{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IZ47D2MXJLTS745ZTETUNR4IBJ","short_pith_number":"pith:IZ47D2MX","canonical_record":{"source":{"id":"1806.02501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-06-07T03:49:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6379560c9eed767c948dff2bd1c1a5ade211bb7dc2030a4bf8b19a08edc0195c","abstract_canon_sha256":"ba1569a61c2aae7f81a0403b3280ef9f96d279ef5370fcf7cb95e66eedfd63ce"},"schema_version":"1.0"},"canonical_sha256":"4679f1e9974ae72ff3b9992746c7880a4205096596fb34d601f68dcb52c015c4","source":{"kind":"arxiv","id":"1806.02501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02501","created_at":"2026-05-18T00:13:56Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02501v1","created_at":"2026-05-18T00:13:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02501","created_at":"2026-05-18T00:13:56Z"},{"alias_kind":"pith_short_12","alias_value":"IZ47D2MXJLTS","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IZ47D2MXJLTS745Z","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IZ47D2MX","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IZ47D2MXJLTS745ZTETUNR4IBJ","target":"record","payload":{"canonical_record":{"source":{"id":"1806.02501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-06-07T03:49:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6379560c9eed767c948dff2bd1c1a5ade211bb7dc2030a4bf8b19a08edc0195c","abstract_canon_sha256":"ba1569a61c2aae7f81a0403b3280ef9f96d279ef5370fcf7cb95e66eedfd63ce"},"schema_version":"1.0"},"canonical_sha256":"4679f1e9974ae72ff3b9992746c7880a4205096596fb34d601f68dcb52c015c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:56.609435Z","signature_b64":"f0MiY00nYLAbIECINHEMEdgASLiQI4mLvns1cRJRK9fdEbR7i9ysimwUF019OUTVujqHCq5bcOjubUel/3eSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4679f1e9974ae72ff3b9992746c7880a4205096596fb34d601f68dcb52c015c4","last_reissued_at":"2026-05-18T00:13:56.608704Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:56.608704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.02501","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":"2026-05-18T00:13:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HEnpWgeciN5Co2QuCP1o/i1U4ty8o4hxKgwsj0DNnISjOoF/NVkwd1ATbuDv27uRmvN4WENQrvzLZA2XXOlJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:29:56.510507Z"},"content_sha256":"ac6276f1a0d7198c20e9b4f26eb8932356aade2eeac9929d473b29b1907ec60d","schema_version":"1.0","event_id":"sha256:ac6276f1a0d7198c20e9b4f26eb8932356aade2eeac9929d473b29b1907ec60d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IZ47D2MXJLTS745ZTETUNR4IBJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simplifying Reward Design through Divide-and-Conquer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Anca D. Dragan, Dylan Hadfield-Menell, Ellis Ratner","submitted_at":"2018-06-07T03:49:05Z","abstract_excerpt":"Designing a good reward function is essential to robot planning and reinforcement learning, but it can also be challenging and frustrating. The reward needs to work across multiple different environments, and that often requires many iterations of tuning. We introduce a novel divide-and-conquer approach that enables the designer to specify a reward separately for each environment. By treating these separate reward functions as observations about the underlying true reward, we derive an approach to infer a common reward across all environments. We conduct user studies in an abstract grid world "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02501","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":""},"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":"2026-05-18T00:13:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E9rZ49er6p4rmCB8Wmj9JAtIz467NlKaXHqmM5MNtdISnNhmOnT9UZS/3xfrfspuvmSdaQsn5HAFso40pMG/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:29:56.510859Z"},"content_sha256":"f7c594844c3c4799593ccb6ffcffb64d1557c59663de2cf9222f3d1d672aa8be","schema_version":"1.0","event_id":"sha256:f7c594844c3c4799593ccb6ffcffb64d1557c59663de2cf9222f3d1d672aa8be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZ47D2MXJLTS745ZTETUNR4IBJ/bundle.json","state_url":"https://pith.science/pith/IZ47D2MXJLTS745ZTETUNR4IBJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZ47D2MXJLTS745ZTETUNR4IBJ/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":"2026-05-28T04:29:56Z","links":{"resolver":"https://pith.science/pith/IZ47D2MXJLTS745ZTETUNR4IBJ","bundle":"https://pith.science/pith/IZ47D2MXJLTS745ZTETUNR4IBJ/bundle.json","state":"https://pith.science/pith/IZ47D2MXJLTS745ZTETUNR4IBJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZ47D2MXJLTS745ZTETUNR4IBJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IZ47D2MXJLTS745ZTETUNR4IBJ","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":"ba1569a61c2aae7f81a0403b3280ef9f96d279ef5370fcf7cb95e66eedfd63ce","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-06-07T03:49:05Z","title_canon_sha256":"6379560c9eed767c948dff2bd1c1a5ade211bb7dc2030a4bf8b19a08edc0195c"},"schema_version":"1.0","source":{"id":"1806.02501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02501","created_at":"2026-05-18T00:13:56Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02501v1","created_at":"2026-05-18T00:13:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02501","created_at":"2026-05-18T00:13:56Z"},{"alias_kind":"pith_short_12","alias_value":"IZ47D2MXJLTS","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IZ47D2MXJLTS745Z","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IZ47D2MX","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:f7c594844c3c4799593ccb6ffcffb64d1557c59663de2cf9222f3d1d672aa8be","target":"graph","created_at":"2026-05-18T00:13:56Z","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":"Designing a good reward function is essential to robot planning and reinforcement learning, but it can also be challenging and frustrating. The reward needs to work across multiple different environments, and that often requires many iterations of tuning. We introduce a novel divide-and-conquer approach that enables the designer to specify a reward separately for each environment. By treating these separate reward functions as observations about the underlying true reward, we derive an approach to infer a common reward across all environments. We conduct user studies in an abstract grid world ","authors_text":"Anca D. Dragan, Dylan Hadfield-Menell, Ellis Ratner","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-06-07T03:49:05Z","title":"Simplifying Reward Design through Divide-and-Conquer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02501","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:ac6276f1a0d7198c20e9b4f26eb8932356aade2eeac9929d473b29b1907ec60d","target":"record","created_at":"2026-05-18T00:13:56Z","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":"ba1569a61c2aae7f81a0403b3280ef9f96d279ef5370fcf7cb95e66eedfd63ce","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-06-07T03:49:05Z","title_canon_sha256":"6379560c9eed767c948dff2bd1c1a5ade211bb7dc2030a4bf8b19a08edc0195c"},"schema_version":"1.0","source":{"id":"1806.02501","kind":"arxiv","version":1}},"canonical_sha256":"4679f1e9974ae72ff3b9992746c7880a4205096596fb34d601f68dcb52c015c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4679f1e9974ae72ff3b9992746c7880a4205096596fb34d601f68dcb52c015c4","first_computed_at":"2026-05-18T00:13:56.608704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:56.608704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f0MiY00nYLAbIECINHEMEdgASLiQI4mLvns1cRJRK9fdEbR7i9ysimwUF019OUTVujqHCq5bcOjubUel/3eSAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:56.609435Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.02501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac6276f1a0d7198c20e9b4f26eb8932356aade2eeac9929d473b29b1907ec60d","sha256:f7c594844c3c4799593ccb6ffcffb64d1557c59663de2cf9222f3d1d672aa8be"],"state_sha256":"488898625928a0d4b0cded23f6998c8fdb74be65bb8c024ea173bb25ac4c786a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PQxNrHEoGW0cHBWRRnRZRam3PA7PPU8OpighEa5/PzRWFCf5WPXgsn9eGYtL+LZS8V71wH4o4MPU6MvvXzs4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:29:56.513391Z","bundle_sha256":"85e002d9d16a9a7c525f1e3e40fbabb712dfb6d368fb1eac76826db776fb71ad"}}