{"as_of":"2026-08-18T10:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4d97341be9872c0cc7af54502f4892bc5c845d826c2abf71d1fcd5370faffa83","coverage":[{"denominator":92,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":92,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T23:30:25.048319Z","state":"measured"},{"denominator":92,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":92,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.24007/citation-record","integrity":"/paper/2607.24007/integrity","json":"/paper/2607.24007/citation-record.json","paper":"/paper/2607.24007"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.093389Z","title":"predict, then optimize","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.093389Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:c41dc864b5c32538b8d83be54d839a5ca68f765724b858ab7b3f6906c06c6174","observation_id":"4ea29477-ef99-494c-bb12-4017a7896cd4","resolution":{"observed_at":"2026-07-31T23:30:16.093389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.157227Z","title":"Management Science , volume=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.157227Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:fced340f25a6729aa56fbda121baee8e405cb3738cbffed08e5f930f0a2171c6","observation_id":"38d2be33-13e9-4046-ad42-76c3e0f36dcc","resolution":{"observed_at":"2026-07-31T23:30:16.157227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.212001Z","title":"2013 , publisher=","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.212001Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:13802dd5fa9110ef16271f2e16b9ba65b7f72c9bf09b52b18a965e802315664c","observation_id":"21d43b77-06b0-4bd5-9dda-318064fb86ff","resolution":{"observed_at":"2026-07-31T23:30:16.212001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.252364Z","title":"Neural networks , volume=","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.252364Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:2f5ecdb6436cf8b310a4fb6a951513bbff4f341e91b5b4c8d434414560b586c4","observation_id":"36199906-e343-4955-9908-49d03096465b","resolution":{"observed_at":"2026-07-31T23:30:16.252364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.300793Z","title":"Neural networks , volume=","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.300793Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:ada44f8a45a9f862d0ef8dc076c9090d2676ddf6389eda7c17b0166ca061bbb6","observation_id":"d671b7f1-10d8-45df-a52b-9d21ba40a8f6","resolution":{"observed_at":"2026-07-31T23:30:16.300793Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.348377Z","title":"Proceedings of the AAAI Conference on Artificial Intelligence , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.348377Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:2b08febb555ca5213c33bb506d5ab848abdd0e5ecc6e2d61bf9f63a8fbdb3c5c","observation_id":"20777408-08e6-4fdf-8339-4ee01c0e25d9","resolution":{"observed_at":"2026-07-31T23:30:16.348377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.427401Z","title":"Mathematical Programming Computation , volume=","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.427401Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:16820d03952af887cc2e6bb6bf0f9e575503c2ae8c9eb1dcefade15eff7e810e","observation_id":"23de318d-d5da-47e8-aac0-30551f1f6580","resolution":{"observed_at":"2026-07-31T23:30:16.427401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.481974Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.481974Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:2d2977ac68156e6327e6cc791f1037ac33d5216cdce3f494949f06eef0bdfa6a","observation_id":"3718fb7a-02be-4fbb-a0b3-016116d13a0d","resolution":{"observed_at":"2026-07-31T23:30:16.481974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.540193Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.540193Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:d67d28aee6ac2ce5069bb35b38a9d74c5ee5735797e51781420279ff574d8538","observation_id":"c655fd8e-2683-4a1a-bb51-61d578703277","resolution":{"observed_at":"2026-07-31T23:30:16.540193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.595205Z","title":"Mathematical programming , volume=","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.595205Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:5104ea89763904d675558d6a7399f34ba6129bd3bb021629433a0b881cc65a4b","observation_id":"d48f4d9e-fb0f-42e0-98e9-06412d39fa1e","resolution":{"observed_at":"2026-07-31T23:30:16.595205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.625424Z","title":"Conference on Learning Theory , pages=","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.625424Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:5eda5c77108ac34d807ea83e9b5fac06f49577c8dc6aaa908ff5414d18c694b6","observation_id":"bd0186d2-afd0-4a00-880b-cccbcbb4c708","resolution":{"observed_at":"2026-07-31T23:30:16.625424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.682619Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.682619Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:59165acb6704b6c0aaa09c7da92e080473938080c0377cc510e26cc42b48ed2e","observation_id":"925c58f4-ac1c-4b0e-be20-37e2f313fd7e","resolution":{"observed_at":"2026-07-31T23:30:16.682619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.738172Z","title":"1970 , publisher=","venue":null,"work_id":null,"year":1970},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.738172Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:d07afb6b4f8cd927ed9d766651a69ee67c06ee51c7958cb81943c75d860b8c55","observation_id":"5db7c17e-44ed-41bc-b1e4-eb0a9354d898","resolution":{"observed_at":"2026-07-31T23:30:16.738172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.781891Z","title":"European Journal of Operational Research , volume=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.781891Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:678902d524c76413d4b65098d9889cf0e1562a4c775b3cfa656d62ec8ec78b7e","observation_id":"111e98f5-927b-4d37-bfbf-72c01fc0729e","resolution":{"observed_at":"2026-07-31T23:30:16.781891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.860730Z","title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pages=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.860730Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:aab2078f074b9cc44a733510c6aae40c3e8f269d741ca898046bf384bef34036","observation_id":"de999c3e-cf4e-431e-b2e1-f57ba166fadd","resolution":{"observed_at":"2026-07-31T23:30:16.860730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.09170","last_updated":"2021-11-17T15:01:53Z","snapshot_observed_at":"2026-08-16T17:41:09.256263Z","submitted_at":"2021-11-17T15:01:53Z","title":"A Universal End-to-End Approach to Portfolio Optimization via Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.09170","snapshot_observed_at":"2026-07-31T23:30:16.920235Z","title":"arXiv preprint arXiv:2111.09170 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.920235Z"},"links":{"cited_paper":"/paper/2111.09170","citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:7a1a2c876ebe7582b067b0b1f11bb9b47fd60d9eab9a57524e5ceee0bc6e1af7","observation_id":"0bd4fa11-b041-4dd7-a816-5d13e77fb8ed","resolution":{"observed_at":"2026-07-31T23:30:16.920235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:16.995030Z","title":"IEEE Transactions on Power Systems , volume=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:16.995030Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:1752ea0457aecf6436b6453661034dac960ce82a22bdc0a78b9f1ffe3b54a982","observation_id":"48333572-7f68-43d2-b9ae-3eb8655bcd30","resolution":{"observed_at":"2026-07-31T23:30:16.995030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:17.023471Z","title":"Operations Research , volume=","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:17.023471Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:6f1b0b87470f7a49e051d1315a6821223a03892a3b637de7ff4eef5a9b814d5d","observation_id":"4afdb2f8-97eb-4365-8936-6fa5a822579a","resolution":{"observed_at":"2026-07-31T23:30:17.023471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:17.112925Z","title":"Management Science , volume=","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:17.112925Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:295e0a19e856ec3af571f2aa4927b8c1cbd697259bedaafd578b307b7c4f73f4","observation_id":"af039af7-4f15-45d4-80cf-c158d8e71de1","resolution":{"observed_at":"2026-07-31T23:30:17.112925Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:17.244250Z","title":"On Data-Driven Prescriptive Analytics with Side Information: A Regularized","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:17.244250Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:3783731f8561903edee08e0efe3c9ba4b858a56afc6f91b0048d4a36612b9244","observation_id":"989b2ec2-1613-4c51-a3e0-bc34bfdb0c65","resolution":{"observed_at":"2026-07-31T23:30:17.244250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:17.345010Z","title":"Operations Research , volume=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:17.345010Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:2807661a6f8a947688fbe2697042c69bb6000e09f94788beecb3d213a8572734","observation_id":"bf147adc-e8d8-45bf-9d73-49399cf384f8","resolution":{"observed_at":"2026-07-31T23:30:17.345010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:17.440789Z","title":"Mathematical Programming , volume=","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:17.440789Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:7bf1c0eed89bb74de1b279b7763e4860fcf791ad43c7bb6845208a1242344a96","observation_id":"14dae24b-26f3-42c8-ad04-27c325de80aa","resolution":{"observed_at":"2026-07-31T23:30:17.440789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:17.572579Z","title":"2022 , eprint=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:17.572579Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:75d222107eb6201bfb57502fba5d5d0a1cec147755b1b553a2f2ff158ffc1cc5","observation_id":"20bc8e37-cec6-4eff-84a2-adf5a260d7ff","resolution":{"observed_at":"2026-07-31T23:30:17.572579Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:17.650509Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:17.650509Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:bc2cf2dfe28182f9fdf1103d0e2f456171bb1369d710aa3529037bfc737a6002","observation_id":"f4e806da-5e50-4cd3-ab3f-ac95d1c50d2d","resolution":{"observed_at":"2026-07-31T23:30:17.650509Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:17.735149Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:17.735149Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:8ae65876e5fb5322955f3a745dd9854e0862f839753cbb41cdd576bca8f3414d","observation_id":"fb98c202-f1a5-4795-b627-899781fbe12e","resolution":{"observed_at":"2026-07-31T23:30:17.735149Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:17.835734Z","title":"International Conference on Machine Learning , pages=","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:17.835734Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:4ab935e1a643dc7b80abd6b29d6797c1e02aeae00c0d302c57b15c4a04748fa9","observation_id":"f4301313-a5df-4d36-89e2-f7e27885504e","resolution":{"observed_at":"2026-07-31T23:30:17.835734Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:17.931595Z","title":"Operations Research , volume=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:17.931595Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:f33aa45b80a18e14456d837d9a697cf3b600cb5845ae9eab15532f609d8b1452","observation_id":"1162bdc8-994f-4756-8fa5-f3e8e322b2ce","resolution":{"observed_at":"2026-07-31T23:30:17.931595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:18.009778Z","title":"Operations Research , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:18.009778Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:bc9633aaaa6592034ae5256678147491c56862b9ef834afa4024435eb0ff07f4","observation_id":"84dc5aeb-d62f-424a-bf8e-41de546a74d4","resolution":{"observed_at":"2026-07-31T23:30:18.009778Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:18.099405Z","title":"Management Science , volume=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:18.099405Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:631f8aa66ddc97c66693fb92cd2ac52d8070033ca17997617840f35df6694429","observation_id":"5109a45b-a5c8-46b6-bfaa-402eea71fb38","resolution":{"observed_at":"2026-07-31T23:30:18.099405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:18.319254Z","title":"Iise Transactions , volume=","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:18.319254Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:4d81efa426407ed47029ac7f05151e6f723e30a73d546336956d1045e2a0ae72","observation_id":"01b0f512-899d-4d2f-befd-b58abcb20756","resolution":{"observed_at":"2026-07-31T23:30:18.319254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:18.411704Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:18.411704Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:6405d57c407ba90f9e127c26bbb17df23ac3e6d12df134c1b6c32b236dd005f2","observation_id":"60954564-fdb4-4d0d-b458-5d0b6f92f8c8","resolution":{"observed_at":"2026-07-31T23:30:18.411704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:18.498487Z","title":"European Journal of Operational Research , volume=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:18.498487Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:5bba9eb30fb6e26a28fc830b7c8d0ec1c519044a2a2042498a41e18e6411518f","observation_id":"c40903c1-b7a5-49e3-9b75-f4d38c33210f","resolution":{"observed_at":"2026-07-31T23:30:18.498487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:18.592476Z","title":"The Review of Financial Studies , volume=","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:18.592476Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:8f6a0939405264939c2e2464e87fe72c8bd506adb6dab955df60af591b185eba","observation_id":"af1e5b26-e28f-4afc-b1c2-3e73970996db","resolution":{"observed_at":"2026-07-31T23:30:18.592476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:18.682989Z","title":"INFOR: Information Systems and Operational Research , volume=","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:18.682989Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:25c1ecb933b5ec00743ab2ad3a3c17c608edb460080af56613e11c2dc6664827","observation_id":"dd973528-4855-43a9-8ce6-b1bb033fb7b0","resolution":{"observed_at":"2026-07-31T23:30:18.682989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:18.752708Z","title":"arXiv preprint arXiv:2509.14557 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:18.752708Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:977e40722e09156795c3b29a76629cfaf03deb71cba20ace5f7bb8ecd6fcc0cf","observation_id":"188c1032-ce89-4686-9bdf-cc347c03d80e","resolution":{"observed_at":"2026-07-31T23:30:18.752708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:18.895472Z","title":"Operations Research , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:18.895472Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:92cc3bc82ee3626adf70f3a2fad67856e7c08feef3657a7a03e1ebfcccc76ae7","observation_id":"7a11ddb4-1255-4cb1-a448-9878bb77a275","resolution":{"observed_at":"2026-07-31T23:30:18.895472Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:18.992037Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:18.992037Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:ab8b0c3110dee10f8bd813841544b3edec3fde38d19a088165382fb81cf244f8","observation_id":"d8a2c79c-d889-457e-82a2-63d979c5f8d1","resolution":{"observed_at":"2026-07-31T23:30:18.992037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:19.087691Z","title":"Available at SSRN 3623006 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:19.087691Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:5c6cb0ad2c63293d42bb44a18700df54882bb344511e50e73893a656fabcba27","observation_id":"e5495216-3345-42ec-a327-45569e33b376","resolution":{"observed_at":"2026-07-31T23:30:19.087691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:19.169337Z","title":"Proceedings of the AAAI Conference on Artificial Intelligence , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:19.169337Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:2805cef24900f839729d69cfe7c708ee129698b0ea396a29058d249fc4612084","observation_id":"2792a815-cdc9-427f-8ac0-b8aeab85d154","resolution":{"observed_at":"2026-07-31T23:30:19.169337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:19.263447Z","title":"International Conference on Machine Learning , pages=","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:19.263447Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:4c639cf0100388889f69a22452adf4ec300dca0711f0cd394474f7f713fa3f36","observation_id":"a1625fe3-45ae-4baa-8440-19b4f6ca442f","resolution":{"observed_at":"2026-07-31T23:30:19.263447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:19.364995Z","title":"Management Science , volume=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:19.364995Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:256b866db657cb6a97025494cb64561044bb20a154d99cde1fcfa320f0879c96","observation_id":"9a899bb9-29d8-455b-96fb-01a6d6ce406c","resolution":{"observed_at":"2026-07-31T23:30:19.364995Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:19.474078Z","title":"Unpublished Manuscript, http://ttic","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:19.474078Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:ee734c8a13eb75977749759c4cd338d76f383e0297858549421ca638da8646e6","observation_id":"c8a10e37-3534-4e9d-944a-4e82f097b6cc","resolution":{"observed_at":"2026-07-31T23:30:19.474078Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:19.570464Z","title":"2009 , publisher=","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:19.570464Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:ddb7be0422247e1214148ff932c875e96973d4f260331fbb95105bdd8905c853","observation_id":"3cbfdf23-52df-4799-9d55-597006dfb0ee","resolution":{"observed_at":"2026-07-31T23:30:19.570464Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:19.740915Z","title":"Practical","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:19.740915Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:430c9b306f3f469712e57b653eb83c09aae6892d63c0670674efb13560907cad","observation_id":"3b62e66c-b885-41eb-bf1a-0a2f24a7f642","resolution":{"observed_at":"2026-07-31T23:30:19.740915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:19.839332Z","title":"Journal of Global optimization , volume=","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:19.839332Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:77bac5415ec2932b8ec75b88c773ea574d96f831afbcbe2d7d149ddf753dcc81","observation_id":"2f48b5f8-6a2e-4f5f-bd28-479ea111152b","resolution":{"observed_at":"2026-07-31T23:30:19.839332Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:19.923770Z","title":"International Conference on Artificial Intelligence and Statistics , pages=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:19.923770Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:306e0c5f22c4e0f794ab450f906546977b8e1977b716dd0ea565917b554ae194","observation_id":"97906c18-3801-4300-b9d7-ae6f33d38054","resolution":{"observed_at":"2026-07-31T23:30:19.923770Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:20.050543Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:20.050543Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:7cdb693ff781e08b5b10fb1b58e47ec84f67d99b1f79d7e3d82e71f287177495","observation_id":"b895fd24-0f01-4c50-8307-636b43618a1e","resolution":{"observed_at":"2026-07-31T23:30:20.050543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:20.143133Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:20.143133Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:64c096009695afa58ab81a7934efdad01f3adfc02fba6b59f30a58b9ca53f4b6","observation_id":"5e43eb30-4ed7-4ff4-83b2-fa670cc8a945","resolution":{"observed_at":"2026-07-31T23:30:20.143133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:20.236943Z","title":", title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:20.236943Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:72fd8a94f49a023c36ccee4f83ebe00181b3955d9d400760a0659ed60de37779","observation_id":"2e851c92-0173-4ac2-95a0-7ab64ff24241","resolution":{"observed_at":"2026-07-31T23:30:20.236943Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:20.365460Z","title":", author=","venue":null,"work_id":null,"year":1971},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:20.365460Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:5ca1bcaf861c7355681903d7f07dcbe70be1e61c1fe61ad9ffaf7a01743cc365","observation_id":"f3b6e5f6-6c02-431c-a6fe-8fd339bb64a7","resolution":{"observed_at":"2026-07-31T23:30:20.365460Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:20.504113Z","title":"Learning with","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:20.504113Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:a17f9f58e18d198e281dfbcfe1daa2f0ac99e25d95a5ba4e5c960530a4360ad7","observation_id":"b8a9dab2-4865-4690-951c-d9b0c99e47aa","resolution":{"observed_at":"2026-07-31T23:30:20.504113Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:20.639694Z","title":"Machine learning meets","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:20.639694Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:2f15dcf06d02bb75ff8030db482fa0af204ad70cb04b8ec8b44b1e17fa837efd","observation_id":"2f93dbea-a5a1-4af7-bd1d-e33570f3c704","resolution":{"observed_at":"2026-07-31T23:30:20.639694Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:20.784865Z","title":"Online linear optimization via smoothing","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:20.784865Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:5be12e561a8557ccf2f3875d35c25f2c55e3876d83230f428bbdb71f577c6227","observation_id":"98d8ec9b-9a8c-4810-a464-6445c53fc2c1","resolution":{"observed_at":"2026-07-31T23:30:20.784865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:21.011903Z","title":"Differentiable convex optimization layers","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:21.011903Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:0b00267ba85346eb74e279e8d394e42e94eda24e1cad38bb8200ed3a4c7def37","observation_id":"f3ea18ee-e50c-417c-b2c9-0c838f9fcec9","resolution":{"observed_at":"2026-07-31T23:30:21.011903Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:21.132330Z","title":"Optnet: Differentiable optimization as a layer in neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:21.132330Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:fa235ab619f8fde6561bd6e97919b288f2adc565a1dd08f7a480084f4de1cf1f","observation_id":"f413e99a-b380-497a-a3fc-ac236a061125","resolution":{"observed_at":"2026-07-31T23:30:21.132330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:21.280225Z","title":"The big data newsvendor: Practical insights from machine learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:21.280225Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:c884758adcc84f68c0750b34250cfa4dda12234e1e337c539d3ad63516845418","observation_id":"5fe6e686-f7e4-4a59-bc96-e334f019f644","resolution":{"observed_at":"2026-07-31T23:30:21.280225Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:21.411392Z","title":"Generalization bounds for regularized portfolio selection with market side information","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:21.411392Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:f93dd9630bf5fa637de1c8e8ab9f1d889753345be2763d21f236150f701100d4","observation_id":"dc3e8767-8a77-471b-a488-c8ca8a6e6666","resolution":{"observed_at":"2026-07-31T23:30:21.411392Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:21.556899Z","title":"Learning with differentiable perturbed optimizers","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:21.556899Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:0fe299d9e49c4bfc0370bfdb3b1ef57b2f13c6265a5d9b72ca48a6fefe386d99","observation_id":"8c733647-88ea-4a04-808e-5bfe9fd1d6fe","resolution":{"observed_at":"2026-07-31T23:30:21.556899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:21.705989Z","title":"Control of uncertain systems with a set-membership description of the uncertainty","venue":null,"work_id":null,"year":1971},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:21.705989Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:3e4fcdd63fc4f8c8a6f847bea737cec7da38a443cc79f9c7d427050eb2ed47ef","observation_id":"d0ad8589-1ed9-4ea4-9f00-23c3b11cefb1","resolution":{"observed_at":"2026-07-31T23:30:21.705989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:21.845325Z","title":"From predictive to prescriptive analytics","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:21.845325Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:707bce3dcd978f10a43b579b5af4ee1ec3ff0c5cc077b30bb5bc8de761fccf7a","observation_id":"e5cd3826-b640-4d30-8b08-48351dcd501c","resolution":{"observed_at":"2026-07-31T23:30:21.845325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:21.978490Z","title":"Data-driven optimization: A reproducing kernel hilbert space approach","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:21.978490Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:d6bc559425ec5646420c9e056c32c2c65232088a2907b14669f8c767d7d1bea9","observation_id":"9c05d3a3-7c06-4b6e-80a9-0d98ece95fd4","resolution":{"observed_at":"2026-07-31T23:30:21.978490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:22.046902Z","title":"Dynamic optimization with side information","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:22.046902Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:bd9b64d413d38a5cef96535013c011bd15fbbcc9a7e0e97260c8094e7f168693","observation_id":"43956e2c-08ce-4287-9832-a9d8d6f6582e","resolution":{"observed_at":"2026-07-31T23:30:22.046902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:22.150295Z","title":"Learning with F enchel- Y oung losses","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:22.150295Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:9ec218b2adf5593a6b38625c505f0ff4216df219d623a8dbaf14de01d520ea0a","observation_id":"ce130e5f-abed-4820-a2e7-71129a506d48","resolution":{"observed_at":"2026-07-31T23:30:22.150295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:22.329594Z","title":"Nonsmooth implicit differentiation for machine-learning and optimization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:22.329594Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:e810f5182084b085bc3cac1442c8d6a78277746bd4513fcac3b34e21028421f0","observation_id":"95a7c030-d533-47e5-aaaa-efbd8fe4631a","resolution":{"observed_at":"2026-07-31T23:30:22.329594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:22.512235Z","title":"Parametric portfolio policies: Exploiting characteristics in the cross-section of equity returns","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:22.512235Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:547f1e3b0f799e148a55834435bf5b83ed5d9af4e86c2da8af5a16444c38f074","observation_id":"a6bc360c-e729-4ef3-b990-39b0a9970601","resolution":{"observed_at":"2026-07-31T23:30:22.512235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:22.691936Z","title":"End-to-end feasible optimization proxies for large-scale economic dispatch","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:22.691936Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:5995fe962c1729d8936bb37ef96ede57ac86ec4fd10a0bdd879ee6ed2efdaa3e","observation_id":"101f3e32-5c92-4aa7-98bd-bae8475cbc8e","resolution":{"observed_at":"2026-07-31T23:30:22.691936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:22.874202Z","title":"Task-based end-to-end model learning in stochastic optimization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:22.874202Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:af9c11a5a46f277d468814e8616004c1feee37cd84a7e0bc7f922e8e32af9b4d","observation_id":"163abd58-401e-4b64-8936-fc4666d2634f","resolution":{"observed_at":"2026-07-31T23:30:22.874202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:23.025887Z","title":"predict, then optimize","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:23.025887Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:eddd30ff9ee321c3626ff841f5d893927fe0b45574b26008c2d76c670e14847d","observation_id":"d636bce0-c13a-4b0f-82ee-7c7893810967","resolution":{"observed_at":"2026-07-31T23:30:23.025887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:23.176110Z","title":"Decision trees for decision-making under the predict-then-optimize framework","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:23.176110Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:91d166b44dfd817c667c41527b0dcfbde25b8a6ce00a014213cf9dc87942765d","observation_id":"2500e1c8-5643-4ebc-a598-8be5f1aec0f3","resolution":{"observed_at":"2026-07-31T23:30:23.176110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:23.332397Z","title":"Mind the (optimality) gap: a gap-aware learning rate scheduler for adversarial nets","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:23.332397Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:b2432382d5a07b0e6f1b907478a6714c363c86c2e289110e913fff184082a40b","observation_id":"40f48950-ba4e-4c74-9f60-4f77a6886533","resolution":{"observed_at":"2026-07-31T23:30:23.332397Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:23.464070Z","title":"Efficient global optimization of expensive black-box functions","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:23.464070Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:b83fcc9ba3d5374cf74dd5881019e20d03c959fdfdbd1a48dabd1e7e2e136af9","observation_id":"f0f31f71-4bf1-4383-8758-947ac31f57fa","resolution":{"observed_at":"2026-07-31T23:30:23.464070Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:23.581141Z","title":"Stochastic optimization forests","venue":null,"work_id":null,"year":1975},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:23.581141Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:a95342d430f0913bc8bdd83a3b1323483156540012a25b5a58ae02a9f4a54d27","observation_id":"dc7db5af-0a45-41f7-8bb2-abd835f3f5a0","resolution":{"observed_at":"2026-07-31T23:30:23.581141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:23.677410Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:23.677410Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:b644107fce82e5c64b12531ae0ded1d50fd47fb95744349077bdc3aa70dcfbbe","observation_id":"a6f6953c-0a7a-4e9b-9cd8-78291d7cfb0b","resolution":{"observed_at":"2026-07-31T23:30:23.677410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s10107-023-02016-z","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:31:37.213962Z","title":null,"venue":null,"work_id":"e736628a-0a7f-4fda-aeca-8bbc5935074b","year":2024},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:23.754701Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:c04e9dfaa65992ae786fdab28f961e274d1c1fbe8f9a2a5f0a62e8372ec56bda","observation_id":"3122cd8f-05cf-4a80-b81e-ab80392f89ca","resolution":{"observed_at":"2026-07-31T23:31:37.281382Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:23.806883Z","title":"Data-driven sample average approximation with covariate information","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:23.806883Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:b8feb95eb1db952961fd11783288159dfa6f13d59c5e970e06441f2c405790b8","observation_id":"7db0f9b6-68fd-4354-b8c4-747306fe9655","resolution":{"observed_at":"2026-07-31T23:30:23.806883Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:23.869667Z","title":"Risk bounds and calibration for a smart predict-then-optimize method","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:23.869667Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:e5d3dcce49235492882bc94ac0c171abf4af3d32ee8b477827a877f2c856d84a","observation_id":"66505624-61fa-46c7-917a-aeeda4b20d67","resolution":{"observed_at":"2026-07-31T23:30:23.869667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:23.949147Z","title":"Decision-driven regularization: A blended model for predict-then-optimize","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:23.949147Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:a4bbc1e37e09c45998bd59eb99e9e31f84e7d6fa3836fb4cd3d38bf0815f3171","observation_id":"14478240-3144-42f4-8e4e-5233beee5b92","resolution":{"observed_at":"2026-07-31T23:30:23.949147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.026970Z","title":"Smart predict-and-optimize for hard combinatorial optimization problems","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.026970Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:070bb2683a46ee6fb6c2a473e38a9862fa68ded018eb0e0f4b48ed85b23c9d3d","observation_id":"0a6f248d-e809-430f-839f-ce0c8c06ba19","resolution":{"observed_at":"2026-07-31T23:30:24.026970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.105321Z","title":"Calibration by distribution matching: Trainable kernel calibration metrics","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.105321Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:ecdac20cb107ea33916f3805febef0d97f53d3552f1ba8c814c8e8c5e8d90fbd","observation_id":"cb43cdfa-804e-4853-85a5-8e2445bea76d","resolution":{"observed_at":"2026-07-31T23:30:24.105321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.181111Z","title":"Smooth minimization of non-smooth functions","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.181111Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:98598f2713b0ab7ed02f900cf06afadba6d1781482824236ce7fce946ae28f04","observation_id":"31f1a0bb-7283-4ce4-ad7d-77a85d07658e","resolution":{"observed_at":"2026-07-31T23:30:24.181111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.250315Z","title":"Sparse MAP : Differentiable sparse structured inference","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.250315Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:bfc3102ed5bbb4a7e8d0455d719ed6681cd3f48c782c4f2053d5db53d6d097f3","observation_id":"c0596e75-79aa-47e2-9d6f-89a8a3fe85a6","resolution":{"observed_at":"2026-07-31T23:30:24.250315Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.297504Z","title":"Applying deep learning to the newsvendor problem","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.297504Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:454c09f13675f8c3ea81ad325090f27db72e8dfd0ff450e9c6d794fe13d88f7f","observation_id":"a3b3ec16-8b8f-4c0e-a56a-8c5b05cbdb6b","resolution":{"observed_at":"2026-07-31T23:30:24.297504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.375612Z","title":"A practical end-to-end inventory management model with deep learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.375612Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:fe99e203b20daa738c8adbe3d6e6fec09204a29c67ba628de3e6cf2a23a98ccb","observation_id":"7c778268-319b-4b6a-aa05-4f287dca9813","resolution":{"observed_at":"2026-07-31T23:30:24.375612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.455699Z","title":"Tyrrell Rockafellar","venue":null,"work_id":null,"year":1970},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.455699Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:55d4d1bfc05035b1c05957801e550a3e642f2f1c6b5c74999f1cc903ae9aabe0","observation_id":"855735d2-63de-4080-bfb5-5b6ea7e1b649","resolution":{"observed_at":"2026-07-31T23:30:24.455699Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.538815Z","title":"Tyrrell Rockafellar and Roger J.-B","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.538815Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:dbe77f0d7bc0de0178a8daa9e2685895cb5877bea00be678a894b2c6687604bd","observation_id":"bb0bc36d-0830-453c-a3e4-acf6074cc959","resolution":{"observed_at":"2026-07-31T23:30:24.538815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.623984Z","title":"Schneider and Daniel Kuhn","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.623984Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:62d0d39a4303495b4c3f5d65b7d2509ae146028b479cf3cd5bc4504d11b3bdfc","observation_id":"fc489cd9-4f8f-46c8-9fad-40bb1cedf27f","resolution":{"observed_at":"2026-07-31T23:30:24.623984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.693806Z","title":"Practical B ayesian optimization of machine learning algorithms","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.693806Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:195d006d35be3dfe71c4e13efee8b004076c6509d6029d02aa99e22fdf484f7c","observation_id":"3da58654-7af3-4948-a63e-8b1e711593e2","resolution":{"observed_at":"2026-07-31T23:30:24.693806Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.746277Z","title":"Machine learning meets M arkowitz","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.746277Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:dc0f75f3c1abc505e3648b993402626e546cd38af328dd7eb5e0adb5e6d3c390","observation_id":"b6483ff3-4a14-4468-ab0b-a37807524caa","resolution":{"observed_at":"2026-07-31T23:30:24.746277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.827967Z","title":"On data-driven prescriptive analytics with side information: A regularized N adaraya-- W atson approach","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.827967Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:74404bb46abbcc32b42e24a92482570b2f711b58a3f4380009a0a4a9ffda7710","observation_id":"8cc360ff-239a-482c-8aba-6b19d95fff0c","resolution":{"observed_at":"2026-07-31T23:30:24.827967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.905147Z","title":"Melding the data-decisions pipeline: Decision-focused learning for combinatorial optimization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.905147Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:8e7bf65bb9cdaa817a56a02c45b5ea00ca789b4562d82aaf68c2a5e2e61ceb7f","observation_id":"73339bb1-28a7-4f28-84dd-93ce1fcdaf63","resolution":{"observed_at":"2026-07-31T23:30:24.905147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:30:24.981357Z","title":"Data-driven piecewise affine decision rules for stochastic programming with covariate information","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:24.981357Z"},"links":{"citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:28036cba8f071d8df2f74570264763bb40a49d074cad91dce828c9ed12539971","observation_id":"2aef28d5-eed9-4f38-81ca-dfd8c92796c8","resolution":{"observed_at":"2026-07-31T23:30:24.981357Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.13665","last_updated":"2021-01-23T18:19:33Z","snapshot_observed_at":"2026-07-06T09:23:55.119397Z","submitted_at":"2020-05-27T21:28:43Z","title":"Deep Learning for Portfolio Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.13665","snapshot_observed_at":"2026-07-31T23:30:25.048319Z","title":"Deep learning for portfolio optimization","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","version":1},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-07-31T23:30:25.048319Z"},"links":{"cited_paper":"/paper/2005.13665","citing_paper":"/paper/2607.24007"},"observation_digest":"sha256:f447418e8038250369a3db04128988e4a236d3331aeb9023eabb48c287e4795e","observation_id":"69b83209-aa86-4c63-97fc-db3b74b0060c","resolution":{"observed_at":"2026-07-31T23:30:25.048319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.24007","last_updated":"2026-07-27T05:09:41Z","latest_version":1,"primary_category":"math.OC","snapshot_observed_at":"2026-08-13T19:57:03.716884Z","submitted_at":"2026-07-27T05:09:41Z","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies"},"reference_resolution":{"displayed":92,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":91,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":92},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 92 of 92 outbound references and 0 inbound Pith citation observations for arXiv:2607.24007."}