{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AF6JWETJLXAD67NDCBMLHL42UZ","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":"dc7b776b403ca60d4e413501b78d26aab85d5902bc49f584bd2f1eff5c565664","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:34:13Z","title_canon_sha256":"ec451db23e60b61ad1cdd981c72a5581de602871af5773a5a00e2d7288e53a0a"},"schema_version":"1.0","source":{"id":"2605.14494","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14494","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14494v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14494","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"AF6JWETJLXAD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"AF6JWETJLXAD67ND","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"AF6JWETJ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:7ec8a72798a76e223a9f12f2ecb7e8458f3974a988202f45470f73c5f55124c0","target":"graph","created_at":"2026-05-17T23:39:06Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"NeurPRISE consistently achieves competitive regret relative to comprehensive methods, maintains strong scalability with varying numbers of scenarios, and delivers 7-200x speedup over PRISE. NeurPRISE also exhibits strong zero-shot generalization, effectively handling instances with larger problem scales (up to 5x), more scenarios (up to 4x), and distribution shifts."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the marginal impact of each scenario on the recourse cost can be accurately approximated by a GNN-Transformer trained only on PRISE's selections, without needing to solve the full subproblems at inference time, and that this approximation transfers across problem scales and distributions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"NeurPRISE trains a GNN-Transformer via imitation learning to mimic a lookahead heuristic for scenario reduction in 2RO, delivering 7-200x speedups with competitive regret on three test problems and zero-shot generalization."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A GNN-Transformer trained to imitate a lookahead heuristic selects reduced scenarios for two-stage robust optimization while matching quality at 7-200x higher speed."}],"snapshot_sha256":"57f20ffff208781e1992a28627b8486606ca447d3768eddf4cbd52b165fc65e5"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Two-Stage Robust Optimization (2RO) with discrete uncertainty is challenging, often rendering exact solutions prohibitive. Scenario reduction alleviates this issue by selecting a small, representative subset of scenarios to enable tractable computation. However, existing methods are largely problem-agnostic, operating solely on the uncertainty set without consulting the feasible region or recourse structure. In this paper, we introduce PRISE, a problem-driven sequential lookahead heuristic that constructs reduced scenario sets by evaluating the marginal impact of each scenario. While PRISE yie","authors_text":"Jianan Zhou, Jieyi Bi, Jie Zhang, Tianjue Lin, Wen Song, Yaoxin Wu, Zhiguang Cao","cross_cats":["cs.LG"],"headline":"A GNN-Transformer trained to imitate a lookahead heuristic selects reduced scenarios for two-stage robust optimization while matching quality at 7-200x higher speed.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:34:13Z","title":"Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty"},"references":{"count":37,"internal_anchors":1,"resolved_work":37,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Robust solutions of linear programming problems contaminated with uncertain data.Mathematical programming, 88(3):411–424, 2000","work_id":"dd148461-db5f-48e9-a94a-5830912210c7","year":2000},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Adjustable robust solutions of uncertain linear programs.Mathematical programming, 99(2):351–376, 2004","work_id":"2fd54eec-a62e-4aa2-8c28-a355dd7bb338","year":2004},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Princeton University Press","work_id":"58a27603-78b1-4098-b51c-1b4ea23e8fa8","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Finite adaptability in multistage linear optimization.IEEE Transactions on Automatic Control, 55(12):2751–2766, 2010","work_id":"24327f44-5d9f-4805-a4cb-40d9b227382f","year":2010},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Design of near optimal decision rules in multistage adaptive mixed-integer optimization.Operations Research, 63(3):610–627, 2015","work_id":"dd3882c4-c615-43f7-bf55-efc5178e92f2","year":2015}],"snapshot_sha256":"883ce7cab3cd6071d374c4d27beb2ac16c5122a84a7bd1643847ae00a2d20ec5"},"source":{"id":"2605.14494","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:00:16.509140Z","id":"62f87a8e-2a1d-46b5-8c7f-f73965a6069c","model_set":{"reader":"grok-4.3"},"one_line_summary":"NeurPRISE trains a GNN-Transformer via imitation learning to mimic a lookahead heuristic for scenario reduction in 2RO, delivering 7-200x speedups with competitive regret on three test problems and zero-shot generalization.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A GNN-Transformer trained to imitate a lookahead heuristic selects reduced scenarios for two-stage robust optimization while matching quality at 7-200x higher speed.","strongest_claim":"NeurPRISE consistently achieves competitive regret relative to comprehensive methods, maintains strong scalability with varying numbers of scenarios, and delivers 7-200x speedup over PRISE. NeurPRISE also exhibits strong zero-shot generalization, effectively handling instances with larger problem scales (up to 5x), more scenarios (up to 4x), and distribution shifts.","weakest_assumption":"That the marginal impact of each scenario on the recourse cost can be accurately approximated by a GNN-Transformer trained only on PRISE's selections, without needing to solve the full subproblems at inference time, and that this approximation transfers across problem scales and distributions."}},"verdict_id":"62f87a8e-2a1d-46b5-8c7f-f73965a6069c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:33b063fd2cd018a6f29a22ea3c5987b3048fbe7deff2a446a84610ebbd2ef905","target":"record","created_at":"2026-05-17T23:39:06Z","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":"dc7b776b403ca60d4e413501b78d26aab85d5902bc49f584bd2f1eff5c565664","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:34:13Z","title_canon_sha256":"ec451db23e60b61ad1cdd981c72a5581de602871af5773a5a00e2d7288e53a0a"},"schema_version":"1.0","source":{"id":"2605.14494","kind":"arxiv","version":1}},"canonical_sha256":"017c9b12695dc03f7da31058b3af9aa6721e19271ef55e9fa5ab0402f64edf90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"017c9b12695dc03f7da31058b3af9aa6721e19271ef55e9fa5ab0402f64edf90","first_computed_at":"2026-05-17T23:39:06.397775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:06.397775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zGif5kYktsQHJbZFIogmqES5bnJ6DgMFwtyS6vy21CL10LQvz6GFRn8bFnAphnQ8eQFnJd7C4Ku/SwM/vOpHCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:06.398522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14494","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33b063fd2cd018a6f29a22ea3c5987b3048fbe7deff2a446a84610ebbd2ef905","sha256:7ec8a72798a76e223a9f12f2ecb7e8458f3974a988202f45470f73c5f55124c0"],"state_sha256":"d8be05d8a88dce8b2eb3cf780164f5aa50e55d23ba1d0606f93872ccd683a56f"}