{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZBDXACQLRBFAMDQ5I5J7NQYL7X","short_pith_number":"pith:ZBDXACQL","schema_version":"1.0","canonical_sha256":"c847700a0b884a060e1d4753f6c30bfdc7c684fbb63758b5d011d8a4ce9cd13a","source":{"kind":"arxiv","id":"2405.01472","version":1},"attestation_state":"computed","paper":{"title":"IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ajay Mandlekar, Caelan Garrett, Dieter Fox, Ken Goldberg, Ryan Hoque","submitted_at":"2024-05-02T17:06:19Z","abstract_excerpt":"Imitation learning is a promising paradigm for training robot control policies, but these policies can suffer from distribution shift, where the conditions at evaluation time differ from those in the training data. A popular approach for increasing policy robustness to distribution shift is interactive imitation learning (i.e., DAgger and variants), where a human operator provides corrective interventions during policy rollouts. However, collecting a sufficient amount of interventions to cover the distribution of policy mistakes can be burdensome for human operators. We propose IntervenGen (I-"},"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":"2405.01472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-02T17:06:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"42363f876d37f3527dff966b2245dd1a49993a1e22d1a91c0493163a2c414dbe","abstract_canon_sha256":"459e58df8d16b69bbf774099bc71a9a1f6dad3b28e1dd13291d4d91ae7f6a185"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:45.620620Z","signature_b64":"mPRL/eaL8a5V49nRUFS2/IbWi2R5tTx7aLyakhQC5RhPN382/E3oRs5B+aBgRY/XdAhLlZYftuGyL6EVEiFmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c847700a0b884a060e1d4753f6c30bfdc7c684fbb63758b5d011d8a4ce9cd13a","last_reissued_at":"2026-07-05T08:14:45.620101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:45.620101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ajay Mandlekar, Caelan Garrett, Dieter Fox, Ken Goldberg, Ryan Hoque","submitted_at":"2024-05-02T17:06:19Z","abstract_excerpt":"Imitation learning is a promising paradigm for training robot control policies, but these policies can suffer from distribution shift, where the conditions at evaluation time differ from those in the training data. A popular approach for increasing policy robustness to distribution shift is interactive imitation learning (i.e., DAgger and variants), where a human operator provides corrective interventions during policy rollouts. However, collecting a sufficient amount of interventions to cover the distribution of policy mistakes can be burdensome for human operators. We propose IntervenGen (I-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01472","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/2405.01472/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":"2405.01472","created_at":"2026-07-05T08:14:45.620161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.01472v1","created_at":"2026-07-05T08:14:45.620161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01472","created_at":"2026-07-05T08:14:45.620161+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBDXACQLRBFA","created_at":"2026-07-05T08:14:45.620161+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBDXACQLRBFAMDQ5","created_at":"2026-07-05T08:14:45.620161+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBDXACQL","created_at":"2026-07-05T08:14:45.620161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01529","citing_title":"Good in Bad (GiB): Sifting Through End-user Demonstrations for Learning a Better Policy","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01529","citing_title":"Good in Bad (GiB): Sifting Through End-user Demonstrations for Learning a Better Policy","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBDXACQLRBFAMDQ5I5J7NQYL7X","json":"https://pith.science/pith/ZBDXACQLRBFAMDQ5I5J7NQYL7X.json","graph_json":"https://pith.science/api/pith-number/ZBDXACQLRBFAMDQ5I5J7NQYL7X/graph.json","events_json":"https://pith.science/api/pith-number/ZBDXACQLRBFAMDQ5I5J7NQYL7X/events.json","paper":"https://pith.science/paper/ZBDXACQL"},"agent_actions":{"view_html":"https://pith.science/pith/ZBDXACQLRBFAMDQ5I5J7NQYL7X","download_json":"https://pith.science/pith/ZBDXACQLRBFAMDQ5I5J7NQYL7X.json","view_paper":"https://pith.science/paper/ZBDXACQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.01472&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBDXACQLRBFAMDQ5I5J7NQYL7X/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBDXACQLRBFAMDQ5I5J7NQYL7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBDXACQLRBFAMDQ5I5J7NQYL7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBDXACQLRBFAMDQ5I5J7NQYL7X/action/storage_attestation","attest_author":"https://pith.science/pith/ZBDXACQLRBFAMDQ5I5J7NQYL7X/action/author_attestation","sign_citation":"https://pith.science/pith/ZBDXACQLRBFAMDQ5I5J7NQYL7X/action/citation_signature","submit_replication":"https://pith.science/pith/ZBDXACQLRBFAMDQ5I5J7NQYL7X/action/replication_record"}},"created_at":"2026-07-05T08:14:45.620161+00:00","updated_at":"2026-07-05T08:14:45.620161+00:00"}