{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TXLGGEDY5KA5ONULDYTBVE43WR","short_pith_number":"pith:TXLGGEDY","canonical_record":{"source":{"id":"2508.02217","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T09:09:04Z","cross_cats_sorted":[],"title_canon_sha256":"463dd0847fc537c31a05dc8ac25727af317f9b6d82817725bf7602e4c93b514c","abstract_canon_sha256":"ad9bf6d231b090d91020160317bf8b07376d74b33c3d876887aac4ab672484fd"},"schema_version":"1.0"},"canonical_sha256":"9dd6631078ea81d7368b1e261a939bb46c9d10b7b86918e08416c7e2dd159d84","source":{"kind":"arxiv","id":"2508.02217","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02217","created_at":"2026-06-01T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02217v2","created_at":"2026-06-01T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02217","created_at":"2026-06-01T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"TXLGGEDY5KA5","created_at":"2026-06-01T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"TXLGGEDY5KA5ONUL","created_at":"2026-06-01T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"TXLGGEDY","created_at":"2026-06-01T01:03:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TXLGGEDY5KA5ONULDYTBVE43WR","target":"record","payload":{"canonical_record":{"source":{"id":"2508.02217","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T09:09:04Z","cross_cats_sorted":[],"title_canon_sha256":"463dd0847fc537c31a05dc8ac25727af317f9b6d82817725bf7602e4c93b514c","abstract_canon_sha256":"ad9bf6d231b090d91020160317bf8b07376d74b33c3d876887aac4ab672484fd"},"schema_version":"1.0"},"canonical_sha256":"9dd6631078ea81d7368b1e261a939bb46c9d10b7b86918e08416c7e2dd159d84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:44.277020Z","signature_b64":"Be+8S68veR7hT2TGc4itKaV3X1E7C3KkH90hgVp/8TbveIZzSRxvRl31JUFIadRXhCTeoV2oFDhsWz0W9oLcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dd6631078ea81d7368b1e261a939bb46c9d10b7b86918e08416c7e2dd159d84","last_reissued_at":"2026-06-01T01:03:44.275451Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:44.275451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.02217","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":"2026-06-01T01:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DELnUGDCFuGficjRFzhUKsXIIPWvtJ3lyrJCWbnIGMzbGo5EtShlgKQi6xBVGYIWKF2Ry/8IhoRaWhOJMHjHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T23:03:44.648530Z"},"content_sha256":"08133ed08af342f2dc5be7b882a60c08629001be5a6120bf773751ca7919c48d","schema_version":"1.0","event_id":"sha256:08133ed08af342f2dc5be7b882a60c08629001be5a6120bf773751ca7919c48d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TXLGGEDY5KA5ONULDYTBVE43WR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Population-Free Pareto Tracking for Sample-Efficient Multi-Policy MORL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jian Li, Junmei Yao, Kaichen Liu, Yueling Che, Zeyu Zhao","submitted_at":"2025-08-04T09:09:04Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) is a fundamental framework for real-world decision-making problems involving multiple conflicting criteria. Existing multi-policy (MP) methods typically rely on online evolutionary frameworks that maintain large policy populations, leading to high sample complexity and excessive agent-environment interactions. To mitigate these limitations, we present Multi-policy Pareto Front Tracking (MPFT), a framework without a self-evolving population. It leverages an efficient Pareto-tracking mechanism initialized with single-objective extreme policies to tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02217","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/2508.02217/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":"2026-06-01T01:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q1bUd023n4h2u07Yq/KaxwsmHIFaeYVeUSjM/97MxJW7lMvmyGpJhH29ApmqsJQ8Puf5ypuV7McIbBMRMcy8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T23:03:44.648904Z"},"content_sha256":"1467b3941a46977c5bace6330b2bcf56dda5659e2d61eb2a11efc7b4170979c4","schema_version":"1.0","event_id":"sha256:1467b3941a46977c5bace6330b2bcf56dda5659e2d61eb2a11efc7b4170979c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXLGGEDY5KA5ONULDYTBVE43WR/bundle.json","state_url":"https://pith.science/pith/TXLGGEDY5KA5ONULDYTBVE43WR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXLGGEDY5KA5ONULDYTBVE43WR/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":"2026-06-28T23:03:44Z","links":{"resolver":"https://pith.science/pith/TXLGGEDY5KA5ONULDYTBVE43WR","bundle":"https://pith.science/pith/TXLGGEDY5KA5ONULDYTBVE43WR/bundle.json","state":"https://pith.science/pith/TXLGGEDY5KA5ONULDYTBVE43WR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXLGGEDY5KA5ONULDYTBVE43WR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TXLGGEDY5KA5ONULDYTBVE43WR","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":"ad9bf6d231b090d91020160317bf8b07376d74b33c3d876887aac4ab672484fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T09:09:04Z","title_canon_sha256":"463dd0847fc537c31a05dc8ac25727af317f9b6d82817725bf7602e4c93b514c"},"schema_version":"1.0","source":{"id":"2508.02217","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02217","created_at":"2026-06-01T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02217v2","created_at":"2026-06-01T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02217","created_at":"2026-06-01T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"TXLGGEDY5KA5","created_at":"2026-06-01T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"TXLGGEDY5KA5ONUL","created_at":"2026-06-01T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"TXLGGEDY","created_at":"2026-06-01T01:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:1467b3941a46977c5bace6330b2bcf56dda5659e2d61eb2a11efc7b4170979c4","target":"graph","created_at":"2026-06-01T01:03:44Z","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/2508.02217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective reinforcement learning (MORL) is a fundamental framework for real-world decision-making problems involving multiple conflicting criteria. Existing multi-policy (MP) methods typically rely on online evolutionary frameworks that maintain large policy populations, leading to high sample complexity and excessive agent-environment interactions. To mitigate these limitations, we present Multi-policy Pareto Front Tracking (MPFT), a framework without a self-evolving population. It leverages an efficient Pareto-tracking mechanism initialized with single-objective extreme policies to tra","authors_text":"Jian Li, Junmei Yao, Kaichen Liu, Yueling Che, Zeyu Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T09:09:04Z","title":"Population-Free Pareto Tracking for Sample-Efficient Multi-Policy MORL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02217","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":"sha256:08133ed08af342f2dc5be7b882a60c08629001be5a6120bf773751ca7919c48d","target":"record","created_at":"2026-06-01T01:03:44Z","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":"ad9bf6d231b090d91020160317bf8b07376d74b33c3d876887aac4ab672484fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T09:09:04Z","title_canon_sha256":"463dd0847fc537c31a05dc8ac25727af317f9b6d82817725bf7602e4c93b514c"},"schema_version":"1.0","source":{"id":"2508.02217","kind":"arxiv","version":2}},"canonical_sha256":"9dd6631078ea81d7368b1e261a939bb46c9d10b7b86918e08416c7e2dd159d84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dd6631078ea81d7368b1e261a939bb46c9d10b7b86918e08416c7e2dd159d84","first_computed_at":"2026-06-01T01:03:44.275451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:44.275451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Be+8S68veR7hT2TGc4itKaV3X1E7C3KkH90hgVp/8TbveIZzSRxvRl31JUFIadRXhCTeoV2oFDhsWz0W9oLcAA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:44.277020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02217","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08133ed08af342f2dc5be7b882a60c08629001be5a6120bf773751ca7919c48d","sha256:1467b3941a46977c5bace6330b2bcf56dda5659e2d61eb2a11efc7b4170979c4"],"state_sha256":"b2a70af1d5a75c3d3ec4754b8906780db7abebfc7f9f9f5074b8f10a73c8e268"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x5/1g7L/2u9ziFmOssDCmhHg41IZ87xxDqBBAhHJj//CPsbCH1h2oANqpj2lCyBGxc+YLZMMixw9ooUe4VYXBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T23:03:44.651187Z","bundle_sha256":"f8e84ee696eb4f0a8e7cb4fa11b087e36ff7ef9773c2306144456e7c29ba9826"}}