{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B4XFQANU6ATQLWA3QJBN7HSJ2K","short_pith_number":"pith:B4XFQANU","schema_version":"1.0","canonical_sha256":"0f2e5801b4f02705d81b8242df9e49d2975edef79b84629c37fe2329038dafde","source":{"kind":"arxiv","id":"2109.08273","version":1},"attestation_state":"computed","paper":{"title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Albert Wilcox, Ashwin Balakrishna, Daniel S. Brown, Ellen Novoseller, Ken Goldberg, Ryan Hoque","submitted_at":"2021-09-17T01:21:16Z","abstract_excerpt":"Effective robot learning often requires online human feedback and interventions that can cost significant human time, giving rise to the central challenge in interactive imitation learning: is it possible to control the timing and length of interventions to both facilitate learning and limit burden on the human supervisor? This paper presents ThriftyDAgger, an algorithm for actively querying a human supervisor given a desired budget of human interventions. ThriftyDAgger uses a learned switching policy to solicit interventions only at states that are sufficiently (1) novel, where the robot poli"},"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":"2109.08273","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-17T01:21:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"198f57c009c64720846314fc9d825b0df9f9c4784d46d7d5ca36f6d940371c3c","abstract_canon_sha256":"ec706da688ba6278ed32c9491c16508c3fbcea5378245c0512d4c4b4fa315b4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:13.914350Z","signature_b64":"cYPGgbrPpGrGLvw60uNX1apvBAuvUHReBzIK4m5GObckThiZKXYz1zzZh5OS2QpJQDrH9hDRwn3FZ+OA3hGJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f2e5801b4f02705d81b8242df9e49d2975edef79b84629c37fe2329038dafde","last_reissued_at":"2026-07-05T03:15:13.913928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:13.913928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Albert Wilcox, Ashwin Balakrishna, Daniel S. Brown, Ellen Novoseller, Ken Goldberg, Ryan Hoque","submitted_at":"2021-09-17T01:21:16Z","abstract_excerpt":"Effective robot learning often requires online human feedback and interventions that can cost significant human time, giving rise to the central challenge in interactive imitation learning: is it possible to control the timing and length of interventions to both facilitate learning and limit burden on the human supervisor? This paper presents ThriftyDAgger, an algorithm for actively querying a human supervisor given a desired budget of human interventions. ThriftyDAgger uses a learned switching policy to solicit interventions only at states that are sufficiently (1) novel, where the robot poli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08273","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/2109.08273/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":"2109.08273","created_at":"2026-07-05T03:15:13.913983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.08273v1","created_at":"2026-07-05T03:15:13.913983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08273","created_at":"2026-07-05T03:15:13.913983+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4XFQANU6ATQ","created_at":"2026-07-05T03:15:13.913983+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4XFQANU6ATQLWA3","created_at":"2026-07-05T03:15:13.913983+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4XFQANU","created_at":"2026-07-05T03:15:13.913983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01651","citing_title":"One Demonstration Is Enough for Real-World Robotic Reinforcement Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31286","citing_title":"DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27114","citing_title":"VR-DAgger: Immersive VR for Dexterous Data Collection and Uncertainty-Guided On-Policy Correction","ref_index":6,"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":69,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04038","citing_title":"Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06222","citing_title":"When to Trust Imagination: Adaptive Action Execution for World Action Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09410","citing_title":"RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06222","citing_title":"When to Trust Imagination: Adaptive Action Execution for World Action Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4XFQANU6ATQLWA3QJBN7HSJ2K","json":"https://pith.science/pith/B4XFQANU6ATQLWA3QJBN7HSJ2K.json","graph_json":"https://pith.science/api/pith-number/B4XFQANU6ATQLWA3QJBN7HSJ2K/graph.json","events_json":"https://pith.science/api/pith-number/B4XFQANU6ATQLWA3QJBN7HSJ2K/events.json","paper":"https://pith.science/paper/B4XFQANU"},"agent_actions":{"view_html":"https://pith.science/pith/B4XFQANU6ATQLWA3QJBN7HSJ2K","download_json":"https://pith.science/pith/B4XFQANU6ATQLWA3QJBN7HSJ2K.json","view_paper":"https://pith.science/paper/B4XFQANU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.08273&json=true","fetch_graph":"https://pith.science/api/pith-number/B4XFQANU6ATQLWA3QJBN7HSJ2K/graph.json","fetch_events":"https://pith.science/api/pith-number/B4XFQANU6ATQLWA3QJBN7HSJ2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4XFQANU6ATQLWA3QJBN7HSJ2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4XFQANU6ATQLWA3QJBN7HSJ2K/action/storage_attestation","attest_author":"https://pith.science/pith/B4XFQANU6ATQLWA3QJBN7HSJ2K/action/author_attestation","sign_citation":"https://pith.science/pith/B4XFQANU6ATQLWA3QJBN7HSJ2K/action/citation_signature","submit_replication":"https://pith.science/pith/B4XFQANU6ATQLWA3QJBN7HSJ2K/action/replication_record"}},"created_at":"2026-07-05T03:15:13.913983+00:00","updated_at":"2026-07-05T03:15:13.913983+00:00"}