{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NIYFI6FYJGKVGEGNUQPWCY5WBF","short_pith_number":"pith:NIYFI6FY","canonical_record":{"source":{"id":"2309.15257","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T20:31:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4c2072843235c94aafa98d923af3b98ae84877da8f7b682351ffca05913e55a","abstract_canon_sha256":"bb4b609e3c025b4b21293f286fc47f90777cee34b388cadf8b97f68be7f29e45"},"schema_version":"1.0"},"canonical_sha256":"6a305478b849955310cda41f6163b6094ef97b0125efee55dd5f9bce9ef1f459","source":{"kind":"arxiv","id":"2309.15257","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15257","created_at":"2026-07-05T09:48:11Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15257v3","created_at":"2026-07-05T09:48:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15257","created_at":"2026-07-05T09:48:11Z"},{"alias_kind":"pith_short_12","alias_value":"NIYFI6FYJGKV","created_at":"2026-07-05T09:48:11Z"},{"alias_kind":"pith_short_16","alias_value":"NIYFI6FYJGKVGEGN","created_at":"2026-07-05T09:48:11Z"},{"alias_kind":"pith_short_8","alias_value":"NIYFI6FY","created_at":"2026-07-05T09:48:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NIYFI6FYJGKVGEGNUQPWCY5WBF","target":"record","payload":{"canonical_record":{"source":{"id":"2309.15257","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T20:31:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4c2072843235c94aafa98d923af3b98ae84877da8f7b682351ffca05913e55a","abstract_canon_sha256":"bb4b609e3c025b4b21293f286fc47f90777cee34b388cadf8b97f68be7f29e45"},"schema_version":"1.0"},"canonical_sha256":"6a305478b849955310cda41f6163b6094ef97b0125efee55dd5f9bce9ef1f459","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:11.329939Z","signature_b64":"+itLMBzlRoGZTCNEOpq789D/RO/Xr3kTsLmgeyloNA5qUUyVdCz1cdPvjGVb17Lwqr73BU8j5iqRdZMRWZm7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a305478b849955310cda41f6163b6094ef97b0125efee55dd5f9bce9ef1f459","last_reissued_at":"2026-07-05T09:48:11.329505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:11.329505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.15257","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":"2026-07-05T09:48:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3AjQLMb2KgCyuKo3fLuWQf/x+StEZsIPDCLlouR7Ot9i54VttTF3Fo0sMP29yGvm3j84nEvMr2wYLtLYT+PZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:06:41.725938Z"},"content_sha256":"997ec59586386506e6f984286e81569eafb048ae2dc1e19214ddf7bd624ab8c3","schema_version":"1.0","event_id":"sha256:997ec59586386506e6f984286e81569eafb048ae2dc1e19214ddf7bd624ab8c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NIYFI6FYJGKVGEGNUQPWCY5WBF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STARC: A General Framework For Quantifying Differences Between Reward Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam Gleave, Alessandro Abate, Erik Jenner, Joar Skalse, Lucy Farnik, Sumeet Ramesh Motwani","submitted_at":"2023-09-26T20:31:19Z","abstract_excerpt":"In order to solve a task using reinforcement learning, it is necessary to first formalise the goal of that task as a reward function. However, for many real-world tasks, it is very difficult to manually specify a reward function that never incentivises undesirable behaviour. As a result, it is increasingly popular to use reward learning algorithms, which attempt to learn a reward function from data. However, the theoretical foundations of reward learning are not yet well-developed. In particular, it is typically not known when a given reward learning algorithm with high probability will learn "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15257","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/2309.15257/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":"2026-07-05T09:48:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tFKbpUENujsiLT/1ZY9mSi8KTDe6tVHlgRA3YiPxUoynMFxuIQu+9V8GSHYTS+83Runk/IDt9uAraW+pt5L/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:06:41.726473Z"},"content_sha256":"11648d7a0a16eb341c90413fca508d381ec37434fec9ff4ac867fc522b70b81d","schema_version":"1.0","event_id":"sha256:11648d7a0a16eb341c90413fca508d381ec37434fec9ff4ac867fc522b70b81d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIYFI6FYJGKVGEGNUQPWCY5WBF/bundle.json","state_url":"https://pith.science/pith/NIYFI6FYJGKVGEGNUQPWCY5WBF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIYFI6FYJGKVGEGNUQPWCY5WBF/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":"2026-08-22T08:06:41Z","links":{"resolver":"https://pith.science/pith/NIYFI6FYJGKVGEGNUQPWCY5WBF","bundle":"https://pith.science/pith/NIYFI6FYJGKVGEGNUQPWCY5WBF/bundle.json","state":"https://pith.science/pith/NIYFI6FYJGKVGEGNUQPWCY5WBF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIYFI6FYJGKVGEGNUQPWCY5WBF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NIYFI6FYJGKVGEGNUQPWCY5WBF","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":"bb4b609e3c025b4b21293f286fc47f90777cee34b388cadf8b97f68be7f29e45","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T20:31:19Z","title_canon_sha256":"c4c2072843235c94aafa98d923af3b98ae84877da8f7b682351ffca05913e55a"},"schema_version":"1.0","source":{"id":"2309.15257","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15257","created_at":"2026-07-05T09:48:11Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15257v3","created_at":"2026-07-05T09:48:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15257","created_at":"2026-07-05T09:48:11Z"},{"alias_kind":"pith_short_12","alias_value":"NIYFI6FYJGKV","created_at":"2026-07-05T09:48:11Z"},{"alias_kind":"pith_short_16","alias_value":"NIYFI6FYJGKVGEGN","created_at":"2026-07-05T09:48:11Z"},{"alias_kind":"pith_short_8","alias_value":"NIYFI6FY","created_at":"2026-07-05T09:48:11Z"}],"graph_snapshots":[{"event_id":"sha256:11648d7a0a16eb341c90413fca508d381ec37434fec9ff4ac867fc522b70b81d","target":"graph","created_at":"2026-07-05T09:48:11Z","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/2309.15257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In order to solve a task using reinforcement learning, it is necessary to first formalise the goal of that task as a reward function. However, for many real-world tasks, it is very difficult to manually specify a reward function that never incentivises undesirable behaviour. As a result, it is increasingly popular to use reward learning algorithms, which attempt to learn a reward function from data. However, the theoretical foundations of reward learning are not yet well-developed. In particular, it is typically not known when a given reward learning algorithm with high probability will learn ","authors_text":"Adam Gleave, Alessandro Abate, Erik Jenner, Joar Skalse, Lucy Farnik, Sumeet Ramesh Motwani","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T20:31:19Z","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15257","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":"sha256:997ec59586386506e6f984286e81569eafb048ae2dc1e19214ddf7bd624ab8c3","target":"record","created_at":"2026-07-05T09:48:11Z","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":"bb4b609e3c025b4b21293f286fc47f90777cee34b388cadf8b97f68be7f29e45","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T20:31:19Z","title_canon_sha256":"c4c2072843235c94aafa98d923af3b98ae84877da8f7b682351ffca05913e55a"},"schema_version":"1.0","source":{"id":"2309.15257","kind":"arxiv","version":3}},"canonical_sha256":"6a305478b849955310cda41f6163b6094ef97b0125efee55dd5f9bce9ef1f459","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a305478b849955310cda41f6163b6094ef97b0125efee55dd5f9bce9ef1f459","first_computed_at":"2026-07-05T09:48:11.329505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:11.329505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+itLMBzlRoGZTCNEOpq789D/RO/Xr3kTsLmgeyloNA5qUUyVdCz1cdPvjGVb17Lwqr73BU8j5iqRdZMRWZm7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:11.329939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15257","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:997ec59586386506e6f984286e81569eafb048ae2dc1e19214ddf7bd624ab8c3","sha256:11648d7a0a16eb341c90413fca508d381ec37434fec9ff4ac867fc522b70b81d"],"state_sha256":"ba5847505f06e2bd2b3aa7a3515aa7690860e4722c01861c350d7a41eef151bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hr12thiil+eruZ+V/mB7w5w425lKnIAADf7K0zpNPu+/Qi4k9diObila1KDjpXWRi3vaz+rLNiQKb/MvAgbxBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T08:06:41.731002Z","bundle_sha256":"7065528ce0693a6e39d6494b478a730fb0f6ecfe33664c88f308a036c6724a13"}}