{"as_of":"2026-08-20T15:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ea4003f93975141724260678e5fd3811a6ec4a79abd7caae5567e51361181696","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T07:00:24.074608Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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":"2026-07-14T00:36:05.289408Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.04485","snapshot_observed_at":"2026-07-14T00:36:05.289408Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.10077","last_updated":"2026-07-11T02:07:53Z","snapshot_observed_at":"2026-08-14T22:58:57.783508Z","submitted_at":"2026-07-11T02:07:53Z","title":"TabLoRA: Parameter-Efficient Low-Rank Ensemble Learning for Large-Scale Tabular Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-14T00:36:05.289408Z"},"links":{"cited_paper":"/paper/2606.04485","citing_paper":"/paper/2607.10077"},"observation_digest":"sha256:fecf95e3d493fd13aec0e528808741e6891962276f2a2308de5ad3c6062ccdc7","observation_id":"9829726b-630c-442f-9867-18341e69d44e","resolution":{"observed_at":"2026-07-14T00:36:05.289408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2606.04485/citation-record","integrity":"/paper/2606.04485/integrity","json":"/paper/2606.04485/citation-record.json","paper":"/paper/2606.04485"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T07:00:24.074608Z","title":"Scaling Learning Algorithms Towards","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:e9be325bd774bc923898485ea2df019dbff18719e95fdc9586a113915087d95d","observation_id":"29747d11-78ab-42dd-b60a-aef6b9080609","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics , pages =","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:65665d64cb74705a47ef4d4cedd9789866ff083b82818a7d18d30c8513f255e3","observation_id":"9893eb70-43f5-445c-87f1-42316a91cf2f","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:54bb8c072edcc9a7566f25babddd82b8dc5e376314705f35df0d71eb4b3f4a47","observation_id":"526a075c-d7b0-4b97-8271-47eae6317dac","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"and Osindero, Simon and Teh, Yee Whye , journal =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:e51da7057f2aa31e8fa946bd6017a53989d2aeb233f20ad7f574f0a9a6988cbc","observation_id":"00ddbe27-d5cb-4665-b79f-f0062819057b","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"2016 , publisher=","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:9456f22fa5baf1c8366d8537ff8cfa98bc74c52815dac46d554d0acabe6b6404","observation_id":"324608df-75d4-4676-b7db-3f32b116244a","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Nature , volume =","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:1e9ca4b2362948172510757480c6caed3ae7fa95138478b919aa7a9347d8db4a","observation_id":"526a76f7-8aad-4475-83fa-3fac2d09ee1d","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.01848","last_updated":"2023-09-16T09:33:32Z","snapshot_observed_at":"2026-08-16T22:29:42.020081Z","submitted_at":"2022-07-05T07:17:43Z","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","version":6},"cited_work":{"arxiv_id":"2207.01848","doi":"10.48550/arxiv.2207.01848","metadata_source":"pith","pith_arxiv_id":"2207.01848","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","venue":"cs.LG","work_id":"2b2cf99d-d6e4-4a96-9e61-f783356a2581","year":2022},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"cited_paper":"/paper/2207.01848","citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:bd14d2a464487872303f03f072003bf94d853eec85c9ec6e9f2649c2c272dfa9","observation_id":"c6999a53-dfb4-48d8-b02b-b4fe537a5650","resolution":{"observed_at":"2026-07-02T07:16:45.166866Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-28T07:00:24.074608Z","title":"Proceedings of the 42nd International Conference on Machine Learning (ICML) , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:22b300a3184a3483f7fcd1f9d9728c33eddeccbd30cf0c8a706c285f6b57cb34","observation_id":"b533bb8c-6763-4aef-b9cd-2aa0f4925e26","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"2016 , doi =","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:4f59694cbb0308af3a723663c462c34ba50153adf29eef5b9ebd2b35b5dd64a5","observation_id":"65c55225-5e19-4b0c-9c5b-f0ee03c5a301","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Advances in Neural Information Processing Systems 30 (NeurIPS) , pages =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:007fe46d8d76dde1b87735f7c248d78c9b09382cf146f2a39714055ebf06b7b3","observation_id":"e00c8f44-ae83-45ac-ada7-eba9920027f0","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Advances in neural information processing systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:ab10f9b5ba85bbe6115e57bc498894d1d712f333e9faa6ca369b8a3b5abcd089","observation_id":"6bb993a8-aa6e-411d-9d0a-d50ca89b6a5d","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.08815","last_updated":"2022-07-18T08:36:08Z","snapshot_observed_at":"2026-08-16T16:45:15.654938Z","submitted_at":"2022-07-18T08:36:08Z","title":"Why do tree-based models still outperform deep learning on tabular data?","version":1},"cited_work":{"arxiv_id":"2207.08815","doi":"10.48550/arxiv.2207.08815","metadata_source":"pith","pith_arxiv_id":"2207.08815","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi:10.48550/arXiv.2207.08815 , urldate =","venue":"cs.LG","work_id":"5571d287-82fd-45cd-a991-34c7a4f4a3ea","year":2022},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"cited_paper":"/paper/2207.08815","citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:64a9aad286ecf123796ef02327ee10c97e5f18283696b72c7c05ea33fac72bd6","observation_id":"e20cc773-ad62-4442-996d-00a9aa8bee89","resolution":{"observed_at":"2026-07-02T07:16:45.153013Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-06-02T00:57:13.693847+00:00","source":"crossref_status_cache"},{"observed_at":"2026-06-02T00:57:13.693847+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.06678","last_updated":"2020-12-11T23:31:23Z","snapshot_observed_at":"2026-08-14T12:45:55.154777Z","submitted_at":"2020-12-11T23:31:23Z","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","version":1},"cited_work":{"arxiv_id":"2012.06678","doi":"10.48550/arxiv.2012.06","metadata_source":"pith","pith_arxiv_id":"2012.06678","snapshot_observed_at":"2026-07-10T17:07:25.686746Z","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","venue":"cs.LG","work_id":"22746e9d-0ec8-4c75-8591-5655c9ec57e1","year":2020},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"cited_paper":"/paper/2012.06678","citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:185305daf73b82c15395adcef550d6e78537c4976638f8e1b9ab72ebd817feb7","observation_id":"517ed565-4884-4b80-a8df-83f67b11fa0c","resolution":{"observed_at":"2026-07-02T07:16:45.156148Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-05-24T02:53:07.527821+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T02:53:07.527821+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-28T07:00:24.074608Z","title":"Advances in Neural Information Processing Systems 34 (NeurIPS) , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:0d473ec26fc2d3f344a816bcd38ba5f13a645f5781d5a89e432cdb8397124190","observation_id":"ff1732b0-f965-44ca-8986-5e8781053a14","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Advances in Neural Information Processing Systems 35 (NeurIPS) , pages =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:10b7f1071c1a7661490a0d3c9b5732aef2216848bd6e990f66451c35c1ca73b8","observation_id":"5be998e2-f76f-42da-a5d8-6c66e9b7f547","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Complex Systems , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:72b9aa7c756235ca67619c3ccf7e7836e42baaf5ffdf26d0b1d44524d076c0eb","observation_id":"d8e9ada6-9198-4f01-97c5-2a627bcc1418","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Neural Computation , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:04e964e2b892acf969d982f451bdb003c2999c403468d81151b6f081a78a41b4","observation_id":"95055eb8-fa72-421a-88f2-68f9f4e2dbfc","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"2018 , publisher=","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:549ba87f09a04082b48b3a2c4e757d3ecdd41f94b408d26be4d328a1e44479c5","observation_id":"614eb770-eb9d-4573-9eda-29f995dccac5","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"2006 , publisher =","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:9a5370dc754304f7928b4277dde49ee7297738eac9032760a74b22e88b9d13a6","observation_id":"b8746fdb-69f7-463d-9979-3c25444c769f","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Advances in Neural Information Processing Systems 20 (NeurIPS) , pages =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:cb256e7be9c3bbccfc2b74fc11c594425a0db5304fffe2b972ac926368b83ccd","observation_id":"f0d3d9ef-298e-4608-a132-1d14c2e4e8cb","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:74260b539ee66b83de814685d66700be7ca30c1a1988a6ff4f02d7f5cf7135a0","observation_id":"7878d60c-4124-48d5-b06b-e2075d339414","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.08564","last_updated":"2022-06-17T05:51:10Z","snapshot_observed_at":"2026-08-16T16:52:21.082758Z","submitted_at":"2022-06-17T05:51:10Z","title":"MET: Masked Encoding for Tabular Data","version":1},"cited_work":{"arxiv_id":"2206.08564","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.08564","snapshot_observed_at":"2026-07-02T07:16:45.157735Z","title":"arXiv preprint arXiv:2206.08564 , year =","venue":null,"work_id":"7b835895-b4b6-4eea-86f0-be76a806cab7","year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"cited_paper":"/paper/2206.08564","citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:3f5cefec22def380483ab89b281d576ca1a1b9587b3922368914e2c9735103e4","observation_id":"70418ba7-dfff-43f2-a789-4dfe1f5738ff","resolution":{"observed_at":"2026-07-02T07:16:45.159892Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-28T07:00:24.074608Z","title":"Advances in Neural Information Processing Systems 33 (NeurIPS) , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:c1876a2ba87e511df96b6d52bfb100f54e69277f76c4b0ec44fb7aa1b99e4296","observation_id":"d2626001-2939-43e6-90de-92194bcebf28","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2509.03505","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T16:09:57.528730Z","title":"Limix: Unleashing structured- data modeling capability for generalist intelligence","venue":null,"work_id":"455825ae-5eb8-4532-a189-0149028dd50b","year":2025},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:84ccfb5ddcfb8d6e97e289e52686eef863f1ffe7e18c6288c82cae8910a411e4","observation_id":"3b5797a0-2e26-4017-89c4-e70062bd0d4d","resolution":{"observed_at":"2026-07-02T07:16:45.135757Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-28T07:00:24.074608Z","title":"Bayan and Goldstein, Tom , journal=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:f2a16554669b9fa0a43d4f9201c252693205f9cc9169c56b58ead125eaee7791","observation_id":"3eb2166d-81e1-467c-891f-a6a3062aaf08","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Proceedings of the AAAI Conference on Artificial Intelligence , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:eea2a6260d41bc9222229dbffce8ba2e87d86601c09d9d31ecf181ed6cefe3b1","observation_id":"afa1bb8f-184c-41ad-991f-652b8193b164","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"2019 , eprint=","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:52da726630dc52916da292f30a5a6ad80b30d8b54fc42ce31d98fe75a9994aac","observation_id":"40d2e5f6-66d3-4414-aaa6-b9f741300303","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"Advances in neural information processing systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:6f2ec5ce808725a35b43e535dd00d12c4039c69a5bbfcec5b8c9d1114ce853b5","observation_id":"6ac848e0-0b66-4854-89f7-13789d1650d1","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"2026 , eprint=","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:6f6dd5e63c35e2ff80f630baaf724da0f82e5aad1c2df08e16be4be01d8ad8ee","observation_id":"b04a2056-488e-4f4c-8f09-79eca14edc49","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","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":"2026-06-28T07:00:24.074608Z","title":"arXiv e-prints , pages=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:2ea0c1da7e19d711808d55703f83262c91e6859b50d52f17207429dc80885da5","observation_id":"78a99176-4826-46b7-b457-d389527eed0e","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.03731","last_updated":"2021-11-22T13:58:04Z","snapshot_observed_at":"2026-08-15T16:15:34.381928Z","submitted_at":"2017-08-11T23:28:48Z","title":"OpenML Benchmarking Suites","version":3},"cited_work":{"arxiv_id":"1708.03731","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1708.03731","snapshot_observed_at":"2026-07-02T07:16:45.137211Z","title":"Bischl, G","venue":null,"work_id":"1d61b369-5d02-4c53-bc32-a511fbbb24ec","year":2019},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"cited_paper":"/paper/1708.03731","citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:8ee9e4871308813725dcba1558b0a670d74316b42d0f6a658aada0f897e14728","observation_id":"388c6986-2ae6-4a97-9b3c-1241e8fe9476","resolution":{"observed_at":"2026-07-02T07:16:45.138956Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-28T07:00:24.074608Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:03b24c4415f15b65a3119388ff8dbfcc4c7b728ab4ed8e65d1ef3f12f3948133","observation_id":"e11f4e01-455d-45d7-9cb5-82215a327f97","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.16791","last_updated":"2025-11-03T18:47:03Z","snapshot_observed_at":"2026-08-15T22:17:49.239798Z","submitted_at":"2025-06-20T07:14:48Z","title":"TabArena: A Living Benchmark for Machine Learning on Tabular Data","version":4},"cited_work":{"arxiv_id":"2506.16791","doi":"10.15585/mmwr.mm6643a2","metadata_source":"pith","pith_arxiv_id":"2506.16791","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"TabArena: A Living Benchmark for Machine Learning on Tabular Data","venue":"cs.LG","work_id":"155b5349-dee8-4870-965c-d54a700a19de","year":2025},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"cited_paper":"/paper/2506.16791","citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:8c1c1519af66c67c86b681ca08fa1bf87ffa4cd779ca89fb59cfe3f27f082f13","observation_id":"3ae0c36f-2b83-4289-9243-bcc12513bb96","resolution":{"observed_at":"2026-07-02T07:16:45.144519Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-28T07:00:24.074608Z","title":"AutoML Conference 2023 (Workshop) , year=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-06-28T07:00:24.074608Z"},"links":{"citing_paper":"/paper/2606.04485"},"observation_digest":"sha256:20ecbe96980386e538d21e0605be0f87e10243864e3824e9af3514dadeaa1c89","observation_id":"11fb1301-b5e0-4dfa-a2bb-3637430f8034","resolution":{"observed_at":"2026-06-28T07:00:24.074608Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.04485","last_updated":"2026-06-04T07:27:03Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T22:43:19.005451Z","submitted_at":"2026-06-03T06:07:33Z","title":"LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":5,"parse_uncertain":0,"unresolved":27,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":34},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 1 inbound Pith citation observation for arXiv:2606.04485."}