{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:OJ45KLNOUIZIWOOYEBDFIE4CDE","short_pith_number":"pith:OJ45KLNO","canonical_record":{"source":{"id":"2006.09324","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T17:06:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"521f837cdead54b8c6fb784e1be13dc5614befe569432d485b0b159130679427","abstract_canon_sha256":"398edb1b371d95477fe720275d69f4e602cac1b753eb697d854b2f5e13fdf5b1"},"schema_version":"1.0"},"canonical_sha256":"7279d52daea2328b39d82046541382190581bdc1117cc0f13ce3c6dfebb036fc","source":{"kind":"arxiv","id":"2006.09324","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:OJ45KLNOUIZIWOOYEBDFIE4CDE","target":"record","payload":{"canonical_record":{"source":{"id":"2006.09324","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T17:06:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"521f837cdead54b8c6fb784e1be13dc5614befe569432d485b0b159130679427","abstract_canon_sha256":"398edb1b371d95477fe720275d69f4e602cac1b753eb697d854b2f5e13fdf5b1"},"schema_version":"1.0"},"canonical_sha256":"7279d52daea2328b39d82046541382190581bdc1117cc0f13ce3c6dfebb036fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:55.383018Z","signature_b64":"NixznmjIm1qzkne6ssIzjCjkt9nqkeiIdhdKHw/ZVH3lxfXBtsnRZH5H7zclsSvDLHJR9WXquUQaU62C7XBbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7279d52daea2328b39d82046541382190581bdc1117cc0f13ce3c6dfebb036fc","last_reissued_at":"2026-07-05T02:20:55.382507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:55.382507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.09324","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:20:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hKnLdK5yuz1vhjtp0bOfndW6O3iOVZsisZZb3+vAh79qcQB2vHdW6oaWAx4kK1a8FhX3Hfw/DVR1zhWEMeh2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T00:28:10.281565Z"},"content_sha256":"811e77943569261548d159ca5131a86a0eee86ac9eb275551031ed8aeb6ac7d5","schema_version":"1.0","event_id":"sha256:811e77943569261548d159ca5131a86a0eee86ac9eb275551031ed8aeb6ac7d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:OJ45KLNOUIZIWOOYEBDFIE4CDE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Sample Complexity of Teaching-by-Reinforcement on Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adish Singla, Shubham Kumar Bharti, Xiaojin Zhu, Xuezhou Zhang, Yuzhe Ma","submitted_at":"2020-06-16T17:06:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09324","kind":"arxiv","version":2},"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/2006.09324/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:20:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+9UCdmmFTEaY+TvJ5A2Xohjit2T66xX5hgw5srp8DrvL5aCTmcc1QOlOGylJqNIwF2gyTgN+z1k8UDsBiP8QBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T00:28:10.282229Z"},"content_sha256":"d027061431ef398205a2b3e7866acc20130e41189fdb8746a4cfa2b44bf74d14","schema_version":"1.0","event_id":"sha256:d027061431ef398205a2b3e7866acc20130e41189fdb8746a4cfa2b44bf74d14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/bundle.json","state_url":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T00:28:10Z","links":{"resolver":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE","bundle":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/bundle.json","state":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mEHaoVGsYsI1RgZGqaf41pcWtedoqfnjAJ0HMLJMAd5C+C8Xgf8l7rvaIiAUOnPh1VHKFSSwabJYFl3nioI+Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T00:28:10.287754Z","bundle_sha256":"770c1baf44723c18f2913795f5dbabe4175757e774a6528fae98a65ed512e945"}}