{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VI6L23WHTYUTMCYLCPVJIJKJ4P","short_pith_number":"pith:VI6L23WH","schema_version":"1.0","canonical_sha256":"aa3cbd6ec79e29360b0b13ea942549e3c7af93b657ad9a9c8cc794de1fb77cf3","source":{"kind":"arxiv","id":"2210.06407","version":1},"attestation_state":"computed","paper":{"title":"Interactive Language: Talking to Robots in Real Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ayzaan Wahid, Corey Lynch, James Betker, Jonathan Tompson, Pete Florence, Robert Baruch, Tianli Ding, Travis Armstrong","submitted_at":"2022-10-12T17:03:41Z","abstract_excerpt":"We present a framework for building interactive, real-time, natural language-instructable robots in the real world, and we open source related assets (dataset, environment, benchmark, and policies). Trained with behavioral cloning on a dataset of hundreds of thousands of language-annotated trajectories, a produced policy can proficiently execute an order of magnitude more commands than previous works: specifically we estimate a 93.5% success rate on a set of 87,000 unique natural language strings specifying raw end-to-end visuo-linguo-motor skills in the real world. We find that the same polic"},"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":"2210.06407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-10-12T17:03:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6063f06bad0283897ef00d31f0f0223f2391b2acc1bd50dd4d82eb60062f928d","abstract_canon_sha256":"993d8649cb7bc820ba22c9b85e7fd9caff81ce93d41de81002154c1e0ee938cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:00.228516Z","signature_b64":"fBUZTx3n/fKRYn4KK0jv2tSARBnzoPF4+lNzhTVi9BcrWj/ol8LFaZashv6e1mjEL3TX13+GdAZq1PIWZa8uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa3cbd6ec79e29360b0b13ea942549e3c7af93b657ad9a9c8cc794de1fb77cf3","last_reissued_at":"2026-07-05T05:06:00.228025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:00.228025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Language: Talking to Robots in Real Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ayzaan Wahid, Corey Lynch, James Betker, Jonathan Tompson, Pete Florence, Robert Baruch, Tianli Ding, Travis Armstrong","submitted_at":"2022-10-12T17:03:41Z","abstract_excerpt":"We present a framework for building interactive, real-time, natural language-instructable robots in the real world, and we open source related assets (dataset, environment, benchmark, and policies). Trained with behavioral cloning on a dataset of hundreds of thousands of language-annotated trajectories, a produced policy can proficiently execute an order of magnitude more commands than previous works: specifically we estimate a 93.5% success rate on a set of 87,000 unique natural language strings specifying raw end-to-end visuo-linguo-motor skills in the real world. We find that the same polic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06407","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/2210.06407/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":"2210.06407","created_at":"2026-07-05T05:06:00.228086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.06407v1","created_at":"2026-07-05T05:06:00.228086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06407","created_at":"2026-07-05T05:06:00.228086+00:00"},{"alias_kind":"pith_short_12","alias_value":"VI6L23WHTYUT","created_at":"2026-07-05T05:06:00.228086+00:00"},{"alias_kind":"pith_short_16","alias_value":"VI6L23WHTYUTMCYL","created_at":"2026-07-05T05:06:00.228086+00:00"},{"alias_kind":"pith_short_8","alias_value":"VI6L23WH","created_at":"2026-07-05T05:06:00.228086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30318","citing_title":"Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09881","citing_title":"Toward Calibrated, Fair, and accurate Deepfake Detection","ref_index":267,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20246","citing_title":"GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17855","citing_title":"QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20246","citing_title":"GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17855","citing_title":"QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08708","citing_title":"Consciousness in Artificial Intelligence: Insights from the Science of Consciousness","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":199,"is_internal_anchor":false},{"citing_arxiv_id":"2312.13139","citing_title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2303.03378","citing_title":"PaLM-E: An Embodied Multimodal Language Model","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VI6L23WHTYUTMCYLCPVJIJKJ4P","json":"https://pith.science/pith/VI6L23WHTYUTMCYLCPVJIJKJ4P.json","graph_json":"https://pith.science/api/pith-number/VI6L23WHTYUTMCYLCPVJIJKJ4P/graph.json","events_json":"https://pith.science/api/pith-number/VI6L23WHTYUTMCYLCPVJIJKJ4P/events.json","paper":"https://pith.science/paper/VI6L23WH"},"agent_actions":{"view_html":"https://pith.science/pith/VI6L23WHTYUTMCYLCPVJIJKJ4P","download_json":"https://pith.science/pith/VI6L23WHTYUTMCYLCPVJIJKJ4P.json","view_paper":"https://pith.science/paper/VI6L23WH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.06407&json=true","fetch_graph":"https://pith.science/api/pith-number/VI6L23WHTYUTMCYLCPVJIJKJ4P/graph.json","fetch_events":"https://pith.science/api/pith-number/VI6L23WHTYUTMCYLCPVJIJKJ4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VI6L23WHTYUTMCYLCPVJIJKJ4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VI6L23WHTYUTMCYLCPVJIJKJ4P/action/storage_attestation","attest_author":"https://pith.science/pith/VI6L23WHTYUTMCYLCPVJIJKJ4P/action/author_attestation","sign_citation":"https://pith.science/pith/VI6L23WHTYUTMCYLCPVJIJKJ4P/action/citation_signature","submit_replication":"https://pith.science/pith/VI6L23WHTYUTMCYLCPVJIJKJ4P/action/replication_record"}},"created_at":"2026-07-05T05:06:00.228086+00:00","updated_at":"2026-07-05T05:06:00.228086+00:00"}