{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FGHCIO2PDRGGEEXHMUPABNPGJ6","short_pith_number":"pith:FGHCIO2P","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"},"canonical_sha256":"298e243b4f1c4c6212e7651e00b5e64fbca93cbe5a5525327f0b76ad4f8c80a4","source":{"kind":"arxiv","id":"2606.26397","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26397","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26397v1","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26397","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"FGHCIO2PDRGG","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"FGHCIO2PDRGGEEXH","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"FGHCIO2P","created_at":"2026-06-26T00:15:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FGHCIO2PDRGGEEXHMUPABNPGJ6","target":"record","payload":{"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"},"canonical_sha256":"298e243b4f1c4c6212e7651e00b5e64fbca93cbe5a5525327f0b76ad4f8c80a4","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"},"source_kind":"arxiv","source_id":"2606.26397","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":"2026-06-26T00:15:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MpEA7hqWw83pYBKbcZ8+WmWrRgE5kC4uMxTjOywUvbXJ6D19A8t+by5Xt3/648zniX4N7LmMaLepCyv9xWCeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T12:31:37.002703Z"},"content_sha256":"519c8aa3367b915ab0fc6e94454f92960f8e703ea8beadcb33f10bd2cb95ad6d","schema_version":"1.0","event_id":"sha256:519c8aa3367b915ab0fc6e94454f92960f8e703ea8beadcb33f10bd2cb95ad6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FGHCIO2PDRGGEEXHMUPABNPGJ6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-26T00:15:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+A/iJhgz95Bp03XpCOfNLgAQE5EwedGxtzda0AldSZDXLOwXK5G/XwYBYHBFxQnuSA8vWvQoC6k9oKbmL2bFBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T12:31:37.003079Z"},"content_sha256":"2e4c8a9a7aec282f1a86b6e405a0d97e2672ae146422b61f3bea746bec81b3a2","schema_version":"1.0","event_id":"sha256:2e4c8a9a7aec282f1a86b6e405a0d97e2672ae146422b61f3bea746bec81b3a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/bundle.json","state_url":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/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":"2026-06-30T12:31:37Z","links":{"resolver":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6","bundle":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/bundle.json","state":"https://pith.science/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGHCIO2PDRGGEEXHMUPABNPGJ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FGHCIO2PDRGGEEXHMUPABNPGJ6","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":"bbf3b9aa23bd5cb4b11c2471b3f043750cc26798c5d6e78fb23a0d59685e4c1b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T21:28:49Z","title_canon_sha256":"2d941c77873239900ef3953323e554b11ddcf75153d30d9ac321812ae2800e91"},"schema_version":"1.0","source":{"id":"2606.26397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26397","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26397v1","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26397","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"FGHCIO2PDRGG","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"FGHCIO2PDRGGEEXH","created_at":"2026-06-26T00:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"FGHCIO2P","created_at":"2026-06-26T00:15:39Z"}],"graph_snapshots":[{"event_id":"sha256:2e4c8a9a7aec282f1a86b6e405a0d97e2672ae146422b61f3bea746bec81b3a2","target":"graph","created_at":"2026-06-26T00:15:39Z","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/2606.26397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aniruddha Joshi, Niklas Lauffer, Sanjit Seshia","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T21:28:49Z","title":"Deterministic Pareto-Optimal Policy Synthesis for Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26397","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":"sha256:519c8aa3367b915ab0fc6e94454f92960f8e703ea8beadcb33f10bd2cb95ad6d","target":"record","created_at":"2026-06-26T00:15:39Z","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":"bbf3b9aa23bd5cb4b11c2471b3f043750cc26798c5d6e78fb23a0d59685e4c1b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T21:28:49Z","title_canon_sha256":"2d941c77873239900ef3953323e554b11ddcf75153d30d9ac321812ae2800e91"},"schema_version":"1.0","source":{"id":"2606.26397","kind":"arxiv","version":1}},"canonical_sha256":"298e243b4f1c4c6212e7651e00b5e64fbca93cbe5a5525327f0b76ad4f8c80a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"298e243b4f1c4c6212e7651e00b5e64fbca93cbe5a5525327f0b76ad4f8c80a4","first_computed_at":"2026-06-26T00:15:39.848391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T00:15:39.848391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"erIx36EuztSWJ3nsvU0AAp7fRALM0+p0bOgXEG6fS5UR2sx6pkX6hKDzlp0OBwy5xMbJLc6PL2bR/9l2ENFfCw==","signature_status":"signed_v1","signed_at":"2026-06-26T00:15:39.848924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:519c8aa3367b915ab0fc6e94454f92960f8e703ea8beadcb33f10bd2cb95ad6d","sha256:2e4c8a9a7aec282f1a86b6e405a0d97e2672ae146422b61f3bea746bec81b3a2"],"state_sha256":"56bdc1bb118954c8063a4abe578ea79e8672faeb3086ead37e9f7efe55856f1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cOc7mH+DcmsFs/rP+ZqRZ6S2Svclx7er2Pbkh158/Lhr1Ant4sUqIUDBBYf+xf1N9wSfpN/P2ejPc6340siLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T12:31:37.005041Z","bundle_sha256":"0055485e2ff9ad31782c7ab7b20e275e71b7bdde5f914a86d672053f8856aaba"}}