{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DZWJHIUS7KDGE6VX4E7OLER6YY","short_pith_number":"pith:DZWJHIUS","schema_version":"1.0","canonical_sha256":"1e6c93a292fa86627ab7e13ee5923ec632d76e78b803ec3082fc876f12179ffc","source":{"kind":"arxiv","id":"2602.07764","version":2},"attestation_state":"computed","paper":{"title":"Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhinav Verma, Jonathan Dodge, Shreyash Kale, Sourav Panda, Tanmay Ambadkar","submitted_at":"2026-02-08T01:45:01Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) seeks to train agents capable of balancing conflicting objectives. While single preference-conditioned policies offer a highly scalable solution, existing approaches remain brittle in practice, frequently failing to recover dense Pareto fronts. We demonstrate that this failure stems from two structural pathologies: destructive advantage cancellation caused by premature Early Scalarization (ES), and representational mode collapse across the preference space. To overcome these bottlenecks, we introduce $D^3PO$, a PPO-based framework that fundamentall"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.07764","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-08T01:45:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e15071710626e996623049a8764f73eaf7fde70eeff1eecb7cd7bdf4d48d879b","abstract_canon_sha256":"a540233e7a581b419ef57423b15de8382571e56a974528fd8f7c027123f8f5c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:17:56.818812Z","signature_b64":"VaA2+WgCl2gmiyjwwmYcXrCp17lCvehXRnQtPTZfeCr4UvZ3NkdTVSfbmsb1gJqnReKAZouFT8TdvCI5elfqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e6c93a292fa86627ab7e13ee5923ec632d76e78b803ec3082fc876f12179ffc","last_reissued_at":"2026-07-13T01:17:56.816822Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:17:56.816822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhinav Verma, Jonathan Dodge, Shreyash Kale, Sourav Panda, Tanmay Ambadkar","submitted_at":"2026-02-08T01:45:01Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) seeks to train agents capable of balancing conflicting objectives. While single preference-conditioned policies offer a highly scalable solution, existing approaches remain brittle in practice, frequently failing to recover dense Pareto fronts. We demonstrate that this failure stems from two structural pathologies: destructive advantage cancellation caused by premature Early Scalarization (ES), and representational mode collapse across the preference space. To overcome these bottlenecks, we introduce $D^3PO$, a PPO-based framework that fundamentall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07764","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/2602.07764/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.07764","created_at":"2026-07-13T01:17:56.817897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.07764v2","created_at":"2026-07-13T01:17:56.817897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07764","created_at":"2026-07-13T01:17:56.817897+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZWJHIUS7KDG","created_at":"2026-07-13T01:17:56.817897+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZWJHIUS7KDGE6VX","created_at":"2026-07-13T01:17:56.817897+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZWJHIUS","created_at":"2026-07-13T01:17:56.817897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZWJHIUS7KDGE6VX4E7OLER6YY","json":"https://pith.science/pith/DZWJHIUS7KDGE6VX4E7OLER6YY.json","graph_json":"https://pith.science/api/pith-number/DZWJHIUS7KDGE6VX4E7OLER6YY/graph.json","events_json":"https://pith.science/api/pith-number/DZWJHIUS7KDGE6VX4E7OLER6YY/events.json","paper":"https://pith.science/paper/DZWJHIUS"},"agent_actions":{"view_html":"https://pith.science/pith/DZWJHIUS7KDGE6VX4E7OLER6YY","download_json":"https://pith.science/pith/DZWJHIUS7KDGE6VX4E7OLER6YY.json","view_paper":"https://pith.science/paper/DZWJHIUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.07764&json=true","fetch_graph":"https://pith.science/api/pith-number/DZWJHIUS7KDGE6VX4E7OLER6YY/graph.json","fetch_events":"https://pith.science/api/pith-number/DZWJHIUS7KDGE6VX4E7OLER6YY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZWJHIUS7KDGE6VX4E7OLER6YY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZWJHIUS7KDGE6VX4E7OLER6YY/action/storage_attestation","attest_author":"https://pith.science/pith/DZWJHIUS7KDGE6VX4E7OLER6YY/action/author_attestation","sign_citation":"https://pith.science/pith/DZWJHIUS7KDGE6VX4E7OLER6YY/action/citation_signature","submit_replication":"https://pith.science/pith/DZWJHIUS7KDGE6VX4E7OLER6YY/action/replication_record"}},"created_at":"2026-07-13T01:17:56.817897+00:00","updated_at":"2026-07-13T01:17:56.817897+00:00"}