{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R3ODEXCXIRYT7ISY77KUNCKMZ2","short_pith_number":"pith:R3ODEXCX","schema_version":"1.0","canonical_sha256":"8edc325c5744713fa258ffd546894ccebca05f6ded37d5e73fd3352d9ac5ea8b","source":{"kind":"arxiv","id":"2202.02005","version":1},"attestation_state":"computed","paper":{"title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Alex Irpan, Chelsea Finn, Corey Lynch, Daniel Kappler, Eric Jang, Frederik Ebert, Mohi Khansari, Sergey Levine","submitted_at":"2022-02-04T07:30:48Z","abstract_excerpt":"In this paper, we study the problem of enabling a vision-based robotic manipulation system to generalize to novel tasks, a long-standing challenge in robot learning. We approach the challenge from an imitation learning perspective, aiming to study how scaling and broadening the data collected can facilitate such generalization. To that end, we develop an interactive and flexible imitation learning system that can learn from both demonstrations and interventions and can be conditioned on different forms of information that convey the task, including pre-trained embeddings of natural language or"},"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":"2202.02005","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-02-04T07:30:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2c944ad680cc00f995476f713bf4fc447d84ca50b24c77e4beb23c4382ffc869","abstract_canon_sha256":"344bd47ae1b808804cbbb171f810533f1b10116c6fe836843295ffa95ad3de0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:07.966803Z","signature_b64":"Q64BTJ/PQ+my6kpfi9NDlWTz5mcpXzfUk8WKjd3dP2lRvcFRA+G7oJHe1cy1BVt2KlWOXZCTFnYN9YhuW5WhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8edc325c5744713fa258ffd546894ccebca05f6ded37d5e73fd3352d9ac5ea8b","last_reissued_at":"2026-07-05T03:54:07.966292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:07.966292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Alex Irpan, Chelsea Finn, Corey Lynch, Daniel Kappler, Eric Jang, Frederik Ebert, Mohi Khansari, Sergey Levine","submitted_at":"2022-02-04T07:30:48Z","abstract_excerpt":"In this paper, we study the problem of enabling a vision-based robotic manipulation system to generalize to novel tasks, a long-standing challenge in robot learning. We approach the challenge from an imitation learning perspective, aiming to study how scaling and broadening the data collected can facilitate such generalization. To that end, we develop an interactive and flexible imitation learning system that can learn from both demonstrations and interventions and can be conditioned on different forms of information that convey the task, including pre-trained embeddings of natural language or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02005","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/2202.02005/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":"2202.02005","created_at":"2026-07-05T03:54:07.966360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02005v1","created_at":"2026-07-05T03:54:07.966360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02005","created_at":"2026-07-05T03:54:07.966360+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3ODEXCXIRYT","created_at":"2026-07-05T03:54:07.966360+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3ODEXCXIRYT7ISY","created_at":"2026-07-05T03:54:07.966360+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3ODEXCX","created_at":"2026-07-05T03:54:07.966360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17511","citing_title":"MagicSim: A Unified Infrastructure for Executable Embodied Interaction","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02092","citing_title":"Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30318","citing_title":"Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27284","citing_title":"FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02125","citing_title":"Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17077","citing_title":"How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04671","citing_title":"X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13119","citing_title":"Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3ODEXCXIRYT7ISY77KUNCKMZ2","json":"https://pith.science/pith/R3ODEXCXIRYT7ISY77KUNCKMZ2.json","graph_json":"https://pith.science/api/pith-number/R3ODEXCXIRYT7ISY77KUNCKMZ2/graph.json","events_json":"https://pith.science/api/pith-number/R3ODEXCXIRYT7ISY77KUNCKMZ2/events.json","paper":"https://pith.science/paper/R3ODEXCX"},"agent_actions":{"view_html":"https://pith.science/pith/R3ODEXCXIRYT7ISY77KUNCKMZ2","download_json":"https://pith.science/pith/R3ODEXCXIRYT7ISY77KUNCKMZ2.json","view_paper":"https://pith.science/paper/R3ODEXCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02005&json=true","fetch_graph":"https://pith.science/api/pith-number/R3ODEXCXIRYT7ISY77KUNCKMZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/R3ODEXCXIRYT7ISY77KUNCKMZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3ODEXCXIRYT7ISY77KUNCKMZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3ODEXCXIRYT7ISY77KUNCKMZ2/action/storage_attestation","attest_author":"https://pith.science/pith/R3ODEXCXIRYT7ISY77KUNCKMZ2/action/author_attestation","sign_citation":"https://pith.science/pith/R3ODEXCXIRYT7ISY77KUNCKMZ2/action/citation_signature","submit_replication":"https://pith.science/pith/R3ODEXCXIRYT7ISY77KUNCKMZ2/action/replication_record"}},"created_at":"2026-07-05T03:54:07.966360+00:00","updated_at":"2026-07-05T03:54:07.966360+00:00"}