{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FGHCIO2PDRGGEEXHMUPABNPGJ6","short_pith_number":"pith:FGHCIO2P","schema_version":"1.0","canonical_sha256":"298e243b4f1c4c6212e7651e00b5e64fbca93cbe5a5525327f0b76ad4f8c80a4","source":{"kind":"arxiv","id":"2606.26397","version":1},"attestation_state":"computed","paper":{"title":"Deterministic Pareto-Optimal Policy Synthesis for Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aniruddha Joshi, Niklas Lauffer, Sanjit Seshia","submitted_at":"2026-06-24T21:28:49Z","abstract_excerpt":"Real-world decision-making often requires balancing multiple conflicting objectives, a challenge that standard Reinforcement Learning (RL) frequently addresses by aggregating rewards into a single scalar signal. While effective for simple tasks, this approach often fails to capture the full spectrum of optimal trade-offs, known as the Pareto frontier. In this paper, we introduce a novel preference-conditioned Bellman operator, motivated from the Chebyshev scalarization, designed to compute deterministic Pareto-optimal policies for Multi-Objective Markov Decision Processes (MOMDPs). We prove th"},"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":"2606.26397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T21:28:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2d941c77873239900ef3953323e554b11ddcf75153d30d9ac321812ae2800e91","abstract_canon_sha256":"bbf3b9aa23bd5cb4b11c2471b3f043750cc26798c5d6e78fb23a0d59685e4c1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:39.848924Z","signature_b64":"erIx36EuztSWJ3nsvU0AAp7fRALM0+p0bOgXEG6fS5UR2sx6pkX6hKDzlp0OBwy5xMbJLc6PL2bR/9l2ENFfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"298e243b4f1c4c6212e7651e00b5e64fbca93cbe5a5525327f0b76ad4f8c80a4","last_reissued_at":"2026-06-26T00:15:39.848391Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:39.848391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deterministic Pareto-Optimal Policy Synthesis for Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aniruddha Joshi, Niklas Lauffer, Sanjit Seshia","submitted_at":"2026-06-24T21:28:49Z","abstract_excerpt":"Real-world decision-making often requires balancing multiple conflicting objectives, a challenge that standard Reinforcement Learning (RL) frequently addresses by aggregating rewards into a single scalar signal. While effective for simple tasks, this approach often fails to capture the full spectrum of optimal trade-offs, known as the Pareto frontier. In this paper, we introduce a novel preference-conditioned Bellman operator, motivated from the Chebyshev scalarization, designed to compute deterministic Pareto-optimal policies for Multi-Objective Markov Decision Processes (MOMDPs). We prove th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26397","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/2606.26397/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":"2606.26397","created_at":"2026-06-26T00:15:39.848466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26397v1","created_at":"2026-06-26T00:15:39.848466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26397","created_at":"2026-06-26T00:15:39.848466+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGHCIO2PDRGG","created_at":"2026-06-26T00:15:39.848466+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGHCIO2PDRGGEEXH","created_at":"2026-06-26T00:15:39.848466+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGHCIO2P","created_at":"2026-06-26T00:15:39.848466+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/FGHCIO2PDRGGEEXHMUPABNPGJ6","json":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6.json","graph_json":"https://pith.science/api/pith-number/FGHCIO2PDRGGEEXHMUPABNPGJ6/graph.json","events_json":"https://pith.science/api/pith-number/FGHCIO2PDRGGEEXHMUPABNPGJ6/events.json","paper":"https://pith.science/paper/FGHCIO2P"},"agent_actions":{"view_html":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6","download_json":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6.json","view_paper":"https://pith.science/paper/FGHCIO2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26397&json=true","fetch_graph":"https://pith.science/api/pith-number/FGHCIO2PDRGGEEXHMUPABNPGJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/FGHCIO2PDRGGEEXHMUPABNPGJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/action/storage_attestation","attest_author":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/action/author_attestation","sign_citation":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/action/citation_signature","submit_replication":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/action/replication_record"}},"created_at":"2026-06-26T00:15:39.848466+00:00","updated_at":"2026-06-26T00:15:39.848466+00:00"}