{"as_of":"2026-08-12T23:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:01045083bacf7238d4ff42951f1ddfd5eccf70604ec98a3cdda968aebeb4bbd9","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T05:40:05.186144Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.17348/citation-record","integrity":"/paper/2412.17348/integrity","json":"/paper/2412.17348/citation-record.json","paper":"/paper/2412.17348"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.06989","last_updated":"2021-07-11T17:41:01Z","snapshot_observed_at":"2026-08-05T21:20:04.167532Z","submitted_at":"2021-06-13T13:33:31Z","title":"The DEformer: An Order-Agnostic Distribution Estimating Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.06989","snapshot_observed_at":"2026-08-11T05:40:04.979286Z","title":"Alcorn and Anh Nguyen","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:04.979286Z"},"links":{"cited_paper":"/paper/2106.06989","citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:099f8350ab25ec0abef264c4359714d6ca3cbaa114ed00bf06c4a13f82e2b774","observation_id":"f82aca86-f7d0-49ba-bf1f-f3257c3040fd","resolution":{"observed_at":"2026-08-11T05:40:04.979286Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.254371Z","title":"Tabnet: Attentive interpretable tabular learning","venue":null,"work_id":"f58fec23-ae23-49ef-9715-61d2580329b1","year":2021},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:04.984499Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:21226ba65606b45ff7f2ae76039d6dd30835c75281a67c5121f683d29f41245d","observation_id":"34c28268-da31-41a3-a6aa-702e555d1ab3","resolution":{"observed_at":"2026-08-11T05:40:06.259042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T05:40:04.989086Z","title":"Transformers for tabular data representation: A tutorial on models and applications","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:04.989086Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:57fcce0ec13b9dcd54f00c9654b33354894014d328694f1cd1c5f6f410b29c99","observation_id":"8934a3b6-f045-4457-b837-07d0f071e250","resolution":{"observed_at":"2026-08-11T05:40:04.989086Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.240244Z","title":"The JavaScript Object Notation (JSON) Data Interchange Format","venue":null,"work_id":"acdd4a14-98be-4509-a498-7507582b23d3","year":2014},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:04.993689Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:9e9f7d92dde8d10446f32b255011e4d4ece4c80bc7889e7c5c21215de4c5c6e6","observation_id":"0d418b85-0b88-4faf-81f3-207ac54cc70a","resolution":{"observed_at":"2026-08-11T05:40:06.244845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T05:40:04.997988Z","title":"XGBoost: A Scalable Tree Boosting System","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:04.997988Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:716d48a62c013c164893c6f6ae88179f2d2e5229b2e68c9ddee980d0215bf3c7","observation_id":"09b2db56-6c55-4a70-bf41-a152d45670af","resolution":{"observed_at":"2026-08-11T05:40:04.997988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.225354Z","title":"TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data","venue":null,"work_id":"91d66906-2524-46f8-a2dc-aa40e888a98a","year":2021},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.002396Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:006757ff5ec90bfea16f4e0f2099c47623e7a0611e41648c1a56a34a4c0dfeb9","observation_id":"46141968-9906-4f1b-bd09-b59c932ec839","resolution":{"observed_at":"2026-08-11T05:40:06.230275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.210906Z","title":"Large language models (LLMs) on tabular data: Prediction, generation, and understanding - a survey","venue":null,"work_id":"63a216b2-63ef-4393-a5ca-fd8644cb3ef8","year":2024},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.007028Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:7a494392b4bc735a41809ce392a17a87dfa19049bea6e22863415f146d711185","observation_id":"67f8f616-7dc8-4bc2-8389-31099bbb892e","resolution":{"observed_at":"2026-08-11T05:40:06.215421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.197139Z","title":"DDXPlus: A new dataset for automatic medical diagnosis","venue":null,"work_id":"b32e3ee4-7a48-4082-834d-9e70f718a536","year":2022},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.011086Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:5f95d135eac8c5a2c48311a555cd606cd65478d0acfccd353844533858e37f09","observation_id":"cada8fdf-bfed-436b-b48a-67301ab02a00","resolution":{"observed_at":"2026-08-11T05:40:06.201819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.08155","last_updated":"2020-09-18T15:38:12Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-02-19T13:09:07Z","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.08155","snapshot_observed_at":"2026-08-11T05:40:05.015188Z","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages, September 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.015188Z"},"links":{"cited_paper":"/paper/2002.08155","citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:8b4f2da06ca48549783340784d85f200d460e082915dd0e897b86283573a0ea4","observation_id":"03816556-7e6c-432b-8528-5aa133b643ba","resolution":{"observed_at":"2026-08-11T05:40:05.015188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.183698Z","title":"A new algorithm for data compression","venue":null,"work_id":"d5436f7e-74a7-491e-aeea-ccce3a9d04fd","year":1994},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.019593Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:a3773068fdda7f443fa6ca187579d25b360ca289e0cf81adeb70730768bab421","observation_id":"99130209-d165-40b5-9474-62c9c6c99daa","resolution":{"observed_at":"2026-08-11T05:40:06.188006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.170280Z","title":"Convolutional Sequence to Sequence Learning","venue":null,"work_id":"32fdc0f2-eaf8-490e-94da-16115a1d971d","year":2017},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.023531Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:c7fcc6f40816a0ac7ed34154f76ad8304a37e2e32d7b4521bf86d9653349f4d9","observation_id":"c1f328b7-63c4-4bd9-8cd6-38b2a641b5e2","resolution":{"observed_at":"2026-08-11T05:40:06.174638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"1996.54891","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.644383Z","title":"Goller and A","venue":null,"work_id":"ed9092e1-9376-4974-bf2c-682f352c8623","year":1996},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.028125Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:8e4b6137e0affdc5210ae06dac5946f250b4af35711d60380ae948bbdd6a4b65","observation_id":"bd1e4853-21c3-4c90-aeab-8712851d193f","resolution":{"observed_at":"2026-08-11T05:40:05.651002Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.156520Z","title":null,"venue":null,"work_id":"a3c748c5-b411-443d-a12d-222818f35760","year":2022},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.032170Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:7b36a90f603b840da565b04e96f2a831cacc7368922836aea344b1b666ac55f9","observation_id":"683e7c83-bdb9-4baa-b313-8750dbc7a82b","resolution":{"observed_at":"2026-08-11T05:40:06.160794Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T05:40:05.036173Z","title":"Long Short-Term Memory","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.036173Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:14a400d2833f78d96d598ec587e8b5a02532a60f00073c9d5d6006fd9ae08301","observation_id":"0e0903dd-d0af-43c9-a303-b9f77eb906d8","resolution":{"observed_at":"2026-08-11T05:40:05.036173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.01848","last_updated":"2023-09-16T09:33:32Z","snapshot_observed_at":"2026-08-11T17:55:52.085401Z","submitted_at":"2022-07-05T07:17:43Z","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.01848","snapshot_observed_at":"2026-08-11T05:40:05.040354Z","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second, September 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.040354Z"},"links":{"cited_paper":"/paper/2207.01848","citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:1fbd69a759adbb3297ec4748d0fef471f677644635547ccf3408c7bf9e9dcf4a","observation_id":"4b4f2ce2-8d42-455d-8512-745eb29359e4","resolution":{"observed_at":"2026-08-11T05:40:05.040354Z","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":"2026-08-11T05:40:05.044698Z","title":"Multilayer feedforward networks are uni- versal approximators","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.044698Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:9f7c169e845e2c5f46c41357ee32920435ec3dbac01c0ef21ac95d682182b281","observation_id":"ed95c5a4-b779-41bc-8682-662d991bb22b","resolution":{"observed_at":"2026-08-11T05:40:05.044698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.06678","last_updated":"2020-12-11T23:31:23Z","snapshot_observed_at":"2026-07-06T10:23:43.246202Z","submitted_at":"2020-12-11T23:31:23Z","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.06678","snapshot_observed_at":"2026-08-11T05:40:05.048810Z","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.048810Z"},"links":{"cited_paper":"/paper/2012.06678","citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:b61d57e65dfd2c48635f586159abd79ce6395e8630420a1bbd569e62e7844720","observation_id":"d5f29184-d99c-49a7-8794-c90e1fbb0d85","resolution":{"observed_at":"2026-08-11T05:40:05.048810Z","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":"2026-08-11T05:40:05.053027Z","title":"LightGBM: A Highly Efficient Gradient Boosting Decision Tree","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.053027Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:b376dc52d3baeaccdf698be28c4e344a3340d0b6802025a672b0ed7383d02215","observation_id":"24a3d698-646f-425a-beab-a4221bbddb10","resolution":{"observed_at":"2026-08-11T05:40:05.053027Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.133935Z","title":"Adam: A Method for Stochastic Optimization","venue":null,"work_id":"de035166-1849-444b-9359-04fc67285dc3","year":2014},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.057054Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:a9edf2b7ef3f019ad163072609d2582e8584ff1ef80cbcb03b3b772be387be8f","observation_id":"1b65060e-3756-41c8-a5e2-82a239626d02","resolution":{"observed_at":"2026-08-11T05:40:06.138996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.119966Z","title":"Automata-based constraints for language model decoding","venue":null,"work_id":"05e79581-bbe4-4fe7-a088-ba0ee17f055d","year":2024},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.061080Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:b58ce0d2d1605998c384e93632a4aa2d7b772d21b589427860115e7b0a583b17","observation_id":"780d062d-01e7-4ed6-94e8-f4049fcd27c9","resolution":{"observed_at":"2026-08-11T05:40:06.124216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.105234Z","title":"TabDDPM: Modelling Tabular Data with Diffusion Models","venue":null,"work_id":"40f6fbb9-c0bb-4bdf-80f8-921e00f0dc44","year":2023},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.065031Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:a681f97e925e4b7eae0332f56679dfb4a012606977cff3cdfa9abef3c37f5bc1","observation_id":"ab0ab05d-cbba-47c5-adeb-9841589a102a","resolution":{"observed_at":"2026-08-11T05:40:06.109822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.091246Z","title":"The Neural Autoregressive Distribution Estimator","venue":null,"work_id":"9ed1435a-a3e5-4f42-b71f-fc199f600831","year":2011},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.068862Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:3c1d5e06ea58a575eb923397178556848f8166832cf71f4cf7dd3f0189afeb60","observation_id":"4c5ddbe7-0120-4c25-87a6-cf5026a5941f","resolution":{"observed_at":"2026-08-11T05:40:06.096060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.077508Z","title":"TreeRNN: Topology-preserving deep graph embedding and learning","venue":null,"work_id":"202a0caf-0896-4bbb-89f2-bcfdfd4e8780","year":2020},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.072744Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:4df27cd5cbaab2d22601a978b0a4e352ebc44053316a7694d7875388b3caf92c","observation_id":"0715b7fd-ac48-48f0-9707-e054ceb16abf","resolution":{"observed_at":"2026-08-11T05:40:06.082063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.063517Z","title":"JsonGrinder.jl: Automated differentiable neural architecture for embedding arbitrary JSON data","venue":null,"work_id":"243ee91f-f48b-4357-b268-f80183cf83ca","year":2022},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.076600Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:2c017fa7056db95b9b8153e9b6403a2be713c7c6493a8a3e267f7a5c49270a12","observation_id":"07ac1ea0-fa70-4acd-8298-a0ee9b0959f1","resolution":{"observed_at":"2026-08-11T05:40:06.067948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.050107Z","title":"The UCI Machine Learning Repository","venue":null,"work_id":"ad5f26b2-d91a-4f8b-b233-d4a5098b6c5f","year":null},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.080609Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:bdb40f59be1d6e60f50cf979979249581e225d8c2bec69cffb7499b5844847fe","observation_id":"b9068ba9-ce1e-44b2-9b8b-8a25ad212ccb","resolution":{"observed_at":"2026-08-11T05:40:06.054327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T05:40:05.084664Z","title":"Pedregosa, G","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.084664Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:b0bd70ddfbd133523c8f2de0007501d210114d6c9907410713d3b88a3ba35b2e","observation_id":"0a156dc9-106e-40fb-9357-b14d9651f4b6","resolution":{"observed_at":"2026-08-11T05:40:05.084664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.027370Z","title":"Approximation capability of neural networks on spaces of probability measures and tree-structured domains, June 2019","venue":null,"work_id":"51e238b9-2922-41e6-b6e4-5e00b4c0dde9","year":2019},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.088786Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:e513589cde6c225e69b7efa54dc7cacec989d52c95982560cfdd296cd53533a1","observation_id":"9e98d07d-94c7-4a5c-95d0-676708157054","resolution":{"observed_at":"2026-08-11T05:40:06.032095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:06.013003Z","title":"CatBoost: Unbiased boosting with categorical features","venue":null,"work_id":"d64b0449-0e6c-4406-bf3f-00ad5929943f","year":2018},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.092922Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:ae2f2324591b9e3a29f1cb49cba87e3974b14e73da9a94c114b5506b1b7e8ae3","observation_id":"e21fba2e-dd50-44d0-8322-f905dbd3c573","resolution":{"observed_at":"2026-08-11T05:40:06.017322Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.999531Z","title":null,"venue":null,"work_id":"f49a85a8-927d-4d46-a49c-ca9f2881fc5c","year":2021},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.097241Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:7f5de5f4996a0345febc21fb40a06c9adec57a01dc87f1e16f47107b2dffbbda","observation_id":"6e8c6723-224b-4a6e-a15a-4c594072f791","resolution":{"observed_at":"2026-08-11T05:40:06.003711Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.985648Z","title":"Improving Language Understanding by Generative Pre-Training,","venue":null,"work_id":"19f150e3-568b-47a4-8c4d-7cf770e73314","year":null},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.101453Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:1e388a9a67226655e6bcc13f18c2d736b4b99be20e4716941b3af9c0247f766f","observation_id":"07a0749d-011b-456f-adb4-ee0d207fd306","resolution":{"observed_at":"2026-08-11T05:40:05.990579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T05:40:05.109725Z","title":"The graph neural network model","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.109725Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:6beb03d0e79658477c30ce06a4f3d337252da1056f5ad15cae7867c948c6c541","observation_id":"3a36b6e3-1ecd-4860-b61d-2814e9a9e076","resolution":{"observed_at":"2026-08-11T05:40:05.109725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.958626Z","title":"Novel positional encodings to enable tree-based transformers","venue":null,"work_id":"f352504b-e376-473d-bc83-0022599170e6","year":2019},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.113688Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:0ce5e98fe485216ceff821ef7cefa97164b6a6a472f383e42ea673e09a564fe8","observation_id":"2e72b383-f559-492b-8f13-2ffdfcd9f693","resolution":{"observed_at":"2026-08-11T05:40:05.963041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T05:40:05.117666Z","title":"Tabular data: Deep learning is not all you need","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.117666Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:6e2c2019c3aee0827a2c300dd9fa3d64a24f0a8ce66e9bd64b029ccb770bc903","observation_id":"b73e131e-4817-42e4-a77b-66af4da065d3","resolution":{"observed_at":"2026-08-11T05:40:05.117666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.936408Z","title":"Introduction to the Theory of Computation","venue":null,"work_id":"47f21de4-d3a4-4cd1-b565-508b59f4dd0e","year":1996},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.121537Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:3170512308321800e1fc694f1e8d752f6a925a6bd3f2e54c889afec274156c4e","observation_id":"265c7cb9-5c36-428a-8cbc-d37d40d3a97e","resolution":{"observed_at":"2026-08-11T05:40:05.940829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.01342","last_updated":"2021-06-02T17:51:05Z","snapshot_observed_at":"2026-08-10T14:13:24.107363Z","submitted_at":"2021-06-02T17:51:05Z","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.01342","snapshot_observed_at":"2026-08-11T05:40:05.125592Z","title":"Bayan Bruss, and Tom Goldstein","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.125592Z"},"links":{"cited_paper":"/paper/2106.01342","citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:3e9e21a733fff35219f2839bf1574c03f4c5bc6679ea48925b86a8768a6cc1cf","observation_id":"794409ce-2016-46d8-a240-d09ffc095e64","resolution":{"observed_at":"2026-08-11T05:40:05.125592Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.922649Z","title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","venue":null,"work_id":"e418aa96-1f23-4034-b1a0-c7b0a5e12eeb","year":1929},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.129882Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:14beb32228c93fb1a4a0b2420ac2d81a173cb1b7c24e38dd88779fb554d97bb9","observation_id":"52f71558-fe50-48be-b732-c07f4ff8bf62","resolution":{"observed_at":"2026-08-11T05:40:05.927108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T05:40:05.133738Z","title":"Roformer: Enhanced transformer with rotary position embedding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.133738Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:2f86fa7149c081999c93b053423a8ab8401ee5138969d2526b4e801ffeee15aa","observation_id":"04e21a6e-6991-49f9-ba77-1fb335338dd5","resolution":{"observed_at":"2026-08-11T05:40:05.133738Z","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":"2026-08-11T05:40:05.137559Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.137559Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:df5d43b09031c4216b9b46a1d311769eb585ae8c5d96ee32ef0f51808cec1fdd","observation_id":"c4f6bdbc-94e6-4325-a626-1c3b50bd89c9","resolution":{"observed_at":"2026-08-11T05:40:05.137559Z","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":"2026-08-11T05:40:05.141553Z","title":"A deep and tractable density estimator","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.141553Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:18aa5e2e513edfdd3d025dc389c8afb6e36ff3f9284c2622f06d0c3911e9d7c9","observation_id":"898c2237-8e7b-4a05-b8f1-67f560f8805c","resolution":{"observed_at":"2026-08-11T05:40:05.141553Z","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":"2026-08-11T05:40:05.145403Z","title":"Gomez, Łukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.145403Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:4caf77da1e6be7b8107febd6dace6979f0ed3f62dffc4ae939b21b8fa69683bb","observation_id":"ae390b37-f310-4e5c-8b9e-1f2ef6e7e67a","resolution":{"observed_at":"2026-08-11T05:40:05.145403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.882904Z","title":"Statistical learning theory: Models, concepts, and results","venue":null,"work_id":"4d6eb937-f044-4478-b2ce-6460db019c70","year":2011},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.149217Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:058bc52b7c83adfdebfc6d69feacd900d72b1e5e7e215a5620ad67fd40edc989","observation_id":"6ddcab2d-e959-4269-b06a-79008cd46cbb","resolution":{"observed_at":"2026-08-11T05:40:05.887353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01204","last_updated":"2024-09-10T07:02:47Z","snapshot_observed_at":"2026-08-12T19:30:49.464948Z","submitted_at":"2024-02-02T08:17:41Z","title":"A Survey on Self-Supervised Learning for Non-Sequential Tabular Data","version":4},"cited_work":{"arxiv_id":"2402.01204","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.01204","snapshot_observed_at":"2026-08-11T05:40:05.444151Z","title":"A Survey on Self-Supervised Learning for Non-Sequential Tabular Data","venue":"cs.LG","work_id":"7fe44361-80d9-4a2f-aaa6-8c9c499e9a80","year":2024},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.153023Z"},"links":{"cited_paper":"/paper/2402.01204","citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:7fece2412d2633cfb90e9ac92bcab02aade3b6bfafc93f23e8a3cf128adf118b","observation_id":"a49a5a24-6f32-47f1-8bd0-973f8628e298","resolution":{"observed_at":"2026-08-11T05:40:05.449505Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.869368Z","title":"Willard and Rémi Louf","venue":null,"work_id":"e0f34e77-78d4-432f-8191-5f5a9533ae7d","year":null},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.157355Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:edfe322bdc66c520dbeb2c04e741a18bd9951b6974721d17b381f5d91b812656","observation_id":"5e4fec8c-c53d-49cc-8448-21cfdecf8536","resolution":{"observed_at":"2026-08-11T05:40:05.873532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.855650Z","title":"Deep Learning on Semi-Structured Data and Its Applications to Video-game AI","venue":null,"work_id":"b9a7f895-5b5c-4a7f-bbf1-e1553c501fc1","year":2020},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.165527Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:28be51da9e4e45bc865fdbadee131315dd5437e08697d81bf94f86588eab0261","observation_id":"ef710e74-ce38-461c-883a-e3690c68ecb9","resolution":{"observed_at":"2026-08-11T05:40:05.860233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05707","last_updated":"2020-02-13T18:49:29Z","snapshot_observed_at":"2026-08-05T02:34:23.104703Z","submitted_at":"2020-02-13T18:49:29Z","title":"A Framework for End-to-End Learning on Semantic Tree-Structured Data","version":1},"cited_work":{"arxiv_id":"2002.05707","doi":null,"metadata_source":"pith","pith_arxiv_id":"2002.05707","snapshot_observed_at":"2026-08-11T05:40:05.402040Z","title":"A Framework for End-to-End Learning on Semantic Tree-Structured Data","venue":"cs.LG","work_id":"3f6eac8d-f2aa-417f-a42d-2d3bb33d4995","year":2020},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.169481Z"},"links":{"cited_paper":"/paper/2002.05707","citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:2cdb375fd6833dc2282d0c92288f4f0536a885e1ebd34cc2a76e07ac8de8507d","observation_id":"37d7343d-6b29-413b-adb4-1109ac487d3b","resolution":{"observed_at":"2026-08-11T05:40:05.410075Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.08144","last_updated":"2016-10-08T19:10:41Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-09-26T19:59:55Z","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.08144","snapshot_observed_at":"2026-08-11T05:40:05.173960Z","title":"Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation, October 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.173960Z"},"links":{"cited_paper":"/paper/1609.08144","citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:d07a87c3129726d32a884a5cf20eeb28fa087d48087ec6913bb19ae603c4b3eb","observation_id":"dd1ac9c2-ed76-4c76-985f-de20cb56d89a","resolution":{"observed_at":"2026-08-11T05:40:05.173960Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.842041Z","title":"Modeling tabular data using conditional GAN","venue":null,"work_id":"58fa9e7e-3688-45c8-ab4e-aa4435273d1e","year":2019},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.178103Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:560c3512abf6655884afa0af65d549251e82539ae53a1b1df109e1f93d3fb6ef","observation_id":"a5df16d7-803b-46c1-b160-426d76b4c8d3","resolution":{"observed_at":"2026-08-11T05:40:05.846532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.08237","last_updated":"2020-01-02T12:48:08Z","snapshot_observed_at":"2026-07-31T22:49:43.034741Z","submitted_at":"2019-06-19T17:35:48Z","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.08237","snapshot_observed_at":"2026-08-11T05:40:05.182106Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.182106Z"},"links":{"cited_paper":"/paper/1906.08237","citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:1204d3e373de57aaef41b7a64a628644c2e694306dfb0cd0c679766f06daea8d","observation_id":"e7737638-8c3e-4c39-9a0b-31621775c20f","resolution":{"observed_at":"2026-08-11T05:40:05.182106Z","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":"2026-08-11T05:40:05.186144Z","title":"AGE\": 12,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.186144Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:5a78024f07fa094047755b87dc5d971a122a97d3b08677263f5ecd598c60798f","observation_id":"c4c894c3-4ede-44f6-83e9-fc52c15b8907","resolution":{"observed_at":"2026-08-11T05:40:05.186144Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:40:05.971851Z","title":"URL https://cdn.openai.com/research-covers/language-unsupervised/ language_understanding_paper.pdf","venue":null,"work_id":"28ffe020-3030-4c84-8e90-c613af991614","year":null},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.105577Z"},"links":{"citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:4fa9e811e86a0b48670c126bfa5e90a5e55e0fd535fd8b86a15d9ba04ab8a773","observation_id":"51aecd0e-7bd4-4c6b-9838-1c80ae7a230d","resolution":{"observed_at":"2026-08-11T05:40:05.976366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09702","last_updated":"2023-08-19T21:27:51Z","snapshot_observed_at":"2026-08-09T04:46:02.275866Z","submitted_at":"2023-07-19T01:14:49Z","title":"Efficient Guided Generation for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09702","snapshot_observed_at":"2026-08-11T05:40:05.161339Z","title":"https://arxiv.org/abs/2307.09702","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-11T05:40:05.161339Z"},"links":{"cited_paper":"/paper/2307.09702","citing_paper":"/paper/2412.17348"},"observation_digest":"sha256:5be9807e8b0c7cf8db8fd23ed10a64f62237abb70d0e3748df0bbae758c095ef","observation_id":"7405377b-35a3-499f-a8db-04271dbbe39e","resolution":{"observed_at":"2026-08-11T05:40:05.161339Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.17348","last_updated":"2024-12-23T07:21:17Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T22:44:29.950168Z","submitted_at":"2024-12-23T07:21:17Z","title":"ORIGAMI: A generative transformer architecture for predictions from semi-structured data"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":22,"verified_exact":2,"verified_fuzzy":25},"total_outbound_references":51},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2412.17348."}