{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OJ45KLNOUIZIWOOYEBDFIE4CDE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"398edb1b371d95477fe720275d69f4e602cac1b753eb697d854b2f5e13fdf5b1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T17:06:04Z","title_canon_sha256":"521f837cdead54b8c6fb784e1be13dc5614befe569432d485b0b159130679427"},"schema_version":"1.0","source":{"id":"2006.09324","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.09324","created_at":"2026-07-05T02:20:55Z"},{"alias_kind":"arxiv_version","alias_value":"2006.09324v2","created_at":"2026-07-05T02:20:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09324","created_at":"2026-07-05T02:20:55Z"},{"alias_kind":"pith_short_12","alias_value":"OJ45KLNOUIZI","created_at":"2026-07-05T02:20:55Z"},{"alias_kind":"pith_short_16","alias_value":"OJ45KLNOUIZIWOOY","created_at":"2026-07-05T02:20:55Z"},{"alias_kind":"pith_short_8","alias_value":"OJ45KLNO","created_at":"2026-07-05T02:20:55Z"}],"graph_snapshots":[{"event_id":"sha256:d027061431ef398205a2b3e7866acc20130e41189fdb8746a4cfa2b44bf74d14","target":"graph","created_at":"2026-07-05T02:20:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.09324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the sample complexity of teaching, termed as \"teaching dimension\" (TDim) in the literature, for the teaching-by-reinforcement paradigm, where the teacher guides the student through rewards. This is distinct from the teaching-by-demonstration paradigm motivated by robotics applications, where the teacher teaches by providing demonstrations of state/action trajectories. The teaching-by-reinforcement paradigm applies to a wider range of real-world settings where a demonstration is inconvenient, but has not been studied systematically. In this paper, we focus on a specific family of reinf","authors_text":"Adish Singla, Shubham Kumar Bharti, Xiaojin Zhu, Xuezhou Zhang, Yuzhe Ma","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T17:06:04Z","title":"The Sample Complexity of Teaching-by-Reinforcement on Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09324","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:811e77943569261548d159ca5131a86a0eee86ac9eb275551031ed8aeb6ac7d5","target":"record","created_at":"2026-07-05T02:20:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"398edb1b371d95477fe720275d69f4e602cac1b753eb697d854b2f5e13fdf5b1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T17:06:04Z","title_canon_sha256":"521f837cdead54b8c6fb784e1be13dc5614befe569432d485b0b159130679427"},"schema_version":"1.0","source":{"id":"2006.09324","kind":"arxiv","version":2}},"canonical_sha256":"7279d52daea2328b39d82046541382190581bdc1117cc0f13ce3c6dfebb036fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7279d52daea2328b39d82046541382190581bdc1117cc0f13ce3c6dfebb036fc","first_computed_at":"2026-07-05T02:20:55.382507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:55.382507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NixznmjIm1qzkne6ssIzjCjkt9nqkeiIdhdKHw/ZVH3lxfXBtsnRZH5H7zclsSvDLHJR9WXquUQaU62C7XBbDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:55.383018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.09324","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:811e77943569261548d159ca5131a86a0eee86ac9eb275551031ed8aeb6ac7d5","sha256:d027061431ef398205a2b3e7866acc20130e41189fdb8746a4cfa2b44bf74d14"],"state_sha256":"77416d911bac1acbe6ab3d01b3a34acf6bb831ad6b22d21be6bcc887540095de"}