{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CNPZACM6JA35LHJDGCAZODK4DL","short_pith_number":"pith:CNPZACM6","schema_version":"1.0","canonical_sha256":"135f90099e4837d59d233081970d5c1ad007756919176816134179b42c20fd85","source":{"kind":"arxiv","id":"2202.02465","version":1},"attestation_state":"computed","paper":{"title":"ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Anca D. Dragan, Glen Berseth, Jensen Gao, Sean Chen, Sergey Levine, Siddharth Reddy","submitted_at":"2022-02-05T02:01:19Z","abstract_excerpt":"Building assistive interfaces for controlling robots through arbitrary, high-dimensional, noisy inputs (e.g., webcam images of eye gaze) can be challenging, especially when it involves inferring the user's desired action in the absence of a natural 'default' interface. Reinforcement learning from online user feedback on the system's performance presents a natural solution to this problem, and enables the interface to adapt to individual users. However, this approach tends to require a large amount of human-in-the-loop training data, especially when feedback is sparse. We propose a hierarchical"},"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":"2202.02465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-02-05T02:01:19Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"e94a34b06582031bdd6f51ceb064a30b74a260381cb49ba4b9ea74cc0f459825","abstract_canon_sha256":"0f5f964c17a05a38c616bb8bb649e17e03d177fb18f767a8a9d473ed3f1f80df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:29.190289Z","signature_b64":"CZhzLjLQ3HWwIofUoqJa4P0B6Vb1s0TdlWyZ2Ao990xL/JQJs9XPoVVS9UNUTeEgOiMuhS4Qh7qBgvlV9hVCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"135f90099e4837d59d233081970d5c1ad007756919176816134179b42c20fd85","last_reissued_at":"2026-07-05T03:54:29.189828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:29.189828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Anca D. Dragan, Glen Berseth, Jensen Gao, Sean Chen, Sergey Levine, Siddharth Reddy","submitted_at":"2022-02-05T02:01:19Z","abstract_excerpt":"Building assistive interfaces for controlling robots through arbitrary, high-dimensional, noisy inputs (e.g., webcam images of eye gaze) can be challenging, especially when it involves inferring the user's desired action in the absence of a natural 'default' interface. Reinforcement learning from online user feedback on the system's performance presents a natural solution to this problem, and enables the interface to adapt to individual users. However, this approach tends to require a large amount of human-in-the-loop training data, especially when feedback is sparse. We propose a hierarchical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02465","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/2202.02465/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":"2202.02465","created_at":"2026-07-05T03:54:29.189915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02465v1","created_at":"2026-07-05T03:54:29.189915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02465","created_at":"2026-07-05T03:54:29.189915+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNPZACM6JA35","created_at":"2026-07-05T03:54:29.189915+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNPZACM6JA35LHJD","created_at":"2026-07-05T03:54:29.189915+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNPZACM6","created_at":"2026-07-05T03:54:29.189915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14727","citing_title":"Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CNPZACM6JA35LHJDGCAZODK4DL","json":"https://pith.science/pith/CNPZACM6JA35LHJDGCAZODK4DL.json","graph_json":"https://pith.science/api/pith-number/CNPZACM6JA35LHJDGCAZODK4DL/graph.json","events_json":"https://pith.science/api/pith-number/CNPZACM6JA35LHJDGCAZODK4DL/events.json","paper":"https://pith.science/paper/CNPZACM6"},"agent_actions":{"view_html":"https://pith.science/pith/CNPZACM6JA35LHJDGCAZODK4DL","download_json":"https://pith.science/pith/CNPZACM6JA35LHJDGCAZODK4DL.json","view_paper":"https://pith.science/paper/CNPZACM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02465&json=true","fetch_graph":"https://pith.science/api/pith-number/CNPZACM6JA35LHJDGCAZODK4DL/graph.json","fetch_events":"https://pith.science/api/pith-number/CNPZACM6JA35LHJDGCAZODK4DL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNPZACM6JA35LHJDGCAZODK4DL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNPZACM6JA35LHJDGCAZODK4DL/action/storage_attestation","attest_author":"https://pith.science/pith/CNPZACM6JA35LHJDGCAZODK4DL/action/author_attestation","sign_citation":"https://pith.science/pith/CNPZACM6JA35LHJDGCAZODK4DL/action/citation_signature","submit_replication":"https://pith.science/pith/CNPZACM6JA35LHJDGCAZODK4DL/action/replication_record"}},"created_at":"2026-07-05T03:54:29.189915+00:00","updated_at":"2026-07-05T03:54:29.189915+00:00"}