{"as_of":"2026-08-07T18:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ae26a7724b17414ac1f17deeac2eb35809f57c14dc4c9622fa0c80f7b0cbd193","coverage":[{"denominator":6,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T19:05:20.221158Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":9,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T13:14:30.940081Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-02T06:06:41.441129Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"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":"2604.12596","last_updated":"2026-04-14T11:24:11Z","snapshot_observed_at":"2026-08-02T22:11:21.181099Z","submitted_at":"2026-04-14T11:24:11Z","title":"KumoRFM-2: Scaling Foundation Models for Relational Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T15:50:50.747066Z"},"links":{"cited_paper":"/paper/2603.03805","citing_paper":"/paper/2604.12596"},"observation_digest":"sha256:9dd768c6eefdcbca55200a0f90a774091c86350233509e81eb0b6e6552dc0d41","observation_id":"e3145a58-51fa-4928-9056-b29a51b9f83a","resolution":{"observed_at":"2026-05-11T09:46:05.983827Z","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":"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":"2605.14907","last_updated":"2026-05-14T14:41:19Z","snapshot_observed_at":"2026-08-04T12:36:41.171600Z","submitted_at":"2026-05-14T14:41:19Z","title":"KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-30T20:28:41.778793Z"},"links":{"cited_paper":"/paper/2603.03805","citing_paper":"/paper/2605.14907"},"observation_digest":"sha256:2925867ea89e7d2834291f27e576b8af0188fa0e5118ed8665383512d46803d6","observation_id":"314de3cc-80e9-4831-8f82-71f6300c9e9e","resolution":{"observed_at":"2026-06-30T20:35:02.826757Z","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":"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":"2605.18971","last_updated":"2026-05-18T18:00:45Z","snapshot_observed_at":"2026-08-01T17:23:16.944962Z","submitted_at":"2026-05-18T18:00:45Z","title":"Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-20T12:38:49.037178Z"},"links":{"cited_paper":"/paper/2603.03805","citing_paper":"/paper/2605.18971"},"observation_digest":"sha256:dc0f32e04d6ecea93d2f14d49110f957f322f554d697ec3119a4d103fcf579f3","observation_id":"afdac293-3d5f-48aa-b9ad-d46ca6984181","resolution":{"observed_at":"2026-05-20T12:43:17.593711Z","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":"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":"2606.03040","last_updated":"2026-06-02T02:25:53Z","snapshot_observed_at":"2026-08-01T15:42:00.069578Z","submitted_at":"2026-06-02T02:25:53Z","title":"RelGT-AC: A Relational Graph Transformer for Autocomplete Tasks in Relational Databases","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-06-28T10:45:28.119622Z"},"links":{"cited_paper":"/paper/2603.03805","citing_paper":"/paper/2606.03040"},"observation_digest":"sha256:b2f82880dc5bbbd72a5d48a4e3135bbbe7980c1599b8bd18dfed27684d4041e4","observation_id":"6b0b6b28-1d03-4da1-9325-ec82d5d2efd4","resolution":{"observed_at":"2026-07-02T02:36:27.506449Z","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":"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":"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":"2606.29091","last_updated":"2026-06-27T21:14:06Z","snapshot_observed_at":"2026-08-02T16:44:23.015790Z","submitted_at":"2026-06-27T21:14:06Z","title":"Statistically Indistinguishable, Operationally Distinct: A Formal Barrier for Tabular Foundation Models","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-06-30T09:27:45.182117Z"},"links":{"cited_paper":"/paper/2603.03805","citing_paper":"/paper/2606.29091"},"observation_digest":"sha256:4584abf687c9886e48a0a14472f3d67593de6bf2b2a1e2ca3bef08dc41d8641f","observation_id":"f5a343d3-364d-4f73-8e51-97737c046377","resolution":{"observed_at":"2026-06-30T09:34:34.755361Z","resolver_source":"local_arxiv","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":{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.03805","snapshot_observed_at":"2026-07-11T11:47:14.742492Z","title":"Relational in- context learning via synthetic pre-training with structural prior.arXiv preprint arXiv:2603.03805,","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":20,"source":"pdf_text","source_observed_at":"2026-07-11T11:47:14.742492Z"},"links":{"cited_paper":"/paper/2603.03805","citing_paper":"/paper/2607.05476"},"observation_digest":"sha256:4a3c690484bd525fe7f436cbac34dbab1b254f10b5d3de681ed46018fe2084e1","observation_id":"8ef35c59-561c-468e-906a-86596598f024","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":"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.03805","snapshot_observed_at":"2026-08-02T08:36:04.443267Z","title":"Relational in- context learning via synthetic pre-training with structural prior.arXiv preprint arXiv:2603.03805,","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":20,"source":"pdf_text","source_observed_at":"2026-08-02T08:36:04.443267Z"},"links":{"cited_paper":"/paper/2603.03805","citing_paper":"/paper/2607.05476"},"observation_digest":"sha256:b74f3b579f8b0845953bfe1929521adee766572d9872eb13e9b7102f8a243787","observation_id":"1878cf31-3e1f-402b-9f36-4a132810ec4b","resolution":{"observed_at":"2026-08-02T08:36:04.443267Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.03805","snapshot_observed_at":"2026-08-03T13:14:30.940081Z","title":"arXiv preprint arXiv:2603.03805 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.29129","last_updated":"2026-07-31T07:59:18Z","snapshot_observed_at":"2026-08-06T21:37:30.014556Z","submitted_at":"2026-07-31T07:59:18Z","title":"PluRel-to-RDB-PFN: Schema-Guided Synthetic Relational Pretraining","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-03T13:14:30.940081Z"},"links":{"cited_paper":"/paper/2603.03805","citing_paper":"/paper/2607.29129"},"observation_digest":"sha256:a83475b2d163ef248bf8a2db0b49bba28a7f7d2ac77a15817af79a48bdd03e11","observation_id":"22573878-d2f7-4724-bcde-8d10bdeed785","resolution":{"observed_at":"2026-08-03T13:14:30.940081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2603.03805/citation-record","integrity":"/paper/2603.03805/integrity","json":"/paper/2603.03805/citation-record.json","paper":"/paper/2603.03805"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:05:19.606764Z","title":null,"venue":null,"work_id":null,"year":null},"citing_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},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T19:05:19.606764Z"},"links":{"citing_paper":"/paper/2603.03805"},"observation_digest":"sha256:3f669815be46fb6b3ba4123b7d85ebd13086da1e6ff4282db272fa045668bbb9","observation_id":"970afa07-9d72-4bde-af01-a0a09e38c883","resolution":{"observed_at":"2026-08-02T19:05:19.606764Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:05:19.695759Z","title":"To capture this, we augment the latent initialization step","venue":null,"work_id":null,"year":2024},"citing_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},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T19:05:19.695759Z"},"links":{"citing_paper":"/paper/2603.03805"},"observation_digest":"sha256:1324d2d7ca1ab963684e5d771ca413be105adeae10bdaaa12c195995b19af7c4","observation_id":"3508abb1-15bd-4027-975b-2a3032f6592f","resolution":{"observed_at":"2026-08-02T19:05:19.695759Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:05:19.818342Z","title":"– Relational Tasks (RDBs):∼1.2M datasets, comprising: * Small Prior (1-hop DFS):∼800k","venue":null,"work_id":null,"year":null},"citing_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},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T19:05:19.818342Z"},"links":{"citing_paper":"/paper/2603.03805"},"observation_digest":"sha256:d59d8cda219c2a226331b46e36ac974bfeac1e824a4e19c810cd28941fbd17f0","observation_id":"827205c2-f7ff-4f51-9b47-a9d3fa90bbae","resolution":{"observed_at":"2026-08-02T19:05:19.818342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:05:20.037269Z","title":"Since DFS produces feature sets of variable length depending on the schema depth, we employ a standardization strategy to maintain consistent input dimensions","venue":null,"work_id":null,"year":null},"citing_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},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T19:05:20.037269Z"},"links":{"citing_paper":"/paper/2603.03805"},"observation_digest":"sha256:8c7770e3a8dae16ed6c9ec338a695511fe10ea7d170323c617861bbf96284769","observation_id":"8b902fed-b757-4cf8-b9a2-edcc9f62dad3","resolution":{"observed_at":"2026-08-02T19:05:20.037269Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:05:20.125528Z","title":"To maximize data utility, we employ a multi-target sampling strategy","venue":null,"work_id":null,"year":null},"citing_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},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T19:05:20.125528Z"},"links":{"citing_paper":"/paper/2603.03805"},"observation_digest":"sha256:b98cdfab5fac03db0c984749411a54e235182e104504482d425f4cd70e824f7b","observation_id":"3366e359-4b8c-4286-aa26-0f76e69b6a5c","resolution":{"observed_at":"2026-08-02T19:05:20.125528Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:05:20.221158Z","title":"row token","venue":null,"work_id":null,"year":2048},"citing_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},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T19:05:20.221158Z"},"links":{"citing_paper":"/paper/2603.03805"},"observation_digest":"sha256:6b25493c7b83fd8d07c7f7890d9c38f2582a71e74279d7cac15539b91b3b3c19","observation_id":"4074a13e-d122-4c92-93aa-3b0f3a6f19ab","resolution":{"observed_at":"2026-08-02T19:05:20.221158Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.03805","last_updated":"2026-05-28T12:33:08Z","latest_version":5,"primary_category":"cs.LG","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"},"reference_resolution":{"displayed":6,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":6},"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 6 of 6 outbound references and 9 inbound Pith citation observations for arXiv:2603.03805."}