{"as_of":"2026-08-10T23:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ab88a700876b6cc55f4724afef31e1238f30871c92bc909538e2a7de8bf0b238","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T00:55:09.100966Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2608.00270/citation-record","integrity":"/paper/2608.00270/integrity","json":"/paper/2608.00270/citation-record.json","paper":"/paper/2608.00270"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.07985","last_updated":"2024-01-13T01:32:56Z","snapshot_observed_at":"2026-07-06T16:31:37.625496Z","submitted_at":"2023-10-12T02:18:50Z","title":"Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.07985","snapshot_observed_at":"2026-08-04T00:55:07.250499Z","title":"Neural combinatorial optimization with heavy decoder: Toward large scale generalization.ArXiv, abs/2310.07985, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.250499Z"},"links":{"cited_paper":"/paper/2310.07985","citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:6ea2d61f55ca8218e497737fef79c7cb621c4dd1d28ae0ea1f2a4b2efe6446d1","observation_id":"3b5896b0-8f92-4332-a08d-ef106c0d52f1","resolution":{"observed_at":"2026-08-04T00:55:07.250499Z","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":"2026-08-04T00:55:07.288171Z","title":"Attention, learn to solve routing problems! InInternational Conference on Learning Representations, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.288171Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:d5ba177bc2ad60475314df3913efb2272127235457d456fbaf4ae0a463611df5","observation_id":"4ba9787b-424a-48b6-8d34-35733989e331","resolution":{"observed_at":"2026-08-04T00:55:07.288171Z","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":"2026-08-04T00:55:07.338622Z","title":"RRNCO: Towards real-world routing with neural combinatorial optimization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.338622Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:3a468152e86f104deb5d3b76a984f993e3f51785b3690e25666d7cd11c5e8a0d","observation_id":"0ea47f14-bd67-4d01-8e40-49ee6e2039e3","resolution":{"observed_at":"2026-08-04T00:55:07.338622Z","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":"2026-08-04T00:55:07.370993Z","title":"Toutanova","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.370993Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:b78e4d923113b5cd506cfbdc3ed1334d89f6b457ab3be4f64502fecf328ff2c4","observation_id":"e4927390-34fc-4527-bf7f-9fffc7049f93","resolution":{"observed_at":"2026-08-04T00:55:07.370993Z","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":"2026-08-04T00:55:07.424856Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.424856Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:3d892fae888d3e80788c0e83c0592a92d7e5b6b225f906eb6f63427b7469f534","observation_id":"aa9adc47-be04-42f3-a62d-e4bdb96a1548","resolution":{"observed_at":"2026-08-04T00:55:07.424856Z","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":"2026-08-04T00:55:07.503453Z","title":"Graphmae2: A decoding-enhanced masked self-supervised graph learner","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.503453Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:643506db958a72dca808d07848c1f3e46565486b61c27f3083aae43e6cd4351c","observation_id":"61a95f5e-2734-4a6b-b851-ff433d887daf","resolution":{"observed_at":"2026-08-04T00:55:07.503453Z","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":"2026-08-04T00:55:07.559550Z","title":"Hamilton, Pietro Liò, Yoshua Bengio, and R Devon Hjelm","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.559550Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:5e6f60dcbb2ac3e4a43f1318a1ba065d93f987d478b62629c6ad9e34ae0a4db2","observation_id":"7a97d52b-1b10-4c43-a8ee-28b99a80f5bd","resolution":{"observed_at":"2026-08-04T00:55:07.559550Z","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":"2026-08-04T00:55:07.583618Z","title":"Graph contrastive learning automated","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.583618Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:654697396d4cb4c3249664584458e95fecbeb9e1b1207cc7dbaa280762cb480a","observation_id":"6b139d3c-0718-4cb8-9c7d-1d710bf15a6b","resolution":{"observed_at":"2026-08-04T00:55:07.583618Z","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":"2026-08-04T00:55:07.639706Z","title":"Applegate, Robert E","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.639706Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:d9c0e99655be46afabb8f9dd3478c2cc78b920afa5a1a4ad83fdaaadc2edbf47","observation_id":"38b4add7-e8f9-4b35-bb03-54cb71355245","resolution":{"observed_at":"2026-08-04T00:55:07.639706Z","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":"2026-08-04T00:55:07.728694Z","title":"Morrison, Sheldon H","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.728694Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:a46fae9f0e2f7116fde4bbf4275af708901c51d8f9c41569e9f35f3d2eb3bdbe","observation_id":"40afd504-2bfe-46c5-ad1f-26f82c301614","resolution":{"observed_at":"2026-08-04T00:55:07.728694Z","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":"2026-08-04T00:55:07.779524Z","title":"An extension of the lin-kernighan-helsgaun tsp solver for constrained traveling salesman and vehicle routing problems: Technical report","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.779524Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:4f3a5eac423428d017df5d3a65dc1c56c367bfab93feff7431a523e4c799967f","observation_id":"7ac8f6b8-eba0-4786-b96a-d93d1631347c","resolution":{"observed_at":"2026-08-04T00:55:07.779524Z","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":"2026-08-04T00:55:07.816087Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.816087Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:2241773f45ca6038210ff965306d28c22f02f13f90c8ffe1a557a26c6d5efdb7","observation_id":"9f6e9ffd-3177-449d-99d9-d2badbcc32af","resolution":{"observed_at":"2026-08-04T00:55:07.816087Z","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":"2026-08-04T00:55:07.894620Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:07.894620Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:9a79606dcebc78180308013473a3a3e503bbbd5fd37568655a7a1348d18abb8f","observation_id":"ca9cdffb-bf08-4653-94c9-d515903344fe","resolution":{"observed_at":"2026-08-04T00:55:07.894620Z","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":"2026-08-04T00:55:08.002901Z","title":"Pointer networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.002901Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:51a328811379cfd8e975e99f3da88a6445d23dbbb4d9e546cbc926ed7404713c","observation_id":"24648818-0cea-4112-a54c-62611954d7e5","resolution":{"observed_at":"2026-08-04T00:55:08.002901Z","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":"2026-08-04T00:55:08.033953Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.033953Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:c5f1b630513872b6c54e1bb99d6e435d1a21dfd5f1f03946f6bcabc5c256518c","observation_id":"64a27c47-ffd8-4fcf-a4fd-c237929d2123","resolution":{"observed_at":"2026-08-04T00:55:08.033953Z","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":"2026-08-04T00:55:08.120126Z","title":"Graph attention networks, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.120126Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:c5ff7ac92a3b8119149cbf042136850133304b3bc8adee04f30a6525fc6020c3","observation_id":"6d14cfa4-2f65-4c1b-9568-50825dfc33e3","resolution":{"observed_at":"2026-08-04T00:55:08.120126Z","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":"2026-08-04T00:55:08.175698Z","title":"Gated graph sequence neural networks, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.175698Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:a1cf74938e76f805312e6b5df76edfa8274ff7936a9ff9bbd9d603d008b4d9fb","observation_id":"1b9c011b-bbcc-4b49-a883-6d0fe3be8ae5","resolution":{"observed_at":"2026-08-04T00:55:08.175698Z","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":"2026-08-04T00:55:08.261943Z","title":"Joshi, Quentin Cappart, Louis-Martin Rousseau, and Thomas Laurent","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.261943Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:a7a68a0c3cdd3a31d8e8956b1464dcb7d8bc179b4a6df9e2aa66d086aa908208","observation_id":"b209f87b-1e83-4ef8-9a92-9452b86ed9ab","resolution":{"observed_at":"2026-08-04T00:55:08.261943Z","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":"2026-08-04T00:55:08.318851Z","title":"Graphmae: Self-supervised masked graph autoencoders","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.318851Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:20b8f24589cf2773e5ed7d583e7227a02b8bef0f78f688d8de3a371bfa1d33b3","observation_id":"ca788509-58cf-4a37-8da9-7e4bdf58f12b","resolution":{"observed_at":"2026-08-04T00:55:08.318851Z","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":"2026-08-04T00:55:08.421569Z","title":"Self-supervised graph representation learning via topology transformations","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.421569Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:15efa889c760d8d5a1f174fb2e17339a76925a99d44ec6fe083f65c851686e16","observation_id":"d457d199-e99d-4596-9458-e21eb69e789e","resolution":{"observed_at":"2026-08-04T00:55:08.421569Z","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":"2026-08-04T00:55:08.487419Z","title":"Graph contrastive learning with personalized augmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.487419Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:e50d48c081925f01d0254a7804b4185eb77295a8e095834f0e83bf33925fae0e","observation_id":"a8a83b20-eed2-47b8-96c7-5a925264c970","resolution":{"observed_at":"2026-08-04T00:55:08.487419Z","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":"2026-08-04T00:55:08.535198Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.535198Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:7c195fc4d030aa7cc5551ac45e1b5243b247ff2597e60d3e6c9ed8a10e1e329e","observation_id":"83012cd0-1235-47fd-a34a-1e9c71c95a0b","resolution":{"observed_at":"2026-08-04T00:55:08.535198Z","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":"2026-08-04T00:55:08.626621Z","title":"Multi-scale self- supervised graph contrastive learning with injective node augmentation.IEEE Transactions on Knowledge and Data Engineering, 36(1):261–274, January 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.626621Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:13483450d7e9a21b42489d5976966e63f3f61c6e8025183a0e0b683747b8cb15","observation_id":"034d50b0-f028-459c-832c-54df1f59312e","resolution":{"observed_at":"2026-08-04T00:55:08.626621Z","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":"2026-08-04T00:55:08.685267Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.685267Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:0d41fd02ca28ccc5cce21ffb69fd5d7c7014ea97b80d09de9526619cd7b32a3e","observation_id":"e3e5c3bc-8330-4f9f-a41d-f0efc770d92c","resolution":{"observed_at":"2026-08-04T00:55:08.685267Z","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":"2026-08-04T00:55:08.755986Z","title":"Data augmentation on graphs: A technical survey.ACM Comput","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.755986Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:dbffefadf9fe48152c623ebae9df715b53a9194bf5df25bd8f80de423436113e","observation_id":"9f854bd5-c370-4263-a767-77f854192d26","resolution":{"observed_at":"2026-08-04T00:55:08.755986Z","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":"2026-08-04T00:55:08.797180Z","title":null,"venue":null,"work_id":null,"year":1960},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.797180Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:4ee73d3865cedd0edc0ecf7483057304369f4de5ccbb9b02677cf7a853138825","observation_id":"a303a09a-a203-4e8b-8b96-7babca0a30db","resolution":{"observed_at":"2026-08-04T00:55:08.797180Z","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":"2026-08-04T00:55:08.868815Z","title":"On layer normalization in the transformer architecture","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.868815Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:7103af7e1e879294658c09ce2f2381bc7e5147004c31f67a2406067f5a7e6541","observation_id":"efa1a3ea-47b1-40b3-973a-a2f6ee12bf98","resolution":{"observed_at":"2026-08-04T00:55:08.868815Z","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":"2026-08-04T00:55:08.976557Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.976557Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:9bbee477d0ebabb0301f4eb20286d4cde125a0d4bc2cf7c3167d4f43d5d5ab99","observation_id":"0fae2b79-3db2-4605-99ee-16391a766ee4","resolution":{"observed_at":"2026-08-04T00:55:08.976557Z","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":"2026-08-04T00:55:08.999872Z","title":"Householder","venue":null,"work_id":null,"year":1958},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:08.999872Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:cddb2cb57c28b42d3abbc03079d14f866c953281d51af6fe65c5965d7836ea17","observation_id":"ba39a198-c0f0-41d6-a330-f02af8daa89a","resolution":{"observed_at":"2026-08-04T00:55:08.999872Z","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":"2026-08-04T00:55:09.044303Z","title":"Contrastive difference predictive coding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:09.044303Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:5ddd2c510e3908324fc54cb5a6667cb74f794f4c2d6949f7b3e0408c0de006fb","observation_id":"3af9eeee-3342-4fec-af62-3b3a7a67151c","resolution":{"observed_at":"2026-08-04T00:55:09.044303Z","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":"2026-08-04T00:55:09.052720Z","title":"White and Douglas J","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:09.052720Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:3fb53be43972759ba9a7a787e65b49f4106c769c5a3365c6745d75826c74268e","observation_id":"5e44f48c-1b71-4381-8ce0-10440942b657","resolution":{"observed_at":"2026-08-04T00:55:09.052720Z","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":"2026-08-04T00:55:09.100966Z","title":"Williams","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T00:55:09.100966Z"},"links":{"citing_paper":"/paper/2608.00270"},"observation_digest":"sha256:c528106a3a7aebfa7088870ba162f409e1ae529225a766dbdcaee94012f67989","observation_id":"1a316c8d-efb5-486a-b386-027c5e3b51a2","resolution":{"observed_at":"2026-08-04T00:55:09.100966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.00270","last_updated":"2026-07-31T20:23:21Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-06T23:12:17.950666Z","submitted_at":"2026-07-31T20:23:21Z","title":"Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":32},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2608.00270."}