{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QH55RYG6RRZCFTEVNK353U6MXQ","short_pith_number":"pith:QH55RYG6","canonical_record":{"source":{"id":"2311.12495","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-21T10:11:19Z","cross_cats_sorted":[],"title_canon_sha256":"7159ae6b6508a9b6b58f53bcb32bd4a2c4512d3831894af0712edf441f817b7a","abstract_canon_sha256":"52554b5c7a6f140d07538244abf72b3f259998afba1df8ede3997dc94f0fca44"},"schema_version":"1.0"},"canonical_sha256":"81fbd8e0de8c7222cc956ab7ddd3ccbc30d2b8ba6b552cf2cabcebb24b7d7dde","source":{"kind":"arxiv","id":"2311.12495","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12495","created_at":"2026-07-05T07:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12495v2","created_at":"2026-07-05T07:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12495","created_at":"2026-07-05T07:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"QH55RYG6RRZC","created_at":"2026-07-05T07:41:00Z"},{"alias_kind":"pith_short_16","alias_value":"QH55RYG6RRZCFTEV","created_at":"2026-07-05T07:41:00Z"},{"alias_kind":"pith_short_8","alias_value":"QH55RYG6","created_at":"2026-07-05T07:41:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QH55RYG6RRZCFTEVNK353U6MXQ","target":"record","payload":{"canonical_record":{"source":{"id":"2311.12495","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-21T10:11:19Z","cross_cats_sorted":[],"title_canon_sha256":"7159ae6b6508a9b6b58f53bcb32bd4a2c4512d3831894af0712edf441f817b7a","abstract_canon_sha256":"52554b5c7a6f140d07538244abf72b3f259998afba1df8ede3997dc94f0fca44"},"schema_version":"1.0"},"canonical_sha256":"81fbd8e0de8c7222cc956ab7ddd3ccbc30d2b8ba6b552cf2cabcebb24b7d7dde","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:00.065817Z","signature_b64":"Vsfi2TtXoBzrSWeYJRNuHL7BdXOeUnI5ygbK46rTj7yIfQj9Mbg2kLTD3X73HyR0eDiQNc8h8VRGypI3CoYmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81fbd8e0de8c7222cc956ab7ddd3ccbc30d2b8ba6b552cf2cabcebb24b7d7dde","last_reissued_at":"2026-07-05T07:41:00.065264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:00.065264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.12495","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qTc2VI7MO/k5Bh5uzJC4g+41xpy2iDVSKRcg8PGJrEpHgvZS1fCwzPFA7AEJc5j+jdcRxgHAUFpL6swIorcWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:43:19.944587Z"},"content_sha256":"570a33a68cd6e957e8dc7314a795f2192c66246323cb0cd455b005fb5de81aa8","schema_version":"1.0","event_id":"sha256:570a33a68cd6e957e8dc7314a795f2192c66246323cb0cd455b005fb5de81aa8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QH55RYG6RRZCFTEVNK353U6MXQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"El-Ghazali Talbi, Florian Felten, Gr\\'egoire Danoy","submitted_at":"2023-11-21T10:11:19Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) extends traditional RL by seeking policies making different compromises among conflicting objectives. The recent surge of interest in MORL has led to diverse studies and solving methods, often drawing from existing knowledge in multi-objective optimization based on decomposition (MOO/D). Yet, a clear categorization based on both RL and MOO/D is lacking in the existing literature. Consequently, MORL researchers face difficulties when trying to classify contributions within a broader context due to the absence of a standardized taxonomy. To tackle su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12495","kind":"arxiv","version":2},"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/2311.12495/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":"2026-07-05T07:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vUUl7AhbEaW9ls3+UcBs64zbJYZbKdNvaJng4uUsfI2/GWFNvDWNb36gtyHP6hfL8WycvVsr25YxgD6V8PXzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:43:19.945504Z"},"content_sha256":"89a210520f2b28aaf6df167e3628673d8aec1bc50a23af280a21bbe91cc294c7","schema_version":"1.0","event_id":"sha256:89a210520f2b28aaf6df167e3628673d8aec1bc50a23af280a21bbe91cc294c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QH55RYG6RRZCFTEVNK353U6MXQ/bundle.json","state_url":"https://pith.science/pith/QH55RYG6RRZCFTEVNK353U6MXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QH55RYG6RRZCFTEVNK353U6MXQ/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":"2026-08-14T01:43:19Z","links":{"resolver":"https://pith.science/pith/QH55RYG6RRZCFTEVNK353U6MXQ","bundle":"https://pith.science/pith/QH55RYG6RRZCFTEVNK353U6MXQ/bundle.json","state":"https://pith.science/pith/QH55RYG6RRZCFTEVNK353U6MXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QH55RYG6RRZCFTEVNK353U6MXQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QH55RYG6RRZCFTEVNK353U6MXQ","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":"52554b5c7a6f140d07538244abf72b3f259998afba1df8ede3997dc94f0fca44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-21T10:11:19Z","title_canon_sha256":"7159ae6b6508a9b6b58f53bcb32bd4a2c4512d3831894af0712edf441f817b7a"},"schema_version":"1.0","source":{"id":"2311.12495","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12495","created_at":"2026-07-05T07:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12495v2","created_at":"2026-07-05T07:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12495","created_at":"2026-07-05T07:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"QH55RYG6RRZC","created_at":"2026-07-05T07:41:00Z"},{"alias_kind":"pith_short_16","alias_value":"QH55RYG6RRZCFTEV","created_at":"2026-07-05T07:41:00Z"},{"alias_kind":"pith_short_8","alias_value":"QH55RYG6","created_at":"2026-07-05T07:41:00Z"}],"graph_snapshots":[{"event_id":"sha256:89a210520f2b28aaf6df167e3628673d8aec1bc50a23af280a21bbe91cc294c7","target":"graph","created_at":"2026-07-05T07:41:00Z","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/2311.12495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective reinforcement learning (MORL) extends traditional RL by seeking policies making different compromises among conflicting objectives. The recent surge of interest in MORL has led to diverse studies and solving methods, often drawing from existing knowledge in multi-objective optimization based on decomposition (MOO/D). Yet, a clear categorization based on both RL and MOO/D is lacking in the existing literature. Consequently, MORL researchers face difficulties when trying to classify contributions within a broader context due to the absence of a standardized taxonomy. To tackle su","authors_text":"El-Ghazali Talbi, Florian Felten, Gr\\'egoire Danoy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-21T10:11:19Z","title":"Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12495","kind":"arxiv","version":2},"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":"sha256:570a33a68cd6e957e8dc7314a795f2192c66246323cb0cd455b005fb5de81aa8","target":"record","created_at":"2026-07-05T07:41:00Z","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":"52554b5c7a6f140d07538244abf72b3f259998afba1df8ede3997dc94f0fca44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-21T10:11:19Z","title_canon_sha256":"7159ae6b6508a9b6b58f53bcb32bd4a2c4512d3831894af0712edf441f817b7a"},"schema_version":"1.0","source":{"id":"2311.12495","kind":"arxiv","version":2}},"canonical_sha256":"81fbd8e0de8c7222cc956ab7ddd3ccbc30d2b8ba6b552cf2cabcebb24b7d7dde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81fbd8e0de8c7222cc956ab7ddd3ccbc30d2b8ba6b552cf2cabcebb24b7d7dde","first_computed_at":"2026-07-05T07:41:00.065264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:00.065264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vsfi2TtXoBzrSWeYJRNuHL7BdXOeUnI5ygbK46rTj7yIfQj9Mbg2kLTD3X73HyR0eDiQNc8h8VRGypI3CoYmCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:00.065817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.12495","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:570a33a68cd6e957e8dc7314a795f2192c66246323cb0cd455b005fb5de81aa8","sha256:89a210520f2b28aaf6df167e3628673d8aec1bc50a23af280a21bbe91cc294c7"],"state_sha256":"51ffdc750cad71d94f4144a7b769c0d7305b80dc3248b1f39b7141a0d8fc1fbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qprUBSrqpweFYXYh52TGDHTLYCD7R9iTUiEE22QrA9/bUKQZvG5wEBXoiFvWKZGF23qjNezdqIIWwuB/htMQAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T01:43:19.953932Z","bundle_sha256":"de4eea5f955f460bc4b63ec5633a92389bde2f596b2b6aff1ec97791d60c2631"}}