{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:S56HPH5K3GASV5CW36FUAYXHVJ","short_pith_number":"pith:S56HPH5K","canonical_record":{"source":{"id":"2407.10971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"4c38a4c31046367dcbd26fe3597e9b7c785dd860d81213f8baea6d97f1a70b33","abstract_canon_sha256":"8aff308e8d1d847ac3eb055f961349b28067c8131ea22e4a17f9cf930a818f75"},"schema_version":"1.0"},"canonical_sha256":"977c779faad9812af456df8b4062e7aa7adee46b08ba26b639097130d9bf9369","source":{"kind":"arxiv","id":"2407.10971","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:S56HPH5K3GASV5CW36FUAYXHVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"4c38a4c31046367dcbd26fe3597e9b7c785dd860d81213f8baea6d97f1a70b33","abstract_canon_sha256":"8aff308e8d1d847ac3eb055f961349b28067c8131ea22e4a17f9cf930a818f75"},"schema_version":"1.0"},"canonical_sha256":"977c779faad9812af456df8b4062e7aa7adee46b08ba26b639097130d9bf9369","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:07.088881Z","signature_b64":"Ah7CPkmMwA94VaogERbrh6ut6bWF5q6J+uNqwEvRJfIGiMBmXJwtlbUswMxaP9ph0vBX8ustgHiSfSgkxwUYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"977c779faad9812af456df8b4062e7aa7adee46b08ba26b639097130d9bf9369","last_reissued_at":"2026-07-05T08:44:07.088379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:07.088379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10971","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"azSPviziziikEDYtY9OkCdmLSvVK4HZgbkrK12z1S9C1dZ/4KmRrF7rf5f/c+6bQMB7vWULCyKUDW1gBwLq9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:53:32.859104Z"},"content_sha256":"c8b75a7976e3e53c28c59414dd27a2f967f29050dc54934c12122d4b0180f2f9","schema_version":"1.0","event_id":"sha256:c8b75a7976e3e53c28c59414dd27a2f967f29050dc54934c12122d4b0180f2f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:S56HPH5K3GASV5CW36FUAYXHVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Walking the Values in Bayesian Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Abate, Konstantinos Gatsis, Michael A. Osborne, Ondrej Bajgar","submitted_at":"2024-07-15T17:59:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10971","kind":"arxiv","version":1},"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/2407.10971/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":"2026-07-05T08:44:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F3IizoLMatJT9aMlBhlCXWqyNJYZlcFJauj61/VpKcmY2JWvYySmcXCDzsLfy8L1csOWFbhubEtZsDXqaUDlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:53:32.859646Z"},"content_sha256":"536ef44f8da4871d5833e470af7606368ae62f1b32d8617ec26b5329268847a7","schema_version":"1.0","event_id":"sha256:536ef44f8da4871d5833e470af7606368ae62f1b32d8617ec26b5329268847a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ/bundle.json","state_url":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S56HPH5K3GASV5CW36FUAYXHVJ/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":"2026-08-06T19:53:32Z","links":{"resolver":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ","bundle":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ/bundle.json","state":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S56HPH5K3GASV5CW36FUAYXHVJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FBXKQ/HClj3Qp/+Pn2qZ8JzpSvn9h692D/F5rjCO2oZTKVDvQfoCAJifWtO5IyRyXw8jyHW/I86IcsbWojJlDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:53:32.867878Z","bundle_sha256":"747e646a7a42c78c8f01e9fccb5a01cfc68852d24b53efeada95fa2dde6ce3b7"}}