{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4L5BEVFDZAHAS52UYC4QTZ2G4I","short_pith_number":"pith:4L5BEVFD","canonical_record":{"source":{"id":"2401.02160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2024-01-04T09:17:53Z","cross_cats_sorted":[],"title_canon_sha256":"a676674ac087e80612172d8e978518131b0c66e1f511100c6eb0cc934f321f3c","abstract_canon_sha256":"bb708b91111499f28605e2dda726ffca39459f1ff55c718d08c1e787fa9bd862"},"schema_version":"1.0"},"canonical_sha256":"e2fa1254a3c80e097754c0b909e746e21f23aada59fb7c6727adf838bd47a1b6","source":{"kind":"arxiv","id":"2401.02160","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02160","created_at":"2026-07-05T07:30:12Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02160v1","created_at":"2026-07-05T07:30:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02160","created_at":"2026-07-05T07:30:12Z"},{"alias_kind":"pith_short_12","alias_value":"4L5BEVFDZAHA","created_at":"2026-07-05T07:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"4L5BEVFDZAHAS52U","created_at":"2026-07-05T07:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"4L5BEVFD","created_at":"2026-07-05T07:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4L5BEVFDZAHAS52UYC4QTZ2G4I","target":"record","payload":{"canonical_record":{"source":{"id":"2401.02160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2024-01-04T09:17:53Z","cross_cats_sorted":[],"title_canon_sha256":"a676674ac087e80612172d8e978518131b0c66e1f511100c6eb0cc934f321f3c","abstract_canon_sha256":"bb708b91111499f28605e2dda726ffca39459f1ff55c718d08c1e787fa9bd862"},"schema_version":"1.0"},"canonical_sha256":"e2fa1254a3c80e097754c0b909e746e21f23aada59fb7c6727adf838bd47a1b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:12.432918Z","signature_b64":"vbTigbeFn9j8pUFbfe/u8TV3uFe9AUWCbkitLfw46LMdqnNzQIkLEI+sQUsS+ZW/G8eyMN8ThWNixOIOKNpBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2fa1254a3c80e097754c0b909e746e21f23aada59fb7c6727adf838bd47a1b6","last_reissued_at":"2026-07-05T07:30:12.432560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:12.432560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.02160","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":"2026-07-05T07:30:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7UsPbVYXptR3XQ4CtfzeiQh/wEjrw2Nbt6gzCDeOfMTnLJfX4cRo/T75lB4xBdatLCL05p0ax9JEZcAvwoLrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:25:42.093188Z"},"content_sha256":"9e933aa9843d89a67505dcc0ca62eb6ce31e7fb60c35807be6313c03fab22699","schema_version":"1.0","event_id":"sha256:9e933aa9843d89a67505dcc0ca62eb6ce31e7fb60c35807be6313c03fab22699"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4L5BEVFDZAHAS52UYC4QTZ2G4I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Han Guo, Ke Li","submitted_at":"2024-01-04T09:17:53Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) aims to find a set of high-performing and diverse policies that address trade-offs between multiple conflicting objectives. However, in practice, decision makers (DMs) often deploy only one or a limited number of trade-off policies. Providing too many diversified trade-off policies to the DM not only significantly increases their workload but also introduces noise in multi-criterion decision-making. With this in mind, we propose a human-in-the-loop policy optimization framework for preference-based MORL that interactively identifies policies of int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02160","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/2401.02160/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":"2026-07-05T07:30:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iSwwvjjsomrBIdAuyx8mJ4nHgzLtkcvkfxuBJ5lJNYfFPVcecxoe9/BPeCSKMtYeU3Y3a0la+vY9hH8dWTQFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:25:42.094124Z"},"content_sha256":"637e7b27db3a3648f16585550df353bf89cb8f7bbc29bd8e9d5fdcc482315fbd","schema_version":"1.0","event_id":"sha256:637e7b27db3a3648f16585550df353bf89cb8f7bbc29bd8e9d5fdcc482315fbd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/bundle.json","state_url":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/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":"2026-08-09T06:25:42Z","links":{"resolver":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I","bundle":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/bundle.json","state":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4L5BEVFDZAHAS52UYC4QTZ2G4I","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":"bb708b91111499f28605e2dda726ffca39459f1ff55c718d08c1e787fa9bd862","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2024-01-04T09:17:53Z","title_canon_sha256":"a676674ac087e80612172d8e978518131b0c66e1f511100c6eb0cc934f321f3c"},"schema_version":"1.0","source":{"id":"2401.02160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02160","created_at":"2026-07-05T07:30:12Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02160v1","created_at":"2026-07-05T07:30:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02160","created_at":"2026-07-05T07:30:12Z"},{"alias_kind":"pith_short_12","alias_value":"4L5BEVFDZAHA","created_at":"2026-07-05T07:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"4L5BEVFDZAHAS52U","created_at":"2026-07-05T07:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"4L5BEVFD","created_at":"2026-07-05T07:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:637e7b27db3a3648f16585550df353bf89cb8f7bbc29bd8e9d5fdcc482315fbd","target":"graph","created_at":"2026-07-05T07:30:12Z","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/2401.02160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective reinforcement learning (MORL) aims to find a set of high-performing and diverse policies that address trade-offs between multiple conflicting objectives. However, in practice, decision makers (DMs) often deploy only one or a limited number of trade-off policies. Providing too many diversified trade-off policies to the DM not only significantly increases their workload but also introduces noise in multi-criterion decision-making. With this in mind, we propose a human-in-the-loop policy optimization framework for preference-based MORL that interactively identifies policies of int","authors_text":"Han Guo, Ke Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2024-01-04T09:17:53Z","title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02160","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":"sha256:9e933aa9843d89a67505dcc0ca62eb6ce31e7fb60c35807be6313c03fab22699","target":"record","created_at":"2026-07-05T07:30:12Z","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":"bb708b91111499f28605e2dda726ffca39459f1ff55c718d08c1e787fa9bd862","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2024-01-04T09:17:53Z","title_canon_sha256":"a676674ac087e80612172d8e978518131b0c66e1f511100c6eb0cc934f321f3c"},"schema_version":"1.0","source":{"id":"2401.02160","kind":"arxiv","version":1}},"canonical_sha256":"e2fa1254a3c80e097754c0b909e746e21f23aada59fb7c6727adf838bd47a1b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2fa1254a3c80e097754c0b909e746e21f23aada59fb7c6727adf838bd47a1b6","first_computed_at":"2026-07-05T07:30:12.432560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:12.432560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vbTigbeFn9j8pUFbfe/u8TV3uFe9AUWCbkitLfw46LMdqnNzQIkLEI+sQUsS+ZW/G8eyMN8ThWNixOIOKNpBDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:12.432918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e933aa9843d89a67505dcc0ca62eb6ce31e7fb60c35807be6313c03fab22699","sha256:637e7b27db3a3648f16585550df353bf89cb8f7bbc29bd8e9d5fdcc482315fbd"],"state_sha256":"c0aff82cccbd98202c7727fd111ddef8e3863d99e191f519376dd81022561c0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8sOM6rxtvtIBJEZTHwBLmg13FmJbWWbBvq6dC1jhf+ADNanqsNPvaBdYN7qPaxthbEnc/3CG2om9Qrhn85oFAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:25:42.099732Z","bundle_sha256":"c41752db298f82e0b273af944f34f87dcc6ef7d7cb430d71b95d52870bdacf0c"}}