{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:MRHKY66BAT72VM4FE3SIV3MNUC","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":"1ebe0a7e5420bc408a862f4e79cc5218b72154d2a188c3595c4b39f96b8e6924","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-20T15:18:02Z","title_canon_sha256":"36bee3f6dbc47f585c6d337bc57de9984f5bbb972430f300b84f9ece816d53e5"},"schema_version":"1.0","source":{"id":"1206.5290","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.5290","created_at":"2026-05-18T03:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"1206.5290v1","created_at":"2026-05-18T03:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.5290","created_at":"2026-05-18T03:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"MRHKY66BAT72","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"MRHKY66BAT72VM4F","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"MRHKY66B","created_at":"2026-05-18T12:27:14Z"}],"graph_snapshots":[{"event_id":"sha256:b2e78881a213f3b7a197f4fcb1026051e4d92a954f09a61a3d4b1cb719e95c17","target":"graph","created_at":"2026-05-18T03:52:40Z","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"},"paper":{"abstract_excerpt":"The goal of imitation learning is for an apprentice to learn how to behave in a stochastic environment by observing a mentor demonstrating the correct behavior. Accurate prior knowledge about the correct behavior can reduce the need for demonstrations from the mentor. We present a novel approach to encoding prior knowledge about the correct behavior, where we assume that this prior knowledge takes the form of a Markov Decision Process (MDP) that is used by the apprentice as a rough and imperfect model of the mentor's behavior. Specifically, taking a Bayesian approach, we treat the value of a p","authors_text":"Robert E. Schapire, Umar Syed","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-20T15:18:02Z","title":"Imitation Learning with a Value-Based Prior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.5290","kind":"arxiv","version":1},"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":"sha256:37d18543ed7bf946366549c1e95b636ab7bae48b5cec23278a67858e9bf1fde0","target":"record","created_at":"2026-05-18T03:52:40Z","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":"1ebe0a7e5420bc408a862f4e79cc5218b72154d2a188c3595c4b39f96b8e6924","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-20T15:18:02Z","title_canon_sha256":"36bee3f6dbc47f585c6d337bc57de9984f5bbb972430f300b84f9ece816d53e5"},"schema_version":"1.0","source":{"id":"1206.5290","kind":"arxiv","version":1}},"canonical_sha256":"644eac7bc104ffaab38526e48aed8da09b9c5808a3373f3a54473391539f5868","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"644eac7bc104ffaab38526e48aed8da09b9c5808a3373f3a54473391539f5868","first_computed_at":"2026-05-18T03:52:40.513669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:52:40.513669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EwT0UjWtGCs2gZOMjMrLeiWlDjsUE3ukRHWCmOjGpKWBmeBGs7y7hk9PnAb/16obx4O2v6mF3HTt+w+6E6SjCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:52:40.514193Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.5290","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37d18543ed7bf946366549c1e95b636ab7bae48b5cec23278a67858e9bf1fde0","sha256:b2e78881a213f3b7a197f4fcb1026051e4d92a954f09a61a3d4b1cb719e95c17"],"state_sha256":"60c10d833c313373064197ea36449ca6d62d41302b387efdbbd3ffd20ea5ea79"}