{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GZ75J4UMPR6VRAYDAYU5UXSAOX","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":"ec36733ebf8c2863c552174c2cec4d186129940ba980c159a4d10922e286b280","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-05T06:32:38Z","title_canon_sha256":"9cc2c060562af578b6827fb7377a7ea5a2ecbe2b9e83a793b4a151e000a21502"},"schema_version":"1.0","source":{"id":"2009.02476","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.02476","created_at":"2026-07-05T06:25:56Z"},{"alias_kind":"arxiv_version","alias_value":"2009.02476v4","created_at":"2026-07-05T06:25:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.02476","created_at":"2026-07-05T06:25:56Z"},{"alias_kind":"pith_short_12","alias_value":"GZ75J4UMPR6V","created_at":"2026-07-05T06:25:56Z"},{"alias_kind":"pith_short_16","alias_value":"GZ75J4UMPR6VRAYD","created_at":"2026-07-05T06:25:56Z"},{"alias_kind":"pith_short_8","alias_value":"GZ75J4UM","created_at":"2026-07-05T06:25:56Z"}],"graph_snapshots":[{"event_id":"sha256:cc5b0b0dec2fec322626bee6ea83e3135c3991317e35cd23de2d5798dc50030d","target":"graph","created_at":"2026-07-05T06:25:56Z","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/2009.02476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Successful teaching requires an assumption of how the learner learns - how the learner uses experiences from the world to update their internal states. We investigate what expectations people have about a learner when they teach them in an online manner using rewards and punishment. We focus on a common reinforcement learning method, Q-learning, and examine what assumptions people have using a behavioral experiment. To do so, we first establish a normative standard, by formulating the problem as a machine teaching optimization problem. To solve the machine teaching optimization problem, we use","authors_text":"Joseph L. Austerweil, Mark K. Ho, Xiaojin Zhu, Xuezhou Zhang, Yun-Shiuan Chuang, Yuzhe Ma","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-05T06:32:38Z","title":"Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.02476","kind":"arxiv","version":4},"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:d87e71ff43d043b8d9e021501aefa9c9e9d0aa168a8161c8da4b179ccb100de9","target":"record","created_at":"2026-07-05T06:25:56Z","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":"ec36733ebf8c2863c552174c2cec4d186129940ba980c159a4d10922e286b280","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-05T06:32:38Z","title_canon_sha256":"9cc2c060562af578b6827fb7377a7ea5a2ecbe2b9e83a793b4a151e000a21502"},"schema_version":"1.0","source":{"id":"2009.02476","kind":"arxiv","version":4}},"canonical_sha256":"367fd4f28c7c7d5883030629da5e4075f173f8cd8de82cd7a55e30afdb983d77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"367fd4f28c7c7d5883030629da5e4075f173f8cd8de82cd7a55e30afdb983d77","first_computed_at":"2026-07-05T06:25:56.304707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:25:56.304707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eRQvVlTAiMhmCeuyCpByJTaaP1EnlMe9fQwGgDH6H0C9hyDlCAIR+8h2JJNvGG85ir3CUp791332HJwjE+xlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:25:56.305095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.02476","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d87e71ff43d043b8d9e021501aefa9c9e9d0aa168a8161c8da4b179ccb100de9","sha256:cc5b0b0dec2fec322626bee6ea83e3135c3991317e35cd23de2d5798dc50030d"],"state_sha256":"4ce0a14efca19a3f874ac5bd44477e74435cb6ed8028349707d58227d6ee8e20"}