{"as_of":"2026-08-07T09:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7102e8f295e9d9953df340305506c49a76a683d9466e752f218b9839e8dea10a","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T07:37:38.063200Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T08:36:02.132826Z","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":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.04320","snapshot_observed_at":"2026-07-11T11:47:14.742492Z","title":"OpenRFM: Dissecting relational in-context learning.arXiv preprint arXiv:2606.04320,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.05476","last_updated":"2026-07-23T10:34:48Z","snapshot_observed_at":"2026-08-07T00:38:37.652270Z","submitted_at":"2026-07-06T10:25:54Z","title":"Parameter-Free Encoders Remain Viable for RDB Foundation Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-11T11:47:14.742492Z"},"links":{"cited_paper":"/paper/2606.04320","citing_paper":"/paper/2607.05476"},"observation_digest":"sha256:57f326a0ba77f3cddd6e35c07708660a1ec046306ffbb34e4f8e78589df2b1e2","observation_id":"6fbc9b01-ada8-4335-9bec-abf828d36e2f","resolution":{"observed_at":"2026-07-11T11:47:14.742492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.04320","snapshot_observed_at":"2026-08-02T08:36:02.132826Z","title":"OpenRFM: Dissecting relational in-context learning.arXiv preprint arXiv:2606.04320,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.05476","last_updated":"2026-07-23T10:34:48Z","snapshot_observed_at":"2026-08-07T00:38:37.652270Z","submitted_at":"2026-07-06T10:25:54Z","title":"Parameter-Free Encoders Remain Viable for RDB Foundation Models","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T08:36:02.132826Z"},"links":{"cited_paper":"/paper/2606.04320","citing_paper":"/paper/2607.05476"},"observation_digest":"sha256:a031474548776ca0420fdb494554e37726fccd4ba5577b5e1495be65b958134e","observation_id":"b74cd081-e5b7-48f5-a7dc-c75c0320a1d1","resolution":{"observed_at":"2026-08-02T08:36:02.132826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2606.04320/citation-record","integrity":"/paper/2606.04320/integrity","json":"/paper/2606.04320/citation-record.json","paper":"/paper/2606.04320"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T07:37:38.063200Z","title":"What learning algorithm is in-context learning? Investigations with linear models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:8be961bf92f8ef54b159b3259238202e574c572c2943ad524b176e873af0bcda","observation_id":"45b8f57d-9a68-44d8-8bca-c74e3abb698f","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Holographic node representations: Pre-training task-agnostic node embeddings","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:f4516e226223cf92202cdb25331838b0beec58ec4251050f5d138eb289b0bf5e","observation_id":"b13f18c1-4e26-4320-8ca8-b320422216a2","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Data distributional proper- ties drive emergent in-context learning in transformers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:3a0425755500443d14297c8de60333061d683262bf64d6a63ba1c82c5669860c","observation_id":"beca206b-0d37-40f0-8208-8f0cf41f77bc","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:0909502e94e3f67f83844ecc0bf6ebebaff47033586cefc846cc72620caf5246","observation_id":"ba165099-d695-43cf-9997-9de85913e992","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"RelGNN: Composite message passing for relational deep learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:e359120ee358f2396363f087c1285bf5d0d44b75848ec2f0196a60b1408e141e","observation_id":"0920b8bb-fdbc-456b-ac10-d4f4c09bbb67","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"9672.293978","doi":"10.1145/2939672.293978","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Chen and C","venue":null,"work_id":"1c2af073-b162-4cd0-a5cd-d8aade23b9b5","year":2016},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:636e29342589b9c98d7166c1c3e7f6b4b6c643b3797096d678554eb8b92fd692","observation_id":"d985fe98-aa56-4abf-bcfa-1702ba97e22d","resolution":{"observed_at":"2026-06-28T07:41:45.394765Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"AutoG: Towards automatic graph construction from tabular data","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:eb7aad392b068b52e71949368f255a96f6c91bb1d033ad151949f13d047b41f6","observation_id":"5de70ff5-aa43-4bd5-af0f-26acb1e199d8","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Re- latron: Automating relational machine learning over relational databases","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:ac904eae31d5fb7d99d14d14d61aed8d91487db4397f8a1d176a5b64d0237e20","observation_id":"fc8b7ab2-787f-4832-8fc3-624642dd98b0","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"On lazy training in differentiable program- ming","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:d20c9232efc307469bd3a7e6ee88800b6efc8371a8b6390ce262770e1b2b7930","observation_id":"9420a7f4-70cf-4c05-a9f1-803f08205300","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"RDB2G-Bench: A comprehensive benchmark for automatic graph modeling of relational databases","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:b7d2049c4e847b7a83761928ed76eb60dd77010751ced196b94f186bac2037bb","observation_id":"deac794b-7cc7-4f63-9f53-57d9309ac686","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Learning posterior predictive distributions for node classification from synthetic graph priors","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:6409d9930a6c2f57815fe39c8de7b8914a470ca4b7a2a1de3015361b096d317c","observation_id":"0573ff7c-06bc-4816-87fc-f6252d018c04","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2384.362685","doi":"10.1145/362384.362685","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Codd , title =","venue":"Communications of the ACM","work_id":"79330988-5031-4ccc-92f1-3378eadf8876","year":1970},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:fc133de6169ddcb2cb9b1878d66051a6e549114a66c3e6841165e75f8a2f32f0","observation_id":"3ab57ecc-0c06-4ccd-86fa-db9075956acd","resolution":{"observed_at":"2026-06-28T07:41:45.389889Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-07-15T00:22:26.521681+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T00:22:26.521681+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"Kanatsoulis, Rishi Puri, Matthias Fey, and Jure Leskovec","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:e3315cf1e8f0c198a38779d88c0b02d32ce9face2f4f4d19c291c247dbe9fe68","observation_id":"99af0941-f30e-4a1c-b967-e5497431c6a1","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.20906","last_updated":"2026-06-22T12:08:08Z","snapshot_observed_at":"2026-08-05T14:47:53.287879Z","submitted_at":"2025-08-28T15:36:37Z","title":"Turning Tabular Foundation Models into Graph Foundation Models","version":3},"cited_work":{"arxiv_id":"2508.20906","doi":null,"metadata_source":"pith","pith_arxiv_id":"2508.20906","snapshot_observed_at":"2026-07-04T16:09:57.521091Z","title":"Turning tabular foundation models into graph foundation models","venue":"cs.LG","work_id":"1a992280-8a3f-4d77-8f13-b9edd08bc7e1","year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"cited_paper":"/paper/2508.20906","citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:b9518505757c569974591d40ebc64297797bb5bdfd16d7d8f8b8598cc75a34b3","observation_id":"08ae370d-40cd-4ddc-b04a-71a7209755d8","resolution":{"observed_at":"2026-07-02T06:06:41.431805Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"GraphPFN: A prior-data fitted graph foundation model","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:232b98eea6d8415ec2f9c2366e7ded24ff56bbfe04beb68e48aa27c919722206","observation_id":"6f0eb500-a235-4d7f-a4df-ce7f1ba74f78","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Position: Relational deep learning – graph representation learning on relational databases","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:dcbb783043361f34872d69d688711d513f92372f072611c4f2d0a1bda31e9632","observation_id":"90de1ce2-4426-40a7-a69f-314e6a99a247","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"KumoRFM: A foundation model for in-context learning on relational data","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:195f855f0ec4da277689960c57eb5a996133455c4108c990d40ccacf57ffa444","observation_id":"78183775-48d9-45d2-8133-991b0784632f","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Towards foun- dation models for knowledge graph reasoning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:41c7e39defcc134954787dadc395c664718ab6ae15bd07264d7fb1e7192ce99e","observation_id":"31db0d47-b8b6-4d4c-b065-8a8dabe39428","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"RelBench v2: A large-scale benchmark and repository for relational data","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:f59a73d3cbd144af7284be890018e5515e61806d9e9e3e80c48d1c7c53b2b6af","observation_id":"9c0e7b50-3bc4-4488-ad3b-7d11d3566d63","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Understanding emergent in-context learning from a kernel regression perspective.Transactions on Machine Learning Research (TMLR), 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:fda8cc3c3c6b6a041535c7f37ab9cfb0e619389de547ff529a1ed1a1e6307837","observation_id":"9f0c8ce6-303c-436f-a2ef-16da23fb2ccd","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Understanding in-context learning via supportive pretraining data","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:bd02cd43316b5ef443197dadd2ab207358d694296fb8ab3f5137ab91caf0be31","observation_id":"84574cb0-79c7-4d59-90fb-780d2d5d3e05","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/0378-8733(83)90021-7","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Holland, Kathryn Blackmond Laskey, and Samuel Leinhardt","venue":"Social Networks","work_id":"66cddcd8-0886-4a62-8430-75923a317831","year":1983},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:0ba9289e40ba137c308d76b845078b187a506bd2cc1110fcce0277b97706991b","observation_id":"26e862e1-a5fa-4469-a506-292033155af6","resolution":{"observed_at":"2026-06-28T07:41:45.402706Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-05-21T11:23:33.428513+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T11:23:33.428513+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/s41586-024-08328-6","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T09:06:59.042414Z","title":"Accurate predictions on small data with a tab- ular foundation model.Nature, 637(8045):319–326","venue":"Nature","work_id":"c5016413-593c-4315-8d0d-78dbbc39ac49","year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:48078118701c45bedf94276f4be96a06c0918408bb1a2c28934fffb640439d84","observation_id":"269d310f-707d-4f29-855f-855d562145b3","resolution":{"observed_at":"2026-06-28T07:41:45.400855Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-07-11T17:19:31.723094+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T17:19:31.723094+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"KumoRFM-2: Scaling foundation models for relational learning","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:a0a808e0a6e7986c36f732ef6ee754fb0f391ace3a70921a1b7739bc624e55f0","observation_id":"21530731-5102-4497-946b-f223aecd28a9","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"IEEE-CIS fraud de- tection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:5b85ed2c4c6140fcec1ca747c99df3540e4c0d393350eef3e86113d49f19959d","observation_id":"ea6f0f78-0432-419a-b497-ce3516f64028","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Neural tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:ba8e47edb22c57dc55d13e8058508d9b80952c573a898e38f819a6706de46b03","observation_id":"d408a95a-86e5-4fbd-bb0a-120cf0bca6da","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"5531.655828","doi":"10.5555/645531.655828","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Linkage and autocorrelation cause feature selection bias in relational learning","venue":null,"work_id":"f17e0020-2fb0-43ec-aced-1c423d3523bb","year":2002},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:1a23d18dea1b37a0febb35b0ab0640f22e53ba38d47c0c7559f7b9b35810384d","observation_id":"fc2efb15-1bf5-4a18-a71d-b6709affe089","resolution":{"observed_at":"2026-06-28T07:41:45.386842Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/sdata.2016.35","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"MIMIC-III, a freely accessible critical care database","venue":"Scientific Data","work_id":"673c213a-7352-4186-9d68-0046d5e2ec44","year":2016},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:cc93edda9aafac81718fea0a1afbc77d7d0c5aeb6879cd1822a6aeac17b369d9","observation_id":"9dd577f3-4fb8-4669-833a-13d699d318a0","resolution":{"observed_at":"2026-06-28T07:41:45.394723Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-05-21T23:23:22.001467+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T23:23:22.001467+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2015.734485","doi":"10.1109/dsaa.2015.7344858","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Deep feature synthesis: Towards automating data science endeavors","venue":null,"work_id":"7e86e54d-5e47-4fe8-93c9-2fffd161ad14","year":2015},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:0ada58fbdde0cf7482d23c247122e4020be9a147743d2b049216b37dd6521b99","observation_id":"dd672585-2f12-44c2-9b9a-1b3c977472fb","resolution":{"observed_at":"2026-06-28T07:41:45.376837Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1103/physreve.83.016107","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Newman, M","venue":"Physical Review E","work_id":"64579b26-873a-47eb-b975-6bf2a006f9aa","year":2011},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:35d6f0a84dcc919e9a18fbe50759bea9ec43f5179b24328f7e59c65e9180601f","observation_id":"d2f79195-690f-46cc-9e10-db728a46fc3a","resolution":{"observed_at":"2026-06-28T07:41:45.398600Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-07-11T06:18:55.271089+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T06:18:55.271089+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"Lightgbm: A highly efficient gradient boosting decision tree","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:8c77f0f126797dc01c54776a9ae43784add29173060f4d143f10ea08b1389fad","observation_id":"364b767c-726c-4892-8704-7ca160f5f5c3","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.09572","last_updated":"2026-07-24T09:08:00Z","snapshot_observed_at":"2026-08-06T11:11:07.339847Z","submitted_at":"2026-02-10T09:22:17Z","title":"Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databases","version":3},"cited_work":{"arxiv_id":"2602.09572","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2602.09572","snapshot_observed_at":"2026-07-27T02:19:55.902966Z","title":"Vignesh Kothapalli, Rishabh Ranjan, Valter Hudovernik, Vijay Prakash Dwivedi, Johannes Hoffart, Carlos Guestrin, and Jure Leskovec","venue":null,"work_id":"62febbba-1e43-4e8f-8bc6-8da1b96ae008","year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"cited_paper":"/paper/2602.09572","citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:8ad463ee38277fdc113bddb72a8b063cc2cf9b0647611bf495b6942adb0f8e94","observation_id":"e1be4d50-6cf9-4330-a4f0-0913d0fad4f1","resolution":{"observed_at":"2026-07-27T02:19:55.902966Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"PluRel: Synthetic data unlocks scaling laws for rela- tional foundation models","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:bd29daaa7a628029b870bb8ab0cf329fffa1138c6ec662218761eede29712652","observation_id":"04aeca26-776c-45f1-a789-ef6c613a350e","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Position: Graph foundation models are already here","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:8b0e44339b11f985c5961cda9a2202a1b63f68094a57f217425a2a4fdfe8f9bb","observation_id":"8fc7c5e3-2ee2-44db-a2a9-7caad314fe80","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Transformers can do bayesian inference","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:c87627bbe6da1e8129c6678546200f9486b43576238d5ff37778adfab0df5a6f","observation_id":"a4fc22d3-14cb-4753-a992-5c336fb77230","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Statistical foundations of prior-data fitted networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:e71bd56de77132b5ec4a0d438cccfa0d13a6c128021ee6739d6fe5a4e708f5bc","observation_id":"83b69c3f-0e2a-4cd0-9e25-9c81d66dff92","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1109/icdm.2005.89","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Leveraging relational autocorrelation with latent group models","venue":null,"work_id":"e5ca2e08-9e77-43e9-8c81-4a91eeb9c348","year":2005},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:b8a35365eee0d4f13c9d2817ab2a929c194da31ed659c8709a13a9b13423bd7a","observation_id":"385fffb2-18ab-427c-9986-79b45d01d28b","resolution":{"observed_at":"2026-06-28T07:41:45.392744Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T12:17:03.600265Z","title":"In: Zong, C., Xia, F., Li, W., Navigli, R","venue":null,"work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","year":2024},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:80420af6362979c3a2123f705e6d5b0784503abbc60070bad437b859e4bb29d3","observation_id":"e1de84ca-efec-4ea7-ae2b-221e61f678c2","resolution":{"observed_at":"2026-06-28T07:41:45.390775Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"Character- izing graph datasets for node classification: Homophily-heterophily dichotomy and beyond","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:ce35988f1efa1b7af29048d2917f5a154e3cb95dd2b11a76d005ef2b9f377332","observation_id":"bc7a30af-36df-4535-a957-189aacc6ead7","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"TabICL: A tabular foundation model for in-context learning on large data","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:5f82ca413dfdbfd675b3c95d2997620a2b0c0e176274937fe181b35aee926199","observation_id":"1637ea10-62f6-4fd4-88a9-e8935333ba69","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Kanatsoulis, Roshan Reddy Upendra, Mahmoud Mohammadi, Joe Meyer, Tom Palczewski, Carlos Guestrin, and Jure Leskovec","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:c9a18952f13daf91fa42ef085518e914cf7528b783da5cd30d24a68d4a2173c2","observation_id":"45b24aa7-541b-43c9-90d3-b3750c2b054b","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Pretraining task diversity and the emergence of non-bayesian in-context learning for regression","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:67d62d7fa64b1a75315788b38f8d8cbe9c317b0a511d12d4acb5e01233a4d15a","observation_id":"d9188648-54a2-4f69-965e-fdfb787d4680","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Lenssen, Yiwen Yuan, Zecheng Zhang, Xinwei He, and Jure Leskovec","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:f5759f67da8071a35e5dc9ab6402db7be8059d780bae6ecc2a8a92c77303a35a","observation_id":"16abacb7-cff2-4bc1-8337-3dbc6ba477a9","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.52202/079017-0672","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"URL https://proceedings.neurips.cc/paper_ files/paper/2024/file/25cd345233c65fac1fec0ce61d0f7836-Paper-Datasets_ and_Benchmarks_Track.pdf","venue":null,"work_id":"b09db11a-cc86-4ed6-b77b-efa0330d21a7","year":2024},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:53930383887debff17bab68eda1f1842fa00db17e6b94c1084c993f29a40474f","observation_id":"c57c0c46-f903-461c-b7d8-d93895524456","resolution":{"observed_at":"2026-06-28T07:41:45.396677Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"Prototypical networks for few-shot learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:782a46533d480e16b5c033beb58a2c0b661dc0566753b00bd43d4c16f979dbf3","observation_id":"dbfe31f3-95a6-4de3-935b-76572d33740d","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"A pre- training framework for relational data with information-theoretic principles","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:3aa5283dd847223cb80026a3d6c701c459185e79030fbacab259f241d4e6351e","observation_id":"c4ed9821-89c8-4bcf-b7a3-a26bd0d73740","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Transformers learn in-context by gradient descent","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:55bb17fda8b3a6a417870eef82ad4e7374b338f0e0bfd0c0880c7f5800203a27","observation_id":"50e7f82e-4ee7-4146-a610-63f9b7d772cb","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.52202/079017-0856","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"4dbinfer: A 4d benchmarking toolbox for graph-centric predictive modeling on rdbs","venue":null,"work_id":"d3cfb200-ba1b-455e-9fa6-ec6135afd27f","year":2024},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:0ce8eaa07f025b97bf7881bf521a1b4206264325cf243c4ae2675cdfc66effbf","observation_id":"bced0889-8b08-43cb-ab02-fa4d4a80096e","resolution":{"observed_at":"2026-06-28T07:41:45.388759Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"Griffin: Towards a graph-centric relational database foundation model","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:4bb02674a409500369d1b05b13d8d0161a39992049848571f3ab29047e84301d","observation_id":"9da47d7f-2ccc-42bb-abd7-1a82dfcd4596","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.03805","last_updated":"2026-05-28T12:33:08Z","snapshot_observed_at":"2026-08-02T19:05:16.400235Z","submitted_at":"2026-03-04T07:30:54Z","title":"Relational In-Context Learning via Synthetic Pre-training with Structural Prior","version":5},"cited_work":{"arxiv_id":"2603.03805","doi":null,"metadata_source":"pith","pith_arxiv_id":"2603.03805","snapshot_observed_at":"2026-07-02T06:06:41.441129Z","title":"Relational In-Context Learning via Synthetic Pre-training with Structural Prior","venue":"cs.LG","work_id":"f7f382e9-3609-4def-ad1c-c3d4db8ecc30","year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"cited_paper":"/paper/2603.03805","citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:5ef9dfdee074ccdb7ae67f0155cb1bb8d3e0b6e7ba484c1b84f73cdb21415110","observation_id":"3e415f33-4000-4f7c-a9ec-55548e2657ee","resolution":{"observed_at":"2026-07-02T06:06:41.442456Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.15116","last_updated":"2025-05-21T05:08:00Z","snapshot_observed_at":"2026-08-05T07:30:58.368854Z","submitted_at":"2025-05-21T05:08:00Z","title":"Graph Foundation Models: A Comprehensive Survey","version":1},"cited_work":{"arxiv_id":"2505.15116","doi":"10.48550/arxiv.2505.15116","metadata_source":"pith","pith_arxiv_id":"2505.15116","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Graph founda- tion models: A comprehensive survey.arXiv preprint arXiv:2505.15116","venue":"cs.LG","work_id":"a2d2734e-af16-43d7-8fa5-e88b5f41ca5a","year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"cited_paper":"/paper/2505.15116","citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:a9138f237e37fcc84e992d0a120fa6daa1afeed8bb95a189257f4411aec700c2","observation_id":"e629c128-26f6-4b4f-bf5a-3a2cfa3b9c52","resolution":{"observed_at":"2026-07-02T06:06:41.439996Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-07-11T01:19:48.163035+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T01:19:48.163035+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.03846","last_updated":"2023-03-08T07:37:43Z","snapshot_observed_at":"2026-07-06T14:59:39.238136Z","submitted_at":"2023-03-07T12:24:17Z","title":"Larger language models do in-context learning differently","version":2},"cited_work":{"arxiv_id":"2303.03846","doi":"10.48550/arxiv.2303.03846","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.03846","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2303.03846 , year =","venue":"arXiv (Cornell University)","work_id":"583ca0e5-c312-49d2-a128-f829fccd49e1","year":2023},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"cited_paper":"/paper/2303.03846","citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:2db746ac99fc6a5b41aff562965bf262a2b8d2ac68e796fbc2cbecfc63160e7a","observation_id":"e4c85886-a6f7-449e-8f29-18b2ced1375a","resolution":{"observed_at":"2026-07-02T06:06:41.434356Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"The learnability of in-context learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:b01839ba32fe67c23923cc1de853ad912aaae496188332fd601dbbeae75740fd","observation_id":"20a32a3a-2823-413f-aab3-1fb69871d64d","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Large language models are good relational learners","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:4f81077988deddfe0a68df583212226b73df035ae75227c34058980be55ed016","observation_id":"01abb29d-cf66-41f9-afa1-2ff87c452b59","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.11829","last_updated":"2024-11-18T18:48:13Z","snapshot_observed_at":"2026-07-06T19:52:07.342252Z","submitted_at":"2024-11-18T18:48:13Z","title":"Tackling prediction tasks in relational databases with LLMs","version":1},"cited_work":{"arxiv_id":"2411.11829","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.11829","snapshot_observed_at":"2026-07-02T06:06:41.435500Z","title":"Wydmuch, L","venue":null,"work_id":"4f1531fe-7251-4a4a-9913-cee87eebb85f","year":2024},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"cited_paper":"/paper/2411.11829","citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:2a3151b21662c0ddd9947db0617b5dec7427fb31bd89e3ca5ae15bf85754c86d","observation_id":"80061069-a6e5-4cd3-9b02-09ce94d007cc","resolution":{"observed_at":"2026-07-02T06:06:41.436991Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T07:37:38.063200Z","title":"An explanation of in- context learning as implicit Bayesian inference","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:f87123614009cac5a47072c4884644ef03da6faea211625538a9cd587f0f6ae6","observation_id":"752b97fd-ab60-4d48-885f-1d467fce2a75","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"Do RDB foundation models even need data? InICLR 2026 Workshop on Foundation Models for Tabular and Structured Data (DATA-FM), 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:a63fff8211a61f68038b9b22cf96fa7726545ff47d99757d39527c9cd8953ea3","observation_id":"82a1ddca-e46a-4c7b-aa90-23a07c9fd85a","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:9259b83a88d9480bffa58b682f9b63cbef1c093d20b8f89393bc41d53b3a47d6","observation_id":"10d22f09-9196-40c9-af68-36efe9813393","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"ContextGNN: Beyond two-tower recommendation systems","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:f4818c6867d22f2e0c4476a032c45ac0b5bccb1c90a3c59b1e1375b58ff28e94","observation_id":"729e1046-834f-4ea8-b67a-aa589db19b48","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2026-06-28T07:37:38.063200Z","title":"What and how does in-context learning learn? Bayesian model averaging, parameterization, and generalization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:648b06f23b579e5690e5fe6cda638d0d9ae6afa89589bb7864447824a044276f","observation_id":"cae1e117-9bb0-4522-ab4b-5ad43a008694","resolution":{"observed_at":"2026-06-28T07:37:38.063200Z","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":"2270.8960","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T06:06:41.443697Z","title":"RT is in the lazy / frozen-feature regime","venue":null,"work_id":"2e1bf5fb-8985-47b6-b32a-708a4990e034","year":2021},"citing_paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-06-28T07:37:38.063200Z"},"links":{"citing_paper":"/paper/2606.04320"},"observation_digest":"sha256:5d815b659e9b6e3d0bc6d6a26345bdec1ddc8907b0d48511e204bb1e6c31265b","observation_id":"49a29fb5-e753-492e-b0b0-bdef93685985","resolution":{"observed_at":"2026-07-02T06:06:41.445137Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2606.04320","last_updated":"2026-06-03T00:48:44Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T23:44:28.265478Z","submitted_at":"2026-06-03T00:48:44Z","title":"OpenRFM: Dissecting Relational In-Context Learning"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":2,"metadata_mismatch":3,"parse_uncertain":0,"unresolved":42,"verified_exact":14,"verified_fuzzy":0},"total_outbound_references":61},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 2 inbound Pith citation observations for arXiv:2606.04320."}