{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MQNGCGPXQJOYVBMTTCQKKCHPCM","short_pith_number":"pith:MQNGCGPX","schema_version":"1.0","canonical_sha256":"641a6119f7825d8a859398a0a508ef1305aa19a99da002966f664d97cbd6b8ab","source":{"kind":"arxiv","id":"2505.10151","version":1},"attestation_state":"computed","paper":{"title":"Training People to Reward Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Endong Sun, Matthew Howard, Yuqing Zhu","submitted_at":"2025-05-15T10:23:56Z","abstract_excerpt":"Learning from demonstration (LfD) is a technique that allows expert teachers to teach task-oriented skills to robotic systems. However, the most effective way of guiding novice teachers to approach expert-level demonstrations quantitatively for specific teaching tasks remains an open question. To this end, this paper investigates the use of machine teaching (MT) to guide novice teachers to improve their teaching skills based on reinforcement learning from demonstration (RLfD). The paper reports an experiment in which novices receive MT-derived guidance to train their ability to teach a given m"},"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":"2505.10151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-15T10:23:56Z","cross_cats_sorted":[],"title_canon_sha256":"6c4723aeef4bf8d245d39e1018dea7f3418ce47114e80be8da5ce467e693cc7c","abstract_canon_sha256":"fac5e0b9112f91881572fce5d5de5b65e907513296ce9533134ec78a8ab0af3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:34.222983Z","signature_b64":"hbt9I8IvT727FJDy8TdufnvUYxqSds6piE138IOdfMurizFnQum1WhseBj09+qnnHuICLlZmyPEx8L+1BbMSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641a6119f7825d8a859398a0a508ef1305aa19a99da002966f664d97cbd6b8ab","last_reissued_at":"2026-07-05T11:03:34.222347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:34.222347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training People to Reward Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Endong Sun, Matthew Howard, Yuqing Zhu","submitted_at":"2025-05-15T10:23:56Z","abstract_excerpt":"Learning from demonstration (LfD) is a technique that allows expert teachers to teach task-oriented skills to robotic systems. However, the most effective way of guiding novice teachers to approach expert-level demonstrations quantitatively for specific teaching tasks remains an open question. To this end, this paper investigates the use of machine teaching (MT) to guide novice teachers to improve their teaching skills based on reinforcement learning from demonstration (RLfD). The paper reports an experiment in which novices receive MT-derived guidance to train their ability to teach a given m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10151","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/2505.10151/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":"2505.10151","created_at":"2026-07-05T11:03:34.222424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10151v1","created_at":"2026-07-05T11:03:34.222424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10151","created_at":"2026-07-05T11:03:34.222424+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQNGCGPXQJOY","created_at":"2026-07-05T11:03:34.222424+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQNGCGPXQJOYVBMT","created_at":"2026-07-05T11:03:34.222424+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQNGCGPX","created_at":"2026-07-05T11:03:34.222424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM","json":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM.json","graph_json":"https://pith.science/api/pith-number/MQNGCGPXQJOYVBMTTCQKKCHPCM/graph.json","events_json":"https://pith.science/api/pith-number/MQNGCGPXQJOYVBMTTCQKKCHPCM/events.json","paper":"https://pith.science/paper/MQNGCGPX"},"agent_actions":{"view_html":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM","download_json":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM.json","view_paper":"https://pith.science/paper/MQNGCGPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10151&json=true","fetch_graph":"https://pith.science/api/pith-number/MQNGCGPXQJOYVBMTTCQKKCHPCM/graph.json","fetch_events":"https://pith.science/api/pith-number/MQNGCGPXQJOYVBMTTCQKKCHPCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/action/storage_attestation","attest_author":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/action/author_attestation","sign_citation":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/action/citation_signature","submit_replication":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/action/replication_record"}},"created_at":"2026-07-05T11:03:34.222424+00:00","updated_at":"2026-07-05T11:03:34.222424+00:00"}