{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BOXFZXQBNG4HMFOGDQTVDAE2BK","short_pith_number":"pith:BOXFZXQB","canonical_record":{"source":{"id":"2606.22146","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T16:55:48Z","cross_cats_sorted":[],"title_canon_sha256":"a579d645cef241cfe594ea8ed0d14f8c11f974ffb30793a891fbeb24f923c19d","abstract_canon_sha256":"97857ed0b75638238c2c44a10cf908a79666aaea640b1d200234e44e0a7660e7"},"schema_version":"1.0"},"canonical_sha256":"0bae5cde0169b87615c61c2751809a0a91388ff179d540e484b0d25fade85f50","source":{"kind":"arxiv","id":"2606.22146","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22146","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22146v1","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22146","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"BOXFZXQBNG4H","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"BOXFZXQBNG4HMFOG","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"BOXFZXQB","created_at":"2026-06-23T02:13:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BOXFZXQBNG4HMFOGDQTVDAE2BK","target":"record","payload":{"canonical_record":{"source":{"id":"2606.22146","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T16:55:48Z","cross_cats_sorted":[],"title_canon_sha256":"a579d645cef241cfe594ea8ed0d14f8c11f974ffb30793a891fbeb24f923c19d","abstract_canon_sha256":"97857ed0b75638238c2c44a10cf908a79666aaea640b1d200234e44e0a7660e7"},"schema_version":"1.0"},"canonical_sha256":"0bae5cde0169b87615c61c2751809a0a91388ff179d540e484b0d25fade85f50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:29.585746Z","signature_b64":"pPoEzLgrDRl2MatnQuQhtbstcHjJY/WmqK8wTx07lOqX9OUXbew5DKEFaKPPlgiZKvZBVuZMc4VwuHu1JNUkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bae5cde0169b87615c61c2751809a0a91388ff179d540e484b0d25fade85f50","last_reissued_at":"2026-06-23T02:13:29.585326Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:29.585326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.22146","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":"2026-06-23T02:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lu4Q0DVMJsv0hXS+kvcaKUhKTrOerTOwe/Htt4yy2A0qeICCUDlxIMGdylvnjTKGctRQ8aaB5e0W8KcsdvFLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T19:11:27.149373Z"},"content_sha256":"f2a83959ed6c3142d86f81fa6712da25672336441715ddecc8774ba57faefee2","schema_version":"1.0","event_id":"sha256:f2a83959ed6c3142d86f81fa6712da25672336441715ddecc8774ba57faefee2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BOXFZXQBNG4HMFOGDQTVDAE2BK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bahrul Ilmi Nasution, Josh Tingey, Pradyumn Shukla, Richard Allmendinger, Rifny Rachman, Wei Pan","submitted_at":"2026-06-20T16:55:48Z","abstract_excerpt":"Meta-reinforcement learning is a promising approach to multi-objective optimisation because it enables rapid policy adaptation across changing environments and preference settings. However, conventional few-shot methods usually fine-tune from a single shared meta-policy, which can reduce solution diversity and limit exploration of the Pareto front, especially in high-dimensional combinatorial problems such as supply chain optimisation. We propose a population-based Meta-reinforcement learning framework that combines decomposition with evolutionary search in scalarisation weight space. The fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22146","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/2606.22146/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":"2026-06-23T02:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v532C0qzKoFbCKN5C6KBMXqC5IdwChrAQcl0ZQLq//WcoZ2aS04ZzwCTNdozOduMPeTs2Hu25QxjHZe3MulcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T19:11:27.149760Z"},"content_sha256":"da48c6cf51cd2b9ebdeb4c6990faf2244e698874ba298c26ab98a2ef6d9d1da6","schema_version":"1.0","event_id":"sha256:da48c6cf51cd2b9ebdeb4c6990faf2244e698874ba298c26ab98a2ef6d9d1da6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BOXFZXQBNG4HMFOGDQTVDAE2BK/bundle.json","state_url":"https://pith.science/pith/BOXFZXQBNG4HMFOGDQTVDAE2BK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BOXFZXQBNG4HMFOGDQTVDAE2BK/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":"2026-07-01T19:11:27Z","links":{"resolver":"https://pith.science/pith/BOXFZXQBNG4HMFOGDQTVDAE2BK","bundle":"https://pith.science/pith/BOXFZXQBNG4HMFOGDQTVDAE2BK/bundle.json","state":"https://pith.science/pith/BOXFZXQBNG4HMFOGDQTVDAE2BK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BOXFZXQBNG4HMFOGDQTVDAE2BK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BOXFZXQBNG4HMFOGDQTVDAE2BK","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":"97857ed0b75638238c2c44a10cf908a79666aaea640b1d200234e44e0a7660e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T16:55:48Z","title_canon_sha256":"a579d645cef241cfe594ea8ed0d14f8c11f974ffb30793a891fbeb24f923c19d"},"schema_version":"1.0","source":{"id":"2606.22146","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22146","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22146v1","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22146","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"BOXFZXQBNG4H","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"BOXFZXQBNG4HMFOG","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"BOXFZXQB","created_at":"2026-06-23T02:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:da48c6cf51cd2b9ebdeb4c6990faf2244e698874ba298c26ab98a2ef6d9d1da6","target":"graph","created_at":"2026-06-23T02:13:29Z","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/2606.22146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-reinforcement learning is a promising approach to multi-objective optimisation because it enables rapid policy adaptation across changing environments and preference settings. However, conventional few-shot methods usually fine-tune from a single shared meta-policy, which can reduce solution diversity and limit exploration of the Pareto front, especially in high-dimensional combinatorial problems such as supply chain optimisation. We propose a population-based Meta-reinforcement learning framework that combines decomposition with evolutionary search in scalarisation weight space. The fram","authors_text":"Bahrul Ilmi Nasution, Josh Tingey, Pradyumn Shukla, Richard Allmendinger, Rifny Rachman, Wei Pan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T16:55:48Z","title":"Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22146","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:f2a83959ed6c3142d86f81fa6712da25672336441715ddecc8774ba57faefee2","target":"record","created_at":"2026-06-23T02:13:29Z","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":"97857ed0b75638238c2c44a10cf908a79666aaea640b1d200234e44e0a7660e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T16:55:48Z","title_canon_sha256":"a579d645cef241cfe594ea8ed0d14f8c11f974ffb30793a891fbeb24f923c19d"},"schema_version":"1.0","source":{"id":"2606.22146","kind":"arxiv","version":1}},"canonical_sha256":"0bae5cde0169b87615c61c2751809a0a91388ff179d540e484b0d25fade85f50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bae5cde0169b87615c61c2751809a0a91388ff179d540e484b0d25fade85f50","first_computed_at":"2026-06-23T02:13:29.585326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:29.585326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pPoEzLgrDRl2MatnQuQhtbstcHjJY/WmqK8wTx07lOqX9OUXbew5DKEFaKPPlgiZKvZBVuZMc4VwuHu1JNUkBg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:29.585746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22146","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2a83959ed6c3142d86f81fa6712da25672336441715ddecc8774ba57faefee2","sha256:da48c6cf51cd2b9ebdeb4c6990faf2244e698874ba298c26ab98a2ef6d9d1da6"],"state_sha256":"dd42f6d80aa10d9d8e695c85a51ec64fea8e1554e6438a98e58ad08d22419078"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H0JaqddzX0EHplW7H/XvglSl23wqZjci8FPwNmGmgTI1aEbWnvladLK9N/e47JzqsH2h9kCOFfKq5rGGvb5JCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T19:11:27.151724Z","bundle_sha256":"60cf47afa8d1098dd5e5f968a4689ec6841b9143d1fb32b9e13c0ebc84d17c98"}}