{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CX6ROFZ2TOSIJZ5KJKBIBDNGFE","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":"268aef5fc9899e833b746ee6309aead1a55f718dbcfc6a5fef263dc148318890","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2018-07-13T12:33:07Z","title_canon_sha256":"2bb678ee203396bcf67e559bf4154f91d8c13baf1ce4b627dcb9f88c39dc1e1e"},"schema_version":"1.0","source":{"id":"1807.05037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05037","created_at":"2026-05-18T00:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05037v1","created_at":"2026-05-18T00:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05037","created_at":"2026-05-18T00:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"CX6ROFZ2TOSI","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CX6ROFZ2TOSIJZ5K","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CX6ROFZ2","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:e6c2e8da73f0a97fe458033e0ac5032bdbbb2785bcf61213eb168b322cf0e587","target":"graph","created_at":"2026-05-18T00:10:49Z","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":"We introduce a new generative model for human planning under the Bayesian Inverse Reinforcement Learning (BIRL) framework which takes into account the fact that humans often plan using hierarchical strategies. We describe the Bayesian Inverse Hierarchical RL (BIHRL) algorithm for inferring the values of hierarchical planners, and use an illustrative toy model to show that BIHRL retains accuracy where standard BIRL fails. Furthermore, BIHRL is able to accurately predict the goals of `Wikispeedia' game players, with inclusion of hierarchical structure in the model resulting in a large boost in a","authors_text":"Chris Cundy, Daniel Filan","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2018-07-13T12:33:07Z","title":"Exploring Hierarchy-Aware Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05037","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":"sha256:479e7b4517f702e237807a61908cefa51ee179a0a14007cacb22bf8f2b2d7d3d","target":"record","created_at":"2026-05-18T00:10:49Z","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":"268aef5fc9899e833b746ee6309aead1a55f718dbcfc6a5fef263dc148318890","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2018-07-13T12:33:07Z","title_canon_sha256":"2bb678ee203396bcf67e559bf4154f91d8c13baf1ce4b627dcb9f88c39dc1e1e"},"schema_version":"1.0","source":{"id":"1807.05037","kind":"arxiv","version":1}},"canonical_sha256":"15fd17173a9ba484e7aa4a82808da62909db99d2521d4fba78043b9dadd27b0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15fd17173a9ba484e7aa4a82808da62909db99d2521d4fba78043b9dadd27b0e","first_computed_at":"2026-05-18T00:10:49.196230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:49.196230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/lU4PDRWP2UrjOVu8Koh6/c8yW+XrHhht4vn6PCi/kM5JHPZaB3+W9snjpxDFbPkkbTOCP9yT6tUdNDXOOavAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:49.196859Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.05037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:479e7b4517f702e237807a61908cefa51ee179a0a14007cacb22bf8f2b2d7d3d","sha256:e6c2e8da73f0a97fe458033e0ac5032bdbbb2785bcf61213eb168b322cf0e587"],"state_sha256":"564dfbc31264827ae640fd0951079bb36ac1dd8c28e31c4512a0f3de009886b3"}