{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O6IRHCDJRJUJXZLTP3WSTQT24I","short_pith_number":"pith:O6IRHCDJ","schema_version":"1.0","canonical_sha256":"77911388698a689be5737eed29c27ae232b4ea5399357e92b0ea4f452715c480","source":{"kind":"arxiv","id":"2112.00874","version":1},"attestation_state":"computed","paper":{"title":"Neural Stochastic Dual Dynamic Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Dale Schuurmans, Hanjun Dai, Yuan Xue, Zia Syed","submitted_at":"2021-12-01T22:55:23Z","abstract_excerpt":"Stochastic dual dynamic programming (SDDP) is a state-of-the-art method for solving multi-stage stochastic optimization, widely used for modeling real-world process optimization tasks. Unfortunately, SDDP has a worst-case complexity that scales exponentially in the number of decision variables, which severely limits applicability to only low dimensional problems. To overcome this limitation, we extend SDDP by introducing a trainable neural model that learns to map problem instances to a piece-wise linear value function within intrinsic low-dimension space, which is architected specifically to "},"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":"2112.00874","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T22:55:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ea8e5b1e05ed4c2fdef743524e5ef8aed8aaa41434c345c40627d03be784e69b","abstract_canon_sha256":"d66ec42581005531a54fbec64428b85f3f602619d73910c0833a634bcebeb04a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:00.699125Z","signature_b64":"jya7Xom/4rB29W18uWyBH4lJwkkbzR3sRgAQyY5q8Wj1yTi6Q7voiQeofWXr32vxgeYFZ6dq/pnLRFo3Q0XwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77911388698a689be5737eed29c27ae232b4ea5399357e92b0ea4f452715c480","last_reissued_at":"2026-07-05T03:37:00.698713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:00.698713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Stochastic Dual Dynamic Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Dale Schuurmans, Hanjun Dai, Yuan Xue, Zia Syed","submitted_at":"2021-12-01T22:55:23Z","abstract_excerpt":"Stochastic dual dynamic programming (SDDP) is a state-of-the-art method for solving multi-stage stochastic optimization, widely used for modeling real-world process optimization tasks. Unfortunately, SDDP has a worst-case complexity that scales exponentially in the number of decision variables, which severely limits applicability to only low dimensional problems. To overcome this limitation, we extend SDDP by introducing a trainable neural model that learns to map problem instances to a piece-wise linear value function within intrinsic low-dimension space, which is architected specifically to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00874","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/2112.00874/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":"2112.00874","created_at":"2026-07-05T03:37:00.698766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.00874v1","created_at":"2026-07-05T03:37:00.698766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00874","created_at":"2026-07-05T03:37:00.698766+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6IRHCDJRJUJ","created_at":"2026-07-05T03:37:00.698766+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6IRHCDJRJUJXZLT","created_at":"2026-07-05T03:37:00.698766+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6IRHCDJ","created_at":"2026-07-05T03:37:00.698766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01524","citing_title":"Flexible and Reliable Network Design for Emerging Transportation Services: Multi-stage Stochastic Programming Approach","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2505.05261","citing_title":"ICNN-enhanced 2SP: Leveraging input convex neural networks for solving two-stage stochastic programming","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O6IRHCDJRJUJXZLTP3WSTQT24I","json":"https://pith.science/pith/O6IRHCDJRJUJXZLTP3WSTQT24I.json","graph_json":"https://pith.science/api/pith-number/O6IRHCDJRJUJXZLTP3WSTQT24I/graph.json","events_json":"https://pith.science/api/pith-number/O6IRHCDJRJUJXZLTP3WSTQT24I/events.json","paper":"https://pith.science/paper/O6IRHCDJ"},"agent_actions":{"view_html":"https://pith.science/pith/O6IRHCDJRJUJXZLTP3WSTQT24I","download_json":"https://pith.science/pith/O6IRHCDJRJUJXZLTP3WSTQT24I.json","view_paper":"https://pith.science/paper/O6IRHCDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.00874&json=true","fetch_graph":"https://pith.science/api/pith-number/O6IRHCDJRJUJXZLTP3WSTQT24I/graph.json","fetch_events":"https://pith.science/api/pith-number/O6IRHCDJRJUJXZLTP3WSTQT24I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6IRHCDJRJUJXZLTP3WSTQT24I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6IRHCDJRJUJXZLTP3WSTQT24I/action/storage_attestation","attest_author":"https://pith.science/pith/O6IRHCDJRJUJXZLTP3WSTQT24I/action/author_attestation","sign_citation":"https://pith.science/pith/O6IRHCDJRJUJXZLTP3WSTQT24I/action/citation_signature","submit_replication":"https://pith.science/pith/O6IRHCDJRJUJXZLTP3WSTQT24I/action/replication_record"}},"created_at":"2026-07-05T03:37:00.698766+00:00","updated_at":"2026-07-05T03:37:00.698766+00:00"}