{"as_of":"2026-08-09T16:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1cf2615f3a906d937b88950418ad5471d891e4f689a4606a1cac96b574fc22f0","coverage":[{"denominator":13,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":13,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T04:26:41.700916Z","state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:19:59.550570Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T19:20:00.490221Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"cited_work":{"arxiv_id":"2502.03608","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.03608","snapshot_observed_at":"2026-08-06T19:20:00.490221Z","title":"(GG) MoE vs. MLP on Tabular Data","venue":"cs.LG","work_id":"942bb5f2-8ea6-4734-8de8-0977b283abf8","year":2025},"citing_paper":{"arxiv_id":"2507.05904","last_updated":"2025-07-08T11:45:29Z","snapshot_observed_at":"2026-08-07T03:04:42.147701Z","submitted_at":"2025-07-08T11:45:29Z","title":"Universal Embeddings of Tabular Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T19:19:59.550570Z"},"links":{"cited_paper":"/paper/2502.03608","citing_paper":"/paper/2507.05904"},"observation_digest":"sha256:2454c2e75bf5c4666f5b192936eb4db400f39599839cb1375079617a84f42e83","observation_id":"b7972f63-07a1-41ba-b5c9-0b46bd4b8db2","resolution":{"observed_at":"2026-08-06T19:20:00.494231Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.03608/citation-record","integrity":"/paper/2502.03608/integrity","json":"/paper/2502.03608/citation-record.json","paper":"/paper/2502.03608"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.24210","last_updated":"2025-02-18T18:58:14Z","snapshot_observed_at":"2026-07-06T19:43:05.453551Z","submitted_at":"2024-10-31T17:58:41Z","title":"TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.24210","snapshot_observed_at":"2026-08-09T04:26:41.668617Z","title":"Tabm: Advancing tabular deep learning with parameter-efficient ensembling","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.668617Z"},"links":{"cited_paper":"/paper/2410.24210","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:6ba179f1f10d733f9a8ffb6f6a0da940c7847c8daead6777cc2e6330264b724e","observation_id":"c42a26c8-8f35-42c8-886b-6cf2402339d9","resolution":{"observed_at":"2026-08-09T04:26:41.668617Z","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":"2026-08-09T04:26:41.818971Z","title":null,"venue":null,"work_id":"17cf2ca6-36c4-4621-b393-8ccf9341c353","year":1979},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.700916Z"},"links":{"citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:0a07ad9eba3ae1f9ca02bd2a07ee39077c9642e8d2f5cd3c5ff182e58ff57a25","observation_id":"ed8d76e4-0d54-4b70-a42e-349aa54f0f42","resolution":{"observed_at":"2026-08-09T04:26:41.821944Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1701.06538","last_updated":"2017-01-23T18:10:00Z","snapshot_observed_at":"2026-07-06T05:27:13.416519Z","submitted_at":"2017-01-23T18:10:00Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.06538","snapshot_observed_at":"2026-08-09T04:26:41.691547Z","title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.691547Z"},"links":{"cited_paper":"/paper/1701.06538","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:51c5b5c95303896034a120e25a614d85b110d6e458e23fb74da841ffc8dc9241","observation_id":"ffd54ced-cfe1-489c-8b3b-29403680437e","resolution":{"observed_at":"2026-08-09T04:26:41.691547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.01342","last_updated":"2021-06-02T17:51:05Z","snapshot_observed_at":"2026-08-05T11:00:48.512556Z","submitted_at":"2021-06-02T17:51:05Z","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.01342","snapshot_observed_at":"2026-08-09T04:26:41.694395Z","title":"B., and Goldstein, T","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.694395Z"},"links":{"cited_paper":"/paper/2106.01342","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:e6be0687dca4824ba38f4b1ac9651547bf9cd9ccc3b7e1064156a826f934dc4c","observation_id":"0ed0bb05-a327-4f09-a488-55ea5057aae9","resolution":{"observed_at":"2026-08-09T04:26:41.694395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06715","last_updated":"2020-02-20T03:38:44Z","snapshot_observed_at":"2026-08-01T10:08:45.076962Z","submitted_at":"2020-02-17T00:00:59Z","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06715","snapshot_observed_at":"2026-08-09T04:26:41.697620Z","title":"Batchensemble: an alterna- tive approach to efficient ensemble and lifelong learning","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.697620Z"},"links":{"cited_paper":"/paper/2002.06715","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:74b3d066858df4f453106ee15998101501485e15efd1cdc81b0d2dc1f92d88b7","observation_id":"f3237f8f-7636-4f1f-858d-d8115f9316d7","resolution":{"observed_at":"2026-08-09T04:26:41.697620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.06678","last_updated":"2020-12-11T23:31:23Z","snapshot_observed_at":"2026-07-06T10:23:43.246202Z","submitted_at":"2020-12-11T23:31:23Z","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.06678","snapshot_observed_at":"2026-08-09T04:26:41.675514Z","title":"Tab- transformer: Tabular data modeling using contextual em- beddings","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":1991,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.675514Z"},"links":{"cited_paper":"/paper/2012.06678","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:55b11568b2c47feacf43f5aa9a775a91597efc4d3915ecbad18ac6cb580b5376","observation_id":"832748ed-dbb5-4190-9185-3dafe291effc","resolution":{"observed_at":"2026-08-09T04:26:41.675514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.05506","last_updated":"2023-03-09T18:57:13Z","snapshot_observed_at":"2026-07-06T15:00:58.804337Z","submitted_at":"2023-03-09T18:57:13Z","title":"TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization","version":1},"cited_work":{"arxiv_id":"2303.05506","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.05506","snapshot_observed_at":"2026-08-09T04:26:41.763687Z","title":"TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization","venue":"cs.LG","work_id":"17258bff-30c9-4b80-9460-79ec09ff41d8","year":2023},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.682331Z"},"links":{"cited_paper":"/paper/2303.05506","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:9b6a1f4343fa0c4bea79872442a1d56d883813c7b89e2d0f576ddeb38093aa4e","observation_id":"d23e68bc-3257-4795-b656-6fae4a4b32d9","resolution":{"observed_at":"2026-08-09T04:26:41.769208Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-09T04:26:41.685480Z","title":"Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.685480Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:4e2a2f05ecef55b3f3e1dba5ae5388c69a19402cf0ef40ea5eff7cd2a72e71b3","observation_id":"dfd34694-d491-4fe7-b6f9-8eba664e303f","resolution":{"observed_at":"2026-08-09T04:26:41.685480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.00951","last_updated":"2024-05-27T11:44:51Z","snapshot_observed_at":"2026-08-09T15:30:21.645746Z","submitted_at":"2023-08-02T05:20:55Z","title":"From Sparse to Soft Mixtures of Experts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.00951","snapshot_observed_at":"2026-08-09T04:26:41.688700Z","title":"From sparse to soft mixtures of experts","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.688700Z"},"links":{"cited_paper":"/paper/2308.00951","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:c6c4f6507c996543a16961ed3b1ddd436ad29c03895dc5975712601c95dd9601","observation_id":"89f4c747-4b63-4fa8-8b5c-dd63fc5ed48f","resolution":{"observed_at":"2026-08-09T04:26:41.688700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.15147","last_updated":"2022-03-15T22:16:20Z","snapshot_observed_at":"2026-08-08T01:49:28.951153Z","submitted_at":"2021-06-29T08:08:33Z","title":"SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.15147","snapshot_observed_at":"2026-08-09T04:26:41.661175Z","title":"Scarf: Self- supervised contrastive learning using random feature cor- ruption","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.661175Z"},"links":{"cited_paper":"/paper/2106.15147","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:9c98cdb384dd9f92a5b424ddfdeb3ec95d629c31fbcd4f256c3037a1c9d6bd40","observation_id":"46c6207b-cccb-4966-a863-414a2421f800","resolution":{"observed_at":"2026-08-09T04:26:41.661175Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01144","last_updated":"2017-08-05T22:45:19Z","snapshot_observed_at":"2026-08-01T18:34:23.156273Z","submitted_at":"2016-11-03T19:48:08Z","title":"Categorical Reparameterization with Gumbel-Softmax","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01144","snapshot_observed_at":"2026-08-09T04:26:41.678984Z","title":"Categorical repa- rameterization with gumbel-softmax","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.678984Z"},"links":{"cited_paper":"/paper/1611.01144","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:44932806b3ef0e442986802ba7287652f418edba2f8227b4bb821d1ccad92ed7","observation_id":"cda1fc54-d834-4cfd-9e49-28645459fa3b","resolution":{"observed_at":"2026-08-09T04:26:41.678984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04491","last_updated":"2025-01-15T16:02:08Z","snapshot_observed_at":"2026-08-09T12:46:51.564233Z","submitted_at":"2024-07-05T13:29:30Z","title":"Better by Default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04491","snapshot_observed_at":"2026-08-09T04:26:41.672006Z","title":"Better by default: Strong pre-tuned mlps and boosted trees on tabular data","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.672006Z"},"links":{"cited_paper":"/paper/2407.04491","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:a32985dabdeab231f0479c00455bac64f643b11d50cbac61c73375ff18759f7c","observation_id":"336d67be-f157-4280-9dd3-2ab0c99b997b","resolution":{"observed_at":"2026-08-09T04:26:41.672006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.01667","last_updated":"2022-09-04T18:00:29Z","snapshot_observed_at":"2026-08-04T15:45:56.618823Z","submitted_at":"2022-09-04T18:00:29Z","title":"A Review of Sparse Expert Models in Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.01667","snapshot_observed_at":"2026-08-09T04:26:41.665208Z","title":"A review of sparse expert models in deep learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-09T04:26:41.665208Z"},"links":{"cited_paper":"/paper/2209.01667","citing_paper":"/paper/2502.03608"},"observation_digest":"sha256:69380b51bca71d7fd780ceaec359c4214b4f740a2fe23ff1fde75414d5775bbc","observation_id":"b684e82b-4a9c-4bc9-afad-96d4871aec55","resolution":{"observed_at":"2026-08-09T04:26:41.665208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.03608","last_updated":"2025-02-05T20:53:16Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T04:19:12.610416Z","submitted_at":"2025-02-05T20:53:16Z","title":"(GG) MoE vs. MLP on Tabular Data"},"reference_resolution":{"displayed":13,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":13},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 1 inbound Pith citation observation for arXiv:2502.03608."}