{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S56HPH5K3GASV5CW36FUAYXHVJ","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":"8aff308e8d1d847ac3eb055f961349b28067c8131ea22e4a17f9cf930a818f75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:52Z","title_canon_sha256":"4c38a4c31046367dcbd26fe3597e9b7c785dd860d81213f8baea6d97f1a70b33"},"schema_version":"1.0","source":{"id":"2407.10971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10971","created_at":"2026-07-05T08:44:07Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10971v1","created_at":"2026-07-05T08:44:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10971","created_at":"2026-07-05T08:44:07Z"},{"alias_kind":"pith_short_12","alias_value":"S56HPH5K3GAS","created_at":"2026-07-05T08:44:07Z"},{"alias_kind":"pith_short_16","alias_value":"S56HPH5K3GASV5CW","created_at":"2026-07-05T08:44:07Z"},{"alias_kind":"pith_short_8","alias_value":"S56HPH5K","created_at":"2026-07-05T08:44:07Z"}],"graph_snapshots":[{"event_id":"sha256:536ef44f8da4871d5833e470af7606368ae62f1b32d8617ec26b5329268847a7","target":"graph","created_at":"2026-07-05T08:44:07Z","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/2407.10971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of Bayesian inverse reinforcement learning (IRL) is recovering a posterior distribution over reward functions using a set of demonstrations from an expert optimizing for a reward unknown to the learner. The resulting posterior over rewards can then be used to synthesize an apprentice policy that performs well on the same or a similar task. A key challenge in Bayesian IRL is bridging the computational gap between the hypothesis space of possible rewards and the likelihood, often defined in terms of Q values: vanilla Bayesian IRL needs to solve the costly forward planning problem - goin","authors_text":"Alessandro Abate, Konstantinos Gatsis, Michael A. Osborne, Ondrej Bajgar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:52Z","title":"Walking the Values in Bayesian Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10971","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:c8b75a7976e3e53c28c59414dd27a2f967f29050dc54934c12122d4b0180f2f9","target":"record","created_at":"2026-07-05T08:44:07Z","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":"8aff308e8d1d847ac3eb055f961349b28067c8131ea22e4a17f9cf930a818f75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:52Z","title_canon_sha256":"4c38a4c31046367dcbd26fe3597e9b7c785dd860d81213f8baea6d97f1a70b33"},"schema_version":"1.0","source":{"id":"2407.10971","kind":"arxiv","version":1}},"canonical_sha256":"977c779faad9812af456df8b4062e7aa7adee46b08ba26b639097130d9bf9369","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"977c779faad9812af456df8b4062e7aa7adee46b08ba26b639097130d9bf9369","first_computed_at":"2026-07-05T08:44:07.088379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:07.088379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ah7CPkmMwA94VaogERbrh6ut6bWF5q6J+uNqwEvRJfIGiMBmXJwtlbUswMxaP9ph0vBX8ustgHiSfSgkxwUYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:07.088881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8b75a7976e3e53c28c59414dd27a2f967f29050dc54934c12122d4b0180f2f9","sha256:536ef44f8da4871d5833e470af7606368ae62f1b32d8617ec26b5329268847a7"],"state_sha256":"e9348eb98028c4ad42e016a2ca4152ce7b6d6fff5aba7b1b2ced006191b28af6"}