{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AU24NU5UGWQ762BAHGYDFLNPWX","short_pith_number":"pith:AU24NU5U","canonical_record":{"source":{"id":"2006.13900","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:35:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"310af64471e37c5464f345107ad94a326ad6e7de5aff9b0ca195c3e2883c6c5e","abstract_canon_sha256":"9051643dc57a55557e65a09ff4b06245609003fa4f9016bbc0cf419bf9f1ed4a"},"schema_version":"1.0"},"canonical_sha256":"0535c6d3b435a1ff682039b032adafb5cc9fb687e62737b93d8c663aabe12b73","source":{"kind":"arxiv","id":"2006.13900","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13900","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13900v3","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13900","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_12","alias_value":"AU24NU5UGWQ7","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_16","alias_value":"AU24NU5UGWQ762BA","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_8","alias_value":"AU24NU5U","created_at":"2026-07-05T02:24:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AU24NU5UGWQ762BAHGYDFLNPWX","target":"record","payload":{"canonical_record":{"source":{"id":"2006.13900","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:35:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"310af64471e37c5464f345107ad94a326ad6e7de5aff9b0ca195c3e2883c6c5e","abstract_canon_sha256":"9051643dc57a55557e65a09ff4b06245609003fa4f9016bbc0cf419bf9f1ed4a"},"schema_version":"1.0"},"canonical_sha256":"0535c6d3b435a1ff682039b032adafb5cc9fb687e62737b93d8c663aabe12b73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:10.109442Z","signature_b64":"YDNc4c3Ac6ytV67YZ/SaZXrpUuzWcssblKRSYLm2kJmQOCtTHqWzh9715q5AHAqET/KHjo/eRZN5wvCqKHGfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0535c6d3b435a1ff682039b032adafb5cc9fb687e62737b93d8c663aabe12b73","last_reissued_at":"2026-07-05T02:24:10.109007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:10.109007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.13900","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:24:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gt0/8xyvpahK1uk7QQr4d81xUIe8WohPum3RBCWYL9YPjSliJe9JtGYSVdkw1o1PD1NB7YmFJtPx3uCllLqlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:22:55.403031Z"},"content_sha256":"83de17152de097b52298a6fb3dfb131de556138d3a0c855a32e3a37f3bc7d62d","schema_version":"1.0","event_id":"sha256:83de17152de097b52298a6fb3dfb131de556138d3a0c855a32e3a37f3bc7d62d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AU24NU5UGWQ762BAHGYDFLNPWX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantifying Differences in Reward Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Gleave, Jan Leike, Michael Dennis, Shane Legg, Stuart Russell","submitted_at":"2020-06-24T17:35:15Z","abstract_excerpt":"For many tasks, the reward function is inaccessible to introspection or too complex to be specified procedurally, and must instead be learned from user data. Prior work has evaluated learned reward functions by evaluating policies optimized for the learned reward. However, this method cannot distinguish between the learned reward function failing to reflect user preferences and the policy optimization process failing to optimize the learned reward. Moreover, this method can only tell us about behavior in the evaluation environment, but the reward may incentivize very different behavior in even"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13900","kind":"arxiv","version":3},"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/2006.13900/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":"2026-07-05T02:24:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fz/4RoBWuCzL/vCUIYqlqkXT6iPezXOXb0bPjuQ6zCkKxqnxmTmlEoJjwF+gpKC/HGwp0HeKTbPLasros5+LCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:22:55.403951Z"},"content_sha256":"0da9d805c5cbdb7765a57300caa85c417b4f2885078e6c342993c9936117bacc","schema_version":"1.0","event_id":"sha256:0da9d805c5cbdb7765a57300caa85c417b4f2885078e6c342993c9936117bacc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AU24NU5UGWQ762BAHGYDFLNPWX/bundle.json","state_url":"https://pith.science/pith/AU24NU5UGWQ762BAHGYDFLNPWX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AU24NU5UGWQ762BAHGYDFLNPWX/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":"2026-08-04T01:22:55Z","links":{"resolver":"https://pith.science/pith/AU24NU5UGWQ762BAHGYDFLNPWX","bundle":"https://pith.science/pith/AU24NU5UGWQ762BAHGYDFLNPWX/bundle.json","state":"https://pith.science/pith/AU24NU5UGWQ762BAHGYDFLNPWX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AU24NU5UGWQ762BAHGYDFLNPWX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AU24NU5UGWQ762BAHGYDFLNPWX","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":"9051643dc57a55557e65a09ff4b06245609003fa4f9016bbc0cf419bf9f1ed4a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:35:15Z","title_canon_sha256":"310af64471e37c5464f345107ad94a326ad6e7de5aff9b0ca195c3e2883c6c5e"},"schema_version":"1.0","source":{"id":"2006.13900","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13900","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13900v3","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13900","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_12","alias_value":"AU24NU5UGWQ7","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_16","alias_value":"AU24NU5UGWQ762BA","created_at":"2026-07-05T02:24:10Z"},{"alias_kind":"pith_short_8","alias_value":"AU24NU5U","created_at":"2026-07-05T02:24:10Z"}],"graph_snapshots":[{"event_id":"sha256:0da9d805c5cbdb7765a57300caa85c417b4f2885078e6c342993c9936117bacc","target":"graph","created_at":"2026-07-05T02:24:10Z","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/2006.13900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For many tasks, the reward function is inaccessible to introspection or too complex to be specified procedurally, and must instead be learned from user data. Prior work has evaluated learned reward functions by evaluating policies optimized for the learned reward. However, this method cannot distinguish between the learned reward function failing to reflect user preferences and the policy optimization process failing to optimize the learned reward. Moreover, this method can only tell us about behavior in the evaluation environment, but the reward may incentivize very different behavior in even","authors_text":"Adam Gleave, Jan Leike, Michael Dennis, Shane Legg, Stuart Russell","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:35:15Z","title":"Quantifying Differences in Reward Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13900","kind":"arxiv","version":3},"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":"sha256:83de17152de097b52298a6fb3dfb131de556138d3a0c855a32e3a37f3bc7d62d","target":"record","created_at":"2026-07-05T02:24:10Z","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":"9051643dc57a55557e65a09ff4b06245609003fa4f9016bbc0cf419bf9f1ed4a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T17:35:15Z","title_canon_sha256":"310af64471e37c5464f345107ad94a326ad6e7de5aff9b0ca195c3e2883c6c5e"},"schema_version":"1.0","source":{"id":"2006.13900","kind":"arxiv","version":3}},"canonical_sha256":"0535c6d3b435a1ff682039b032adafb5cc9fb687e62737b93d8c663aabe12b73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0535c6d3b435a1ff682039b032adafb5cc9fb687e62737b93d8c663aabe12b73","first_computed_at":"2026-07-05T02:24:10.109007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:10.109007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YDNc4c3Ac6ytV67YZ/SaZXrpUuzWcssblKRSYLm2kJmQOCtTHqWzh9715q5AHAqET/KHjo/eRZN5wvCqKHGfDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:10.109442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.13900","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83de17152de097b52298a6fb3dfb131de556138d3a0c855a32e3a37f3bc7d62d","sha256:0da9d805c5cbdb7765a57300caa85c417b4f2885078e6c342993c9936117bacc"],"state_sha256":"105f30c235bb88dde7492924f86b591831a7b177c1df5f03da8834aa311af63d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MCdr21YjplUIeW01MEtOxmHuvnRPDaUc/k/mtns2lUmZaPWBm8hs7xElBGY5gAooSgaaqiLpSf+tZ4dUzPs3DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:22:55.409956Z","bundle_sha256":"65135d7e871f45f62fca5e083827c3a6e84a3bf12180c1a77fdd285a03878633"}}