes as well as the estimated initial objec"},"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":"2410.12782","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-16T17:56:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"99b1ca24eac79021b36b9467976aefc6328914622350f3ea5536a5553ffa4b55","abstract_canon_sha256":"ed2e4c9d81685b31296cd1725d67308c14d6cabd69460b00b496a554c349cebd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:32.191238Z","signature_b64":"dMKYHbxArrYzZQA9zJh7m7ymHUUlPwyMv2IMDXnKe+3H5rOlBZX2PanZ+rhv+L79LeOAeDE5tMXYq27x5LUDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7398d41a92a779a163d36e0d73785215aa5cca5724f39bf74f5e348b14d51f24","last_reissued_at":"2026-07-05T10:32:32.190379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:32.190379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning Enables Robot Action Prediction in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.RO","authors_text":"Dantong Niu, Roei Herzig, Trevor Darrell, Yida Yin, Yuvan Sharma, Zekai Wang","submitted_at":"2024-10-16T17:56:49Z","abstract_excerpt":"Recently, Large Language Models (LLMs) have achieved remarkable success using in-context learning (ICL) in the language domain. However, leveraging the ICL capabilities within LLMs to directly predict robot actions remains largely unexplored. In this paper, we introduce RoboPrompt, a framework that enables off-the-shelf text-only LLMs to directly predict robot actions through ICL without training. Our approach first heuristically identifies keyframes that capture important moments from an episode. Next, we extract end-effector actions from these keyframes as well as the estimated initial objec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12782","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/2410.12782/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":"2410.12782","created_at":"2026-07-05T10:32:32.190481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12782v2","created_at":"2026-07-05T10:32:32.190481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12782","created_at":"2026-07-05T10:32:32.190481+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOMNIGUSU542","created_at":"2026-07-05T10:32:32.190481+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOMNIGUSU542CY6T","created_at":"2026-07-05T10:32:32.190481+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOMNIGUS","created_at":"2026-07-05T10:32:32.190481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15215","citing_title":"A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13193","citing_title":"Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12412","citing_title":"Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05115","citing_title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","ref_index":262,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01448","citing_title":"Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic Manipulation","ref_index":21,"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":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOMNIGUSU542CY6TNYGXG6CSCW","json":"https://pith.science/pith/OOMNIGUSU542CY6TNYGXG6CSCW.json","graph_json":"https://pith.science/api/pith-number/OOMNIGUSU542CY6TNYGXG6CSCW/graph.json","events_json":"https://pith.science/api/pith-number/OOMNIGUSU542CY6TNYGXG6CSCW/events.json","paper":"https://pith.science/paper/OOMNIGUS"},"agent_actions":{"view_html":"https://pith.science/pith/OOMNIGUSU542CY6TNYGXG6CSCW","download_json":"https://pith.science/pith/OOMNIGUSU542CY6TNYGXG6CSCW.json","view_paper":"https://pith.science/paper/OOMNIGUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12782&json=true","fetch_graph":"https://pith.science/api/pith-number/OOMNIGUSU542CY6TNYGXG6CSCW/graph.json","fetch_events":"https://pith.science/api/pith-number/OOMNIGUSU542CY6TNYGXG6CSCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOMNIGUSU542CY6TNYGXG6CSCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOMNIGUSU542CY6TNYGXG6CSCW/action/storage_attestation","attest_author":"https://pith.science/pith/OOMNIGUSU542CY6TNYGXG6CSCW/action/author_attestation","sign_citation":"https://pith.science/pith/OOMNIGUSU542CY6TNYGXG6CSCW/action/citation_signature","submit_replication":"https://pith.science/pith/OOMNIGUSU542CY6TNYGXG6CSCW/action/replication_record"}},"created_at":"2026-07-05T10:32:32.190481+00:00","updated_at":"2026-07-05T10:32:32.190481+00:00"}