{"as_of":"2026-08-18T04:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4f4c0b06a3c2b086a8bee6742e58aa502ecf9a9473eca0f0864768f56e6a6022","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T12:21:10.258752Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2608.09707/citation-record","integrity":"/paper/2608.09707/integrity","json":"/paper/2608.09707/citation-record.json","paper":"/paper/2608.09707"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:10.044729Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.044729Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:6d0aa3fe4aea48b2e72217dde5451dd5bbbf827bd2b8e084be523ec959f8d163","observation_id":"86804e03-fcc7-4361-8d49-58af699bd8db","resolution":{"observed_at":"2026-08-11T12:21:10.044729Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07152","last_updated":"2017-06-14T17:59:12Z","snapshot_observed_at":"2026-08-14T21:38:34.304198Z","submitted_at":"2016-09-22T20:10:57Z","title":"Input Convex Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.07152","snapshot_observed_at":"2026-08-11T12:21:10.051913Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.051913Z"},"links":{"cited_paper":"/paper/1609.07152","citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:7bf6b56f64ee09b1a068f768adda321290e95a5d16d251906130f41723d98da9","observation_id":"1c6bcdb1-6762-45c3-9a58-6cf7bd76dc35","resolution":{"observed_at":"2026-08-11T12:21:10.051913Z","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":"2026-08-11T12:21:10.059866Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.059866Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:1f9d6624b47e267ed637964d9be04cd15e1f6ed0411e8a86d8a79812c51382a0","observation_id":"d1765981-6658-4646-ba69-b86e43f4732c","resolution":{"observed_at":"2026-08-11T12:21:10.059866Z","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":"2026-08-11T12:21:10.064315Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.064315Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:39f631254e7c21a12691915f31b0c0c8cbda35e92bcafbe79221bacd26e3cd94","observation_id":"bf3a0e37-a2f4-4e71-b1f0-fdb85ba64fac","resolution":{"observed_at":"2026-08-11T12:21:10.064315Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:12.415548Z","title":null,"venue":null,"work_id":"a1e1d0d1-26d8-4074-9c65-5655b4ae0202","year":2021},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.068833Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:08fecad47dc1da14ec1711820b5e5e8f75318b68adea6d446cb8bc2762fda0eb","observation_id":"89d164ad-bffd-4ce5-98d2-66e00e3a906d","resolution":{"observed_at":"2026-08-11T12:21:12.419071Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T12:21:10.074060Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.074060Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:c4bddf7ed614534fe78f6d3cd5cf87ffaa22f82ae3655e7c4be2f43e3f8a5b8d","observation_id":"305aa26c-56f1-4336-b171-baceb0e3c490","resolution":{"observed_at":"2026-08-11T12:21:10.074060Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.01040","last_updated":"2017-07-05T11:27:46Z","snapshot_observed_at":"2026-08-16T03:38:11.314976Z","submitted_at":"2017-04-28T12:04:02Z","title":"Maximum Resilience of Artificial Neural Networks","version":2},"cited_work":{"arxiv_id":"1705.01040","doi":"10.48550/arxiv.1705.01040","metadata_source":"pith","pith_arxiv_id":"1705.01040","snapshot_observed_at":"2026-08-11T18:16:15.004306Z","title":"Maximum Resilience of Artificial Neural Networks","venue":"cs.LG","work_id":"846d4d9f-1f33-4c52-881f-f1a0ec75a032","year":2017},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.078860Z"},"links":{"cited_paper":"/paper/1705.01040","citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:c42811044e3736abd7ef7131a18479725daa2ac6a3c2791386935ce5df7b02bc","observation_id":"81b3ae9e-f37a-40b0-ad81-13441c46328f","resolution":{"observed_at":"2026-08-11T12:21:10.461251Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.09282","last_updated":"2020-06-14T19:10:03Z","snapshot_observed_at":"2026-08-14T20:21:05.078282Z","submitted_at":"2017-10-23T20:16:55Z","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09282","snapshot_observed_at":"2026-08-11T12:21:10.082979Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.082979Z"},"links":{"cited_paper":"/paper/1710.09282","citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:adf3feb5f848ff5ac24d4b5e20a6ff4764530da8f27d7704b56cb4d10f2696e4","observation_id":"d11a501a-0a22-4279-a763-f2a9a578ef23","resolution":{"observed_at":"2026-08-11T12:21:10.082979Z","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":"2026-08-11T12:21:10.087317Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.087317Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:ff24e012b2500a14c7a109d51183b5ca6a368240e85e5f96b4448aa35559ca47","observation_id":"60f256eb-2f17-42e9-a3cd-4962a01e20c0","resolution":{"observed_at":"2026-08-11T12:21:10.087317Z","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":"2025.1446","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:12.111923Z","title":"B., & Bent, R","venue":null,"work_id":"494a8bba-4d11-4953-aa19-f27678fa838b","year":2026},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.092595Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:727c20f4295b27d7110b87f1145ee56b4c6ca8de02b14b18ae3e2ee06da04e24","observation_id":"02d2f2e4-27ec-4e00-862c-ffaff92cf05b","resolution":{"observed_at":"2026-08-11T12:21:12.117554Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T12:21:10.102756Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.102756Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:38b3c58da9b0046621fdec628f5ba90c333d39b840bbde1573766f94ddc9bc67","observation_id":"8c3a4a44-1fdc-4666-8b88-169731fab438","resolution":{"observed_at":"2026-08-11T12:21:10.102756Z","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":"2026-08-11T12:21:10.110300Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.110300Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:f599f8aad76e70f1c4862118f39b0de70f7d6b724f5bd3a629ecaea374e88389","observation_id":"e1a994ed-a6e0-4619-8b7d-532486889bb0","resolution":{"observed_at":"2026-08-11T12:21:10.110300Z","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":"2026-08-11T12:21:10.115603Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.115603Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:72cb983cd0b7a52c0b8fe448654cd4b59524ca2487f689904b25175bb0c53737","observation_id":"d03f3569-6e24-4984-ac9c-2600209e0f07","resolution":{"observed_at":"2026-08-11T12:21:10.115603Z","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/s10851-025-01253-x","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:10.419402Z","title":null,"venue":null,"work_id":"dc308321-fa48-46b3-95ec-2c19e7f40b86","year":2025},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.119532Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:7d04a5216b565c84c5b59efa97c12ae2cee04d91a3d693bc0da8d9ee7b39dae0","observation_id":"139aee2b-b762-49fb-8760-dc48df064bfa","resolution":{"observed_at":"2026-08-11T12:21:10.423583Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T12:21:10.123375Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.123375Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:6d740c87b6c0def33ddba0bddc44ddf6ee7e34b8c025701476b8e7f69443de89","observation_id":"2025609a-cf68-4975-818e-ba1288464139","resolution":{"observed_at":"2026-08-11T12:21:10.123375Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:12.403295Z","title":null,"venue":null,"work_id":"0f773df6-de9b-4d8b-95b0-ee763c129786","year":2022},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.127082Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:7fc48b679afec78434157b77297aeab2cbe2f5b111c4b0ef4835b4f4861431fd","observation_id":"d708ba1c-d7fa-4690-997c-95bd1eca2886","resolution":{"observed_at":"2026-08-11T12:21:12.407755Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T12:21:10.130843Z","title":"& Andersson, H","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.130843Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:71e4f71ebbce65130c6b76b2cda79ec1d99ebfa5e914541a5bf3c7d51f5fa791","observation_id":"5d63e179-cdd5-431f-a560-58a89495577b","resolution":{"observed_at":"2026-08-11T12:21:10.130843Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:12.390802Z","title":"Gurobi Optimizer Reference Manual","venue":null,"work_id":"7aa2a414-f1e9-4966-addb-ac96096b9a08","year":2024},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.134287Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:6f13255a38afe7ba1debb8e27219d3414f8244cdfb142aa348ea1cf46f84676c","observation_id":"56357555-4051-4000-91dd-7e4d6ed10ad6","resolution":{"observed_at":"2026-08-11T12:21:12.394571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T12:21:10.137808Z","title":null,"venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.137808Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:9d121009a8be6b0936032ad5b1267de1e3416310bb6febd916d4276e17dae97e","observation_id":"3f590524-850c-4546-b7b6-4658168b43c3","resolution":{"observed_at":"2026-08-11T12:21:10.137808Z","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":"2026-08-11T12:21:10.141425Z","title":"& Hall, J","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.141425Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:cbf502d05a6849a07c3eecb95e9b1f119e4a751c34f20265ba6a6acf281ea90b","observation_id":"d9bf9e12-9c3c-463f-9fdc-0988d1b5cc1b","resolution":{"observed_at":"2026-08-11T12:21:10.141425Z","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":"2024.0902","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:11.703858Z","title":null,"venue":null,"work_id":"4a3ac895-0fca-428f-ac14-e7e17458ab70","year":2026},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.145547Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:cbd1fc95afc21deea259de8b04c2d5e0bd4a83a24313dde6852073ca7523c24a","observation_id":"afe45258-0785-4efe-b466-a6d8bc21a56c","resolution":{"observed_at":"2026-08-11T12:21:11.710039Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T12:21:10.149180Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.149180Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:26934cb2caa55502240cf683b311e7abcf26faad56b81d46838e64a5dd881744","observation_id":"c6234258-76a5-4c1e-981e-25d1354792f8","resolution":{"observed_at":"2026-08-11T12:21:10.149180Z","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":"2026-08-11T12:21:10.153521Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.153521Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:c0790abd74138a5947e8f5f4d486cfc28be8cd7c48914799cc9bf1c8a6eedc6d","observation_id":"228a5a13-b7b8-4c2d-a019-063cee370daf","resolution":{"observed_at":"2026-08-11T12:21:10.153521Z","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":"2024.10604","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:11.615905Z","title":"S., Ali, M., & Pistikopoulos, E","venue":null,"work_id":"b949cb49-cf6c-4fc3-8f2a-3cc66f6a1e5a","year":2024},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.157646Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:5f0b3dea93e2ab71dfc35e7db40476eb825f220a716abf1b11fab0b4275ca9cf","observation_id":"289ceb68-0aa5-4b29-8889-f27de18af84b","resolution":{"observed_at":"2026-08-11T12:21:11.621697Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2025.10899","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:11.528667Z","title":"H., Kwon, H., & Jeong, H","venue":null,"work_id":"cfd1d4e8-f0fa-49da-9c06-d549b72cf0b0","year":2026},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.161156Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:1962219e16b240b16932acdd426ea4f04cb483e024a22f75973f315d62a19696","observation_id":"660bc13d-d21d-4284-b77e-3c95ba285833","resolution":{"observed_at":"2026-08-11T12:21:11.533823Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-11T12:21:10.165346Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.165346Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:0553d6bbc4faee549d10408a354e48cbeba596e2a151c13f9be072398d5adfbf","observation_id":"8ede5fdc-732b-44b0-b3df-08185e6fadc1","resolution":{"observed_at":"2026-08-11T12:21:10.165346Z","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":"2026-08-11T12:21:10.169779Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.169779Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:f8a98ce5f91283940136a15fa8572daf50660ee163922d79e66f6017651e1487","observation_id":"670cccf8-d3d9-4541-8bc2-d7cb1263e6f0","resolution":{"observed_at":"2026-08-11T12:21:10.169779Z","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":"2025.10924","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:11.435423Z","title":"& Oliveira, F","venue":null,"work_id":"2d3922aa-6ae9-485d-b89b-861ebf0d2efe","year":2025},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.173085Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:20bee3d4e229645e8df805b0c52f49f57b8ae54d51ce769f4f47fa99222dfb5e","observation_id":"a8cdf67d-90a9-4f4d-b7f0-fb68d42cf764","resolution":{"observed_at":"2026-08-11T12:21:11.440548Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.05261","last_updated":"2026-04-23T12:25:21Z","snapshot_observed_at":"2026-08-17T03:02:24.789604Z","submitted_at":"2025-05-08T14:06:38Z","title":"ICNN-enhanced 2SP: Leveraging input convex neural networks for solving two-stage stochastic programming","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.05261","snapshot_observed_at":"2026-08-11T12:21:10.177604Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.177604Z"},"links":{"cited_paper":"/paper/2505.05261","citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:96f00aa5a0f3c69fad384da65a7edb895c136974a2db52f42a0a08a4403f4eef","observation_id":"5b09fe7f-f84a-4984-8fdc-376af5c99b37","resolution":{"observed_at":"2026-08-11T12:21:10.177604Z","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":"2026-08-11T12:21:10.183238Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.183238Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:931555a4a0f6b3efe67d477e19bb879e1e4cc5dbf4319f1926287691cf19d91f","observation_id":"dad25439-34e0-4211-b4a0-bfcdde040dc1","resolution":{"observed_at":"2026-08-11T12:21:10.183238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10962","last_updated":"2020-06-17T19:44:15Z","snapshot_observed_at":"2026-08-17T13:56:00.049386Z","submitted_at":"2019-08-28T21:59:58Z","title":"Optimal transport mapping via input convex neural networks","version":2},"cited_work":{"arxiv_id":"1908.10962","doi":"10.48550/arxiv.1908.10962","metadata_source":"pith","pith_arxiv_id":"1908.10962","snapshot_observed_at":"2026-08-11T18:16:15.004306Z","title":"Optimal transport mapping via input convex neural networks","venue":"cs.LG","work_id":"ef7ce4b8-7813-46c5-9e41-ddd03db39dea","year":2019},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.189574Z"},"links":{"cited_paper":"/paper/1908.10962","citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:4c458b860aff544e5cf987edceacfa6d3f96cbf09266eaae7a430b52d7ff6a2a","observation_id":"8f206673-9a31-48e2-a16a-68cc28545f43","resolution":{"observed_at":"2026-08-11T12:21:10.348849Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:12.379418Z","title":"& Wiberg, H","venue":null,"work_id":"14c37b96-2a11-45fe-aebd-9de679a07b49","year":2021},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.195672Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:9c3aa6cac66800349acb2710f85a3cd23b40167f95bad8de09c67591cbe5817b","observation_id":"bf1f0085-1360-4964-ac4a-184c9d3df96b","resolution":{"observed_at":"2026-08-11T12:21:12.383375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2021.0707","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:11.359048Z","title":"\\.I ., den Hertog, D., & Fajemisin, A","venue":null,"work_id":"c49a7436-4d37-469f-9e11-0e4ecf5afc2a","year":2023},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.199894Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:a4da6c67ed9ca02c7ccccadfc8769d154b4177492233444dce0a563b132d0e9e","observation_id":"1feb568a-58e4-4775-ba73-5e7a1cc7f42c","resolution":{"observed_at":"2026-08-11T12:21:11.364401Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T12:21:10.203675Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.203675Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:153144cc10c711dd6fe99e74ab919953ba5080ed8b0a1026c2717394a3569a17","observation_id":"3b68bde2-d4b7-46ad-bc43-703cf593c1be","resolution":{"observed_at":"2026-08-11T12:21:10.203675Z","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":"2026-08-11T12:21:10.207632Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.207632Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:2380909868b272861c1bc23e5cddbe450f37dcc636832d6b0c410a2269c7cf60","observation_id":"3e3cb203-0a4a-4ef4-90a3-7d7db76f3a97","resolution":{"observed_at":"2026-08-11T12:21:10.207632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.02114","last_updated":"2018-09-16T01:36:41Z","snapshot_observed_at":"2026-08-14T20:16:27.036473Z","submitted_at":"2017-11-06T19:06:12Z","title":"Bounding and Counting Linear Regions of Deep Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.02114","snapshot_observed_at":"2026-08-11T12:21:10.212889Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.212889Z"},"links":{"cited_paper":"/paper/1711.02114","citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:70f35b0758d603b941af88aa1bd3d8695daf1aae248f3ec1d6b9fb042c9c2573","observation_id":"8406928b-6b8a-4632-94dd-932f3aab30f1","resolution":{"observed_at":"2026-08-11T12:21:10.212889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.07356","last_updated":"2019-02-18T04:39:10Z","snapshot_observed_at":"2026-08-17T22:18:35.161858Z","submitted_at":"2017-11-20T15:05:33Z","title":"Evaluating Robustness of Neural Networks with Mixed Integer Programming","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.07356","snapshot_observed_at":"2026-08-11T12:21:10.216567Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.216567Z"},"links":{"cited_paper":"/paper/1711.07356","citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:ee0ec65bfd896af51d0e3e9b43d5f7e2d93fd4df5018aafb0ebe68cc01f998f8","observation_id":"5254f220-4fb7-405e-ba93-20121eacf8f2","resolution":{"observed_at":"2026-08-11T12:21:10.216567Z","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":"2026-08-11T12:21:10.221123Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.221123Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:180c3dc4363e822683fa4b3acb97ad2cb8303311cb2e0552dae4ad3cb1c36605","observation_id":"dc154caf-86d6-40c5-bc52-079282b911d8","resolution":{"observed_at":"2026-08-11T12:21:10.221123Z","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":"2026-08-11T12:21:10.224751Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.224751Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:57cc3ea14278a17b6a740b62e91ef8fdae0a1056fa575772fc5668a627146874","observation_id":"2a01433e-b3e8-4633-b687-edddf4f1e5c9","resolution":{"observed_at":"2026-08-11T12:21:10.224751Z","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":"records/1123114","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:11.062075Z","title":null,"venue":null,"work_id":"a82a2f84-2ec7-46fb-b2ef-de11cbed03fb","year":2024},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.228462Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:5dbd09103501ca0d1f4e384733f6c7740cb6890b73984b76bd89a32a1562efe7","observation_id":"58defa6e-3ee1-44bb-8bae-080f208a5ef9","resolution":{"observed_at":"2026-08-11T12:21:11.067798Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T12:21:10.231989Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.231989Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:735020da0b7e5ca97840697900b62393f429e63dc96e066f998cf45c45057aba","observation_id":"34145bd5-a75e-4da2-bef8-ce3260088617","resolution":{"observed_at":"2026-08-11T12:21:10.231989Z","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":"2023.1285","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:10.916476Z","title":null,"venue":null,"work_id":"81ddf96e-a454-4c22-a868-283bd1085d1a","year":2023},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.235607Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:1ffd40bbde62f8245776a85e48d50b642420ee38c60902e7a6b12de87d2c4fc3","observation_id":"c481a939-8b02-4072-a6a1-6f3857ca3b8e","resolution":{"observed_at":"2026-08-11T12:21:10.921660Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T12:21:10.238915Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.238915Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:56e3f185e2287b618b58010d1f530ad9bc55067286565b99b41a695e057ca034","observation_id":"6fc183ec-fc43-4d91-99c0-980574a7c248","resolution":{"observed_at":"2026-08-11T12:21:10.238915Z","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":"2026-08-11T12:21:10.244557Z","title":"& Wang, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.244557Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:783e5f369697daec978149f8edb3fcc72acab0ba605dd574d14ee232d0a58b1c","observation_id":"0d90c5ea-404f-4d1e-a256-d96920c02744","resolution":{"observed_at":"2026-08-11T12:21:10.244557Z","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":"2020.10714","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:10.770299Z","title":"& Bequette, B","venue":null,"work_id":"a1ce7f38-b06b-41e4-b8ac-689561a85ed0","year":2021},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.247999Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:7b2582219ec136b5c37c2217244fa6df56d64353dc869f581307d3e44f59edc9","observation_id":"a3bef834-9907-42e4-b36b-7081ff430798","resolution":{"observed_at":"2026-08-11T12:21:10.775690Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T12:21:10.251136Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.251136Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:1da820104685303c8bd9678835e822014afd0cb9edd8289a0453d79032720c87","observation_id":"eda421ef-8617-4916-aea4-1d92399dc817","resolution":{"observed_at":"2026-08-11T12:21:10.251136Z","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":"2025.36161","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:10.607067Z","title":null,"venue":null,"work_id":"b8eafc61-6144-4342-9c09-b1cd7d7c4849","year":2025},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.255354Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:c708d96c711fc1ee60d2ca730cf4b9792618d86362c6c25aa320e6c42c825e5f","observation_id":"e6eec090-0f21-4e1a-b376-93d94d13e513","resolution":{"observed_at":"2026-08-11T12:21:10.612497Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.neucom.2022.09.108","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T12:21:10.287548Z","title":null,"venue":null,"work_id":"01bb2345-93f9-49c8-ba79-0136c3706929","year":2022},"citing_paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-11T12:21:10.258752Z"},"links":{"citing_paper":"/paper/2608.09707"},"observation_digest":"sha256:7c48c8a6350b190b91ae49541366e622da8ab82318a6731c22c0f0ab25bfd464","observation_id":"f857a294-5af3-48a8-98c3-00dc515c7dbe","resolution":{"observed_at":"2026-08-11T12:21:10.292818Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.09707","last_updated":"2026-08-10T15:11:22Z","latest_version":1,"primary_category":"math.OC","snapshot_observed_at":"2026-08-15T15:28:28.927255Z","submitted_at":"2026-08-10T15:11:22Z","title":"Input convex neural networks as surrogates in mathematical optimisation"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":6,"parse_uncertain":0,"unresolved":32,"verified_exact":8,"verified_fuzzy":2},"total_outbound_references":48},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2608.09707."}