{"as_of":"2026-08-20T19:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c307c23de0cf911ab536a9cb5633c84ab73bbae0c89f88f3211acd620cc771b4","coverage":[{"denominator":56,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":56,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-09T21:11:02.461038Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2607.07047/citation-record","integrity":"/paper/2607.07047/integrity","json":"/paper/2607.07047/citation-record.json","paper":"/paper/2607.07047"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1610.01644","last_updated":"2018-11-22T23:40:00Z","snapshot_observed_at":"2026-08-09T22:50:03.459615Z","submitted_at":"2016-10-05T20:59:01Z","title":"Understanding intermediate layers using linear classifier probes","version":4},"cited_work":{"arxiv_id":"1610.01644","doi":"10.48550/arxiv.1610.01644","metadata_source":"pith","pith_arxiv_id":"1610.01644","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Understanding intermediate layers using linear classifier probes","venue":"stat.ML","work_id":"bdc944db-4be2-44f7-950b-eaef12fab00e","year":2016},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1610.01644","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:e56c072cfb5a1c1f3167d2414e800ac1d904127d1a8042908a5f1ddfcb34fad8","observation_id":"6cfe7fae-e448-46cd-a525-c31ec69b74d8","resolution":{"observed_at":"2026-07-09T21:16:34.231619Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-15T03:08:13.648934+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-15T03:08:13.648934+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.535968Z","title":null,"venue":null,"work_id":"92f111cf-43d6-49b1-a5a5-3359bdc17c76","year":2025},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:2e13d21c32067b0d26466bb71bcb9009495d2d5124bc484b241e50d8d887246b","observation_id":"96b5a201-bdb1-4f36-983f-cb98ebfc2495","resolution":{"observed_at":"2026-07-09T21:16:34.537168Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.5281/zenodo.10034224","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"Zenodo (CERN European Organization for Nuclear Research)","work_id":"ec822956-c7b7-40fc-8ee5-4ccf12b65381","year":2023},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:6e4dec10aed9eb579aa834405ca4320c5a0ca4d1b5277429ed09a3111994b1c3","observation_id":"fcac0b6e-05f1-4a07-b2a3-13614558937d","resolution":{"observed_at":"2026-07-09T21:16:34.059076Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.11379","last_updated":"2021-12-13T14:51:39Z","snapshot_observed_at":"2026-08-14T20:18:33.018821Z","submitted_at":"2017-10-31T09:10:10Z","title":"Latent Space Oddity: on the Curvature of Deep Generative Models","version":3},"cited_work":{"arxiv_id":"1710.11379","doi":"10.48550/arxiv.1710.11379","metadata_source":"pith","pith_arxiv_id":"1710.11379","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Latent space oddity: on the curvature of deep generative models","venue":"stat.ML","work_id":"d1a9f73d-d2c7-406a-9aa1-bc445b2c1b91","year":2017},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1710.11379","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:1ab1bfa7aadfd9a8f9baa8a0058b0458a8aedf8e1f1aa66ca8ce46a0a3f44991","observation_id":"aef80b47-5185-42fc-8f6b-898287b4b4a3","resolution":{"observed_at":"2026-07-09T21:16:34.254859Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.5281/zenodo.593816","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Barachant et al.,Pyriemann, version 0.11, 2026","venue":"Zenodo (CERN European Organization for Nuclear Research)","work_id":"8e11d8f5-28f0-4180-a4d9-9da0d3b5877d","year":2026},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:61138d461bbc77ae1657db77de6be883c80df58ee809a698ab25718f4b7aa31a","observation_id":"ab1805ea-18ef-4c89-accc-0478c9fbaa70","resolution":{"observed_at":"2026-07-09T21:16:34.051521Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2011.217221","doi":"10.1109/tbme.2011.2172210","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"IEEE Transactions on Biomedical Engineering","work_id":"4aa8eda3-9f8d-42c0-be4a-8b0828c40acf","year":2012},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:645025e8f928cab577e92e4480deab0362a34c31f68c7efaa477abbe890020ab","observation_id":"c39d1b6b-8130-4a1a-bd16-3a83ffeae8d9","resolution":{"observed_at":"2026-07-09T21:16:34.068562Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.537792Z","title":null,"venue":null,"work_id":"6a43c0f5-3bf2-4d82-bbc3-9f01e3aec5fe","year":2003},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:6a06cb2b5741f2e3deab0be56f2400823317d6024e5a614c18c5d0a1df9b1cca","observation_id":"2d420ec8-9d94-4e43-bb96-8845d4e26cd2","resolution":{"observed_at":"2026-07-09T21:16:34.538997Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2512.00196","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.234916Z","title":null,"venue":null,"work_id":"c21f1563-345c-4265-be02-bc45b3540266","year":2025},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:a9edcdc7b7b82c531e5248a18ab3a02b4c693eb81be5e8aaf64c6ee510c7d2e4","observation_id":"40c9e7d9-4353-4081-9733-3f8084ac9074","resolution":{"observed_at":"2026-07-09T21:16:34.236304Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.02414","last_updated":"2019-09-12T17:13:21Z","snapshot_observed_at":"2026-08-16T06:50:29.631844Z","submitted_at":"2019-09-03T23:03:50Z","title":"Riemannian batch normalization for SPD neural networks","version":2},"cited_work":{"arxiv_id":"1909.02414","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.02414","snapshot_observed_at":"2026-07-09T21:16:34.256122Z","title":"Riemannian batch normalization for SPD neural networks","venue":"cs.LG","work_id":"a841f020-8740-4b58-b9db-ccbecb66c842","year":2019},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1909.02414","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:f6d592b070bb9524fb400240a016a757a84abf42d9620584a37b22f85eca7799","observation_id":"ef12b601-9f49-4a2e-a501-ee854253f2d4","resolution":{"observed_at":"2026-07-09T21:16:34.257362Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19433","last_updated":"2024-10-02T09:53:48Z","snapshot_observed_at":"2026-08-16T13:14:30.190605Z","submitted_at":"2024-09-28T18:38:21Z","title":"RMLR: Extending Multinomial Logistic Regression into General Geometries","version":2},"cited_work":{"arxiv_id":"2409.19433","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.19433","snapshot_observed_at":"2026-07-09T21:16:34.207392Z","title":"RMLR: Extending Multinomial Logistic Regression into General Geometries","venue":"cs.LG","work_id":"7fa2a09d-4df7-4872-abb7-0756fb9ff039","year":2024},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2409.19433","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:db5ed5d3a0e09a1bc1c655f5a7676034a362d665850089ad40dfe01b19871dd8","observation_id":"4ef8cbd4-6f2f-4801-9abb-18dd70843926","resolution":{"observed_at":"2026-07-09T21:16:34.208870Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15471","last_updated":"2025-04-30T16:06:00Z","snapshot_observed_at":"2026-08-18T14:37:15.642295Z","submitted_at":"2024-05-24T11:49:07Z","title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers","version":4},"cited_work":{"arxiv_id":"2405.15471","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.15471","snapshot_observed_at":"2026-07-09T21:16:34.225463Z","title":"arXiv preprint arXiv:2405.15471 , year=","venue":"cs.CL","work_id":"8c8df321-682c-44d7-8d47-900add8c7239","year":2024},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2405.15471","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:4f2f14e15590b1c22dba0325f3e4b7a0f27ac5fa91affc6e8fa799f0f32fcf04","observation_id":"cca1229a-e7c9-4903-b88b-43ae8434838d","resolution":{"observed_at":"2026-07-09T21:16:34.226679Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.15319","last_updated":"2024-04-03T15:18:50Z","snapshot_observed_at":"2026-08-20T07:31:34.603876Z","submitted_at":"2024-04-03T15:18:50Z","title":"The largest EEG-based BCI reproducibility study for open science: the MOABB benchmark","version":1},"cited_work":{"arxiv_id":"2404.15319","doi":"10.48550/arxiv.2404.15319","metadata_source":"pith","pith_arxiv_id":"2404.15319","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The largest EEG -based BCI reproducibility study for open science: the moabb benchmark","venue":"eess.SP","work_id":"3b18d6fa-4aa5-4946-9c71-788c9156c265","year":2024},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2404.15319","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:323b01195ada5486163013576a701999f7fc9da9e083cc752973cc3b5c8079a2","observation_id":"05a87f77-cd09-4f92-bbc3-b84cf7f5e192","resolution":{"observed_at":"2026-07-09T21:16:34.057461Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.04082","last_updated":"2023-09-08T02:44:37Z","snapshot_observed_at":"2026-08-19T04:26:35.949756Z","submitted_at":"2023-09-08T02:44:37Z","title":"Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning","version":1},"cited_work":{"arxiv_id":"2309.04082","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.04082","snapshot_observed_at":"2026-07-09T21:16:34.189991Z","title":"Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning","venue":"cs.LG","work_id":"bf8beaa4-f2b6-4000-81bc-a412719baa61","year":2023},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2309.04082","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:06041a078d4b045d62bf8b176ac0e82bace05107188e5c9e71d162240f481451","observation_id":"314b9f74-df73-4bbf-bb9b-0aa627a4e478","resolution":{"observed_at":"2026-07-09T21:16:34.191429Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2017.129719","doi":"10.1080/2326263x.2017.1297192","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Riemannian geometry for EEG-based brain-computer interfaces; a primer and a review.Brain-Computer Interfaces, 4(3):155–174","venue":"Brain-Computer Interfaces","work_id":"1b250732-7745-4cbb-bd58-d32223a62235","year":2017},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:c7efbc848eea4eb1eb2729ecc5d87d0d9b8679da7b6fb97f3cfdc90046d2e1e5","observation_id":"18fc7ee9-d1b8-4cc1-8aad-7d91bf4c6602","resolution":{"observed_at":"2026-07-09T21:16:34.054232Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2603.01326","doi":"10.48550/arxiv.2603.01326","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Truth as a trajectory: What internal representations reveal about large language model reasoning","venue":"arXiv (Cornell University)","work_id":"8909b172-e63d-4aab-bdfe-f858c8110344","year":2026},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:1982df419d557b526b2f500a6fc6481cc7bffdc1b4711275567c43043476bd75","observation_id":"a33235fa-7986-4c57-97a8-314411b6212d","resolution":{"observed_at":"2026-07-09T21:16:34.250174Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":"1810.04805","doi":"10.1111/jofi.12885","metadata_source":"pith","pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","venue":"cs.CL","work_id":"ed240a10-5b19-406c-baa5-30803f465785","year":2018},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:cacf58bb6012a094649a5d3739c531461d8e26200c37737d12d41450b59ceccc","observation_id":"76cfb491-d7af-41b2-ba00-5cc352ce508a","resolution":{"observed_at":"2026-07-09T21:16:34.224321Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2511.03060","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.227757Z","title":"The curved spacetime of transformer architectures.arXiv preprint arXiv:2511.03060","venue":null,"work_id":"96160ee9-e8c8-40fa-a4b9-bf3fd514b840","year":2025},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:25195414adffc7217b1012fa51cd1348582d7b7c3e3ae58a29ea1889caa81c4b","observation_id":"1a34f11e-34b0-4cb4-862e-21006865912c","resolution":{"observed_at":"2026-07-09T21:16:34.229150Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01950","last_updated":"2025-05-22T18:09:32Z","snapshot_observed_at":"2026-08-18T00:54:40.395945Z","submitted_at":"2024-10-02T18:52:12Z","title":"Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows","version":2},"cited_work":{"arxiv_id":"2410.01950","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.01950","snapshot_observed_at":"2026-07-09T21:16:34.206557Z","title":"Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows","venue":"cs.LG","work_id":"94b9dd17-b52f-4466-b6d4-0dcfb0da6683","year":2024},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2410.01950","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:81bcec4eb13b0b49fe949c1f6a564a5ed6fb9ab15cd5c8e17b56aabff3d3bd49","observation_id":"260803d0-da20-4df3-8ab8-fbb852a48b04","resolution":{"observed_at":"2026-07-09T21:16:34.207916Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.00512","last_updated":"2019-09-02T01:51:46Z","snapshot_observed_at":"2026-08-20T14:57:46.747447Z","submitted_at":"2019-09-02T01:51:46Z","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","version":1},"cited_work":{"arxiv_id":"1909.00512","doi":"10.48550/arxiv.1909.00512","metadata_source":"pith","pith_arxiv_id":"1909.00512","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"How contextual are contextualized word representations? comparing the geometry of bert, elmo, and gpt-2 embeddings","venue":"cs.CL","work_id":"f9f9736d-1065-4243-8be7-6f9238114277","year":2019},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1909.00512","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:b25440989e869274e12edf3d4bbdaf7c59baa3434dd41f9768c5ea8f7fa7c0f2","observation_id":"de84d82b-c8c8-4a9e-b99f-438956dbf017","resolution":{"observed_at":"2026-07-09T21:16:34.196869Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2004.831793","doi":"10.1109/tmi.2004.831793","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"IEEE Transactions on Medical Imaging , author =","venue":"IEEE Transactions on Medical Imaging","work_id":"356cdbc7-1c8b-4562-a4f7-79a3f13c0c60","year":2004},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:431f4757f8b5b2f3381e22f9bdc209e864cf6ff52e6aa442ba963dca33a3fb38","observation_id":"8c258d11-52d4-4b9d-a797-bb2dd41771b2","resolution":{"observed_at":"2026-07-09T21:16:34.062133Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-07-14T22:50:49.134756+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T22:50:49.134756+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-662-05296-9_31","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":null,"work_id":"0c7c3147-4ddb-454a-9c9a-fd9fdc8ff3f2","year":2000},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:64a5697fc0723937ede8d94d9580c785bd12e4a96e96dece2d61bd731c8a05f4","observation_id":"f1a21f09-0011-4aa7-8ff6-2f70b0b45714","resolution":{"observed_at":"2026-07-09T21:16:34.054029Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.patrec.2010.08.005","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"Pattern Recognition Letters","work_id":"1cc6766b-2179-42c2-a2f1-45faac8b6902","year":2011},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:20bd5b1a3d8eda575dc2c3d5f6022dddbf814912dc3c664184406b77cf14181f","observation_id":"bf7aaec5-bc5f-409c-9dfa-7144f5f9125d","resolution":{"observed_at":"2026-07-09T21:16:34.065937Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02207","last_updated":"2024-03-04T18:25:29Z","snapshot_observed_at":"2026-08-16T14:55:25.223461Z","submitted_at":"2023-10-03T17:06:52Z","title":"Language Models Represent Space and Time","version":3},"cited_work":{"arxiv_id":"2310.02207","doi":"10.48550/arxiv.2310.02207","metadata_source":"pith","pith_arxiv_id":"2310.02207","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Language models represent space and time","venue":"cs.LG","work_id":"5c3d9000-de88-448f-bcdc-4ac78faeb394","year":2023},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2310.02207","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:0c72f1162a8b2a41e4e2559a7ddc58f67f370dcc0e089ef53935146d57e085a4","observation_id":"e29bda07-219b-4f20-a684-77c668283a55","resolution":{"observed_at":"2026-07-09T21:16:34.188806Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.534100Z","title":null,"venue":null,"work_id":"9b6a5deb-3ca0-4fad-854f-a26865bab909","year":2017},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:fc32dd9b098e8752d3062868c5665f279a7cce6261b9c3da94307e0840d9da81","observation_id":"1f4176d4-41c5-4314-88ce-ce4181f2368a","resolution":{"observed_at":"2026-07-09T21:16:34.535343Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2025.repl4nlp-1.5","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":null,"work_id":"78bbc56e-e6da-4019-b4ef-e6c2c9a8ae4b","year":2025},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:e5a389c0e796f1bb6c546435801d14561a25b26d3ad68fdad0b80a636fb5277c","observation_id":"6d5c8a33-ede0-4f72-aea6-ee5a355e5a47","resolution":{"observed_at":"2026-07-09T21:16:34.070209Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2506.07405","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.245629Z","title":"Ji.RiemannFormer: A Framework for Attention in Curved Spaces","venue":null,"work_id":"ddf31232-137f-4bab-a9f3-5f891cbfe5f5","year":2025},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:883ab08eb315dae0eaaebd411a697e694f0f5999d376e95933ebdf1cfd0ae412","observation_id":"50293a13-064d-4568-8a86-0ef2b2c4c49a","resolution":{"observed_at":"2026-07-09T21:16:34.247163Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2504.18882","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.197048Z","title":"SPD Matrix Learning for Neuroimaging Analysis: Perspectives, Methods, and Challenges, January 2026","venue":null,"work_id":"17c2e0ec-a983-4f2e-a2e1-56828b4c38e3","year":2024},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:ef383bf6fb510ffb9ddbf75d689a1648f6c2358ebb0c6f702d8f5f49e083c472","observation_id":"88cb7a14-6106-4a43-8403-413a225a4920","resolution":{"observed_at":"2026-07-09T21:16:34.198937Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.02142","last_updated":"2025-03-04T00:19:01Z","snapshot_observed_at":"2026-08-16T12:53:24.099540Z","submitted_at":"2025-03-04T00:19:01Z","title":"Measuring Intrinsic Dimension of Token Embeddings","version":1},"cited_work":{"arxiv_id":"2503.02142","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.02142","snapshot_observed_at":"2026-07-09T21:16:34.240044Z","title":"Measuring Intrinsic Dimension of Token Embeddings","venue":"cs.CL","work_id":"a6b10045-2ab7-4003-8ca3-00855228d585","year":2025},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2503.02142","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:f36ea902af9374d477757aac9e06a58a9d40b825dd05ccecb6113e554d1f0b94","observation_id":"60188531-584e-4dd6-84fd-0b0691c2a0b6","resolution":{"observed_at":"2026-07-09T21:16:34.241389Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.532062Z","title":null,"venue":null,"work_id":"e889df07-05fb-473e-85cd-2018163f1673","year":2022},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:e49367da11b57cfd08faeb7b6565608d5fae867541824cd3c718383ba864176d","observation_id":"b4ed3b9a-a475-44c4-8b6f-941271df7647","resolution":{"observed_at":"2026-07-09T21:16:34.533447Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.07167","last_updated":"2017-06-22T04:37:31Z","snapshot_observed_at":"2026-08-14T20:52:23.985309Z","submitted_at":"2017-06-22T04:37:31Z","title":"Curvature-aware Manifold Learning","version":1},"cited_work":{"arxiv_id":"1706.07167","doi":"10.48550/arxiv.1706.07167","metadata_source":"pith","pith_arxiv_id":"1706.07167","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"Curvature-aware Manifold Learning","venue":"cs.LG","work_id":"8e549411-e23f-4358-8b35-76699ac2c801","year":2017},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1706.07167","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:4bd29a37efd05df37b07e53edfe8f814ade4e894ad368f202ff1485777efef5d","observation_id":"11b5aae8-0f35-41f6-a4a7-88f2bb86cd03","resolution":{"observed_at":"2026-07-09T21:16:34.072807Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.00335","last_updated":"2021-07-05T23:47:42Z","snapshot_observed_at":"2026-08-11T09:26:12.950232Z","submitted_at":"2020-02-29T19:49:38Z","title":"Differentiating through the Fr\\'echet Mean","version":4},"cited_work":{"arxiv_id":"2003.00335","doi":null,"metadata_source":"pith","pith_arxiv_id":"2003.00335","snapshot_observed_at":"2026-07-09T21:16:34.217145Z","title":"Differentiating through the Fr\\'echet Mean","venue":"stat.ML","work_id":"fee777c6-a485-4ee4-816d-30000b1518f9","year":2020},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2003.00335","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:b06fda9264bdd251741bf15f58f9d9c8c70605891d27b214fdd508de203eb40b","observation_id":"c6b4c511-dfd7-4269-9bd6-057f399c9808","resolution":{"observed_at":"2026-07-09T21:16:34.218375Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.21107","last_updated":"2025-07-08T23:05:00Z","snapshot_observed_at":"2026-08-06T19:01:44.548147Z","submitted_at":"2025-07-08T23:05:00Z","title":"Curved Inference: Concern-Sensitive Geometry in Large Language Model Residual Streams","version":1},"cited_work":{"arxiv_id":"2507.21107","doi":null,"metadata_source":"pith","pith_arxiv_id":"2507.21107","snapshot_observed_at":"2026-07-09T21:16:34.232764Z","title":"Curved Inference: Concern-Sensitive Geometry in Large Language Model Residual Streams","venue":"cs.CL","work_id":"64413f45-9f88-4a8f-a8e8-ae09c227ce9e","year":2025},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2507.21107","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:27a84c11dfe128353d77f1c17f4fd4afd8d2cc59020c351eb104910ca7733fc9","observation_id":"f1b45a3f-fdcf-4837-897b-ae70950f190c","resolution":{"observed_at":"2026-07-09T21:16:34.234109Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.jneumeth.2007.03.024","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Journal of Neuroscience Methods164(1), 177–190 (2007)","venue":"Journal of Neuroscience Methods","work_id":"967e986a-ab30-4ca4-8cf9-b9ee05442f32","year":2007},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:b1cbaab4f15a83dba8e07b92d4e6d12be9e8b6c03f9f94bb964643f2f873109e","observation_id":"5aec7729-7c9f-41a0-8594-06077d22fda1","resolution":{"observed_at":"2026-07-09T21:16:34.045241Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06824","last_updated":"2024-08-19T01:18:41Z","snapshot_observed_at":"2026-08-17T14:45:35.765424Z","submitted_at":"2023-10-10T17:54:39Z","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","version":3},"cited_work":{"arxiv_id":"2310.06824","doi":"10.18653/v1/2025.findings-acl.38","metadata_source":"pith","pith_arxiv_id":"2310.06824","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","venue":"cs.AI","work_id":"400e017f-8643-4166-b6da-a75d4446da80","year":2023},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2310.06824","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:b2de53fabbf4c9adb93812ca5e0280ef1269050477f5374312e32d4a49e312f2","observation_id":"55c04578-b327-4712-bd2a-8d6b02e43576","resolution":{"observed_at":"2026-07-09T21:16:34.238646Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.03426","last_updated":"2020-09-18T01:56:41Z","snapshot_observed_at":"2026-08-02T15:32:07.466568Z","submitted_at":"2018-02-09T19:39:33Z","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","version":3},"cited_work":{"arxiv_id":"1802.03426","doi":"10.1037/adb0001138","metadata_source":"pith","pith_arxiv_id":"1802.03426","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","venue":"stat.ML","work_id":"54c15172-6304-4008-a3b6-c4cc0803c054","year":2018},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1802.03426","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:c601d5546b3179dad3bdc5fceeaf9be744f0a64f21de3c0b58703b7dc9683ac6","observation_id":"e93ec14d-e46c-4568-8262-3226c23b2479","resolution":{"observed_at":"2026-07-09T21:16:34.249155Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-05-25T15:24:07.856203+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T15:24:07.856203+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2510.04933","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.224338Z","title":"The geometry of truth: Layer-wise semantic dynamics for hallucination detection in large language models","venue":null,"work_id":"1d9d4906-fdb1-45f5-9be7-08f511ccb958","year":2025},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:8424f9a49cca3516f9de19d0a7388afc9c9193013c0fd261faaeb2fd7cf17b9f","observation_id":"67600567-77c1-44c0-bc68-02de0abcf913","resolution":{"observed_at":"2026-07-09T21:16:34.225930Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.530293Z","title":null,"venue":null,"work_id":"0c73c97f-b833-4d1d-876b-618327141492","year":2008},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:adf071366dc553070afb410b767c3ba53d8eef3f7aa713ab2d4bb902ec9b6790","observation_id":"6c60c721-0705-4db8-a501-91293b38474a","resolution":{"observed_at":"2026-07-09T21:16:34.531521Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.08039","last_updated":"2017-05-26T17:40:55Z","snapshot_observed_at":"2026-08-14T20:58:55.084884Z","submitted_at":"2017-05-22T23:14:36Z","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","version":2},"cited_work":{"arxiv_id":"1705.08039","doi":"10.48550/arxiv.1705.08039","metadata_source":"pith","pith_arxiv_id":"1705.08039","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","venue":"cs.AI","work_id":"341e74b0-2817-4f13-ac9b-341f36428729","year":2017},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1705.08039","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:1e92159965a1578cb76864d8406975cd0321db56c736060099dad2087b020f8e","observation_id":"0a4112f3-4bb3-48f3-a721-9ede198bd35a","resolution":{"observed_at":"2026-07-09T21:16:34.228192Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.03417","last_updated":"2018-07-08T13:06:31Z","snapshot_observed_at":"2026-08-14T19:05:47.790624Z","submitted_at":"2018-06-09T05:56:50Z","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","version":2},"cited_work":{"arxiv_id":"1806.03417","doi":"10.48550/arxiv.1806.03417","metadata_source":"pith","pith_arxiv_id":"1806.03417","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","venue":"cs.AI","work_id":"c46d0aad-489b-4122-822a-e179474bd4aa","year":2018},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1806.03417","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:4a3c014b2984c6a158ca29e3c2d7b151bc6402a9fbec584cbe2a6ed364b43597","observation_id":"d14198f5-2ad5-473d-87b3-f071d6e3f489","resolution":{"observed_at":"2026-07-09T21:16:34.179818Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.01653","last_updated":"2021-09-03T17:56:40Z","snapshot_observed_at":"2026-08-20T03:55:17.161754Z","submitted_at":"2021-09-03T17:56:40Z","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","version":1},"cited_work":{"arxiv_id":"2109.01653","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.01653","snapshot_observed_at":"2026-07-09T21:16:34.258664Z","title":"Qwen Team","venue":"cs.CL","work_id":"6556e532-be63-4484-87af-6836773da651","year":2021},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2109.01653","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:302f66154a6c98436661abf9282df40c8c9f4744d01fdac4e88b79d650fba12c","observation_id":"f944276b-3715-4d0f-84be-f0728fb436db","resolution":{"observed_at":"2026-07-09T21:16:34.260088Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01506","last_updated":"2025-02-18T02:23:45Z","snapshot_observed_at":"2026-08-17T00:18:50.876112Z","submitted_at":"2024-06-03T16:34:01Z","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","version":3},"cited_work":{"arxiv_id":"2406.01506","doi":"10.48550/arxiv.2406.01506","metadata_source":"pith","pith_arxiv_id":"2406.01506","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2406.01506 , year=","venue":"cs.CL","work_id":"50fe71d6-8df7-4aba-81c3-41f35bcc40c7","year":2024},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2406.01506","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:a6eba49d2ef92e5ae6da98b4d05784301de372bb37d1145ce47ca80ee7e8ef80","observation_id":"9c70fb15-4fa5-4b3e-80d2-434c26cbdddc","resolution":{"observed_at":"2026-07-09T21:16:34.223200Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.03658","last_updated":"2024-07-17T22:24:27Z","snapshot_observed_at":"2026-08-16T23:25:38.049210Z","submitted_at":"2023-11-07T01:59:11Z","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","version":2},"cited_work":{"arxiv_id":"2311.03658","doi":"10.48550/arxiv.2311.03658","metadata_source":"pith","pith_arxiv_id":"2311.03658","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","venue":"cs.CL","work_id":"a7b44adc-f2c2-4420-a27d-8ade97dd3b75","year":2023},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2311.03658","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:4cc97efc603022df30dcd7964702d3f9be7b7b6dd5489ef5d2c6418526ae86ca","observation_id":"e7a474e3-88ee-4278-bf52-d259e6c03d86","resolution":{"observed_at":"2026-07-09T21:16:34.244246Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-10T18:38:16.194264+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-10T18:38:16.194264+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.526135Z","title":"Pedregosa, G","venue":null,"work_id":"91bfb072-a975-4964-902e-4da15d38bd17","year":2011},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:95fe75c6ed3d72a5ded228e227c10829e77ed9bc51e6e13409b260500a540ca5","observation_id":"3acbc428-8705-49df-828b-0fdb7b90b9ff","resolution":{"observed_at":"2026-07-09T21:16:34.527771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.528454Z","title":null,"venue":null,"work_id":"4373b7bd-6f32-4c30-939f-1d31d30c36b2","year":2026},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:12d37186196d5ceaed9cd2fc113e526ac3875282f37deb0364e9217707f9e016","observation_id":"04187d1f-2cdd-44ae-b5ec-efc101a1d5e6","resolution":{"observed_at":"2026-07-09T21:16:34.529719Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10084","last_updated":"2019-08-27T08:50:17Z","snapshot_observed_at":"2026-08-14T05:02:11.716316Z","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","version":1},"cited_work":{"arxiv_id":"1908.10084","doi":"10.48550/arxiv.1908.10084","metadata_source":"pith","pith_arxiv_id":"1908.10084","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","venue":"cs.CL","work_id":"27adfcc9-2a67-43d6-a844-78309012411f","year":2019},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1908.10084","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:236a6928d54c39fe28cc3b82034e38619c4614f1b201ac46a0f387abb40ebee0","observation_id":"b7a29808-b516-4fff-99a7-6920c1e5ecd2","resolution":{"observed_at":"2026-07-09T21:16:34.164121Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-07-12T06:19:15.148899+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T06:19:15.148899+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2504.01002","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T21:16:34.220548Z","title":"Token embeddings violate the manifold hypothesis.arXiv preprint arXiv:2504.01002","venue":null,"work_id":"7c413345-7635-4ff5-a560-3b9b49b1a459","year":2025},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:c0f6bacbba485f981cde2298623060aa0c20254fd0422fd2bba5bde827409e44","observation_id":"887e0efa-e7ad-4f4c-b316-817dfb36d381","resolution":{"observed_at":"2026-07-09T21:16:34.221949Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.12327","last_updated":"2020-11-09T15:33:50Z","snapshot_observed_at":"2026-08-20T02:40:28.570724Z","submitted_at":"2020-02-27T18:46:42Z","title":"A Primer in BERTology: What we know about how BERT works","version":3},"cited_work":{"arxiv_id":"2002.12327","doi":"10.48550/arxiv.2002.12327","metadata_source":"pith","pith_arxiv_id":"2002.12327","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"A primer in BERTology: What we know about how BERT works.arXiv [cs.CL]","venue":"cs.CL","work_id":"76933c5a-8e0c-4e19-94e1-e5574965f411","year":2020},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2002.12327","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:b449598ac8a729d1883d8f9740cb616faae6f48bba2c85894c5dba75a8cc4fa3","observation_id":"6b77cb11-b8b3-42fa-a8a1-a7a449e2cb11","resolution":{"observed_at":"2026-07-09T21:16:34.220963Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03329","last_updated":"2018-04-24T04:11:36Z","snapshot_observed_at":"2026-08-14T19:27:36.936105Z","submitted_at":"2018-04-10T03:39:16Z","title":"Representation Tradeoffs for Hyperbolic Embeddings","version":2},"cited_work":{"arxiv_id":"1804.03329","doi":null,"metadata_source":"pith","pith_arxiv_id":"1804.03329","snapshot_observed_at":"2026-07-09T21:16:34.235323Z","title":"Representation Tradeoffs for Hyperbolic Embeddings , url =","venue":"cs.LG","work_id":"30576a7c-869a-4ec3-8637-d32db4a1cb7a","year":2018},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1804.03329","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:bfe1df10488d2c750430f25702680955547779675c83ad9bda4526934d6a02b3","observation_id":"7e8c3432-5c5b-4068-8a4e-81b8daf6c1a6","resolution":{"observed_at":"2026-07-09T21:16:34.236587Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.05267","last_updated":"2019-08-31T03:10:24Z","snapshot_observed_at":"2026-08-20T12:41:24.489424Z","submitted_at":"2019-08-14T17:47:02Z","title":"Towards Debiasing Fact Verification Models","version":2},"cited_work":{"arxiv_id":"1908.05267","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.05267","snapshot_observed_at":"2026-07-09T21:16:34.210001Z","title":"Towards Debiasing Fact Verification Models","venue":"cs.CL","work_id":"955bf3df-2bed-466f-80c3-320520671347","year":2019},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1908.05267","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:705e2a7d14458fcdeab57a1973397b8a89260fef9abe2a5063213051a26ee8d0","observation_id":"76231bdd-10f1-4cc7-85e8-e9da0aafcdc0","resolution":{"observed_at":"2026-07-09T21:16:34.211092Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.acha.2006.03.004","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"From graph to manifold Laplacian: the convergence rate.Applied and Computa- tional Harmonic Analysis, 21(1):128–134","venue":"Applied and Computational Harmonic Analysis","work_id":"50c7cef7-8b38-4822-9977-bc577641f5c5","year":2006},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:5db325d3d651414eb05d456e44d215776ef17bb5cb149d1551422b2913a1e038","observation_id":"d0e421b2-0cc2-45a0-a560-832964ee3d27","resolution":{"observed_at":"2026-07-09T21:16:34.050617Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-07-13T11:19:44.952732+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-13T11:19:44.952732+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2605.05026","last_updated":"2026-05-06T15:22:52Z","snapshot_observed_at":"2026-08-12T12:23:14.075440Z","submitted_at":"2026-05-06T15:22:52Z","title":"Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models","version":1},"cited_work":{"arxiv_id":"2605.05026","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.05026","snapshot_observed_at":"2026-07-09T21:16:34.212100Z","title":"Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models","venue":"cs.CV","work_id":"79e24b9a-f7ca-4430-9db9-1c85b7df1459","year":2026},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2605.05026","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:b63c2f9c412753a06a7125d27a92a863a28c4e902391c18d55255168247740fd","observation_id":"319461e8-2a1a-429a-8c8e-c66154322a08","resolution":{"observed_at":"2026-07-09T21:16:34.213323Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.04373","last_updated":"2025-06-10T17:05:41Z","snapshot_observed_at":"2026-08-15T18:19:39.321184Z","submitted_at":"2025-06-04T18:42:57Z","title":"Mechanistic Decomposition of Sentence Representations","version":2},"cited_work":{"arxiv_id":"2506.04373","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.04373","snapshot_observed_at":"2026-07-09T21:16:34.251295Z","title":"Mechanistic Decomposition of Sentence Representations","venue":"cs.CL","work_id":"d9488445-dbf9-4adc-9614-5bd8ca44d28b","year":2025},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2506.04373","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:bcd7c0a1abdc6a61809b1f68ee6c70e3d873151d524c410073a4d203d175297e","observation_id":"c51e3263-944c-4cd8-969a-4505b4a41f12","resolution":{"observed_at":"2026-07-09T21:16:34.252488Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05355","last_updated":"2018-12-18T10:58:20Z","snapshot_observed_at":"2026-08-20T03:41:32.061428Z","submitted_at":"2018-03-14T15:30:37Z","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","version":3},"cited_work":{"arxiv_id":"1803.05355","doi":"10.18653/v1/n18-1074","metadata_source":"pith","pith_arxiv_id":"1803.05355","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","venue":"cs.CL","work_id":"b696f75f-e5ad-4555-9c12-e292e77c388f","year":2018},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1803.05355","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:72750dcba3bbb18f736ab6d03a8bf2e08ddce0e411a1cc986afdf30d1bcf2f8b","observation_id":"e470a26e-a10a-4b4d-98e9-ee44bd8b9a1a","resolution":{"observed_at":"2026-07-09T21:16:34.244501Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-17T23:38:13.224522+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-17T23:38:13.224522+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.00294","last_updated":"2023-10-30T16:11:05Z","snapshot_observed_at":"2026-08-19T23:06:37.376527Z","submitted_at":"2023-02-01T07:50:26Z","title":"The geometry of hidden representations of large transformer models","version":2},"cited_work":{"arxiv_id":"2302.00294","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.00294","snapshot_observed_at":"2026-07-10T09:26:59.664193Z","title":"The geometry of hidden repre- sentations of large transformer models.arXiv preprint arXiv:2302.00294","venue":"cs.LG","work_id":"a116fac9-c056-47d9-95d5-567b1ced3175","year":2023},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/2302.00294","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:348a463af1c785906c1cfa57337ff746cca8720fff3df2140433c273b85aa50b","observation_id":"e0c7e869-80a5-4c0a-b917-84c11321def0","resolution":{"observed_at":"2026-07-09T21:16:34.195918Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/w18-5446","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Proceedings of the 2018","venue":null,"work_id":"24f74631-3b99-4e7e-ab15-b562e791542e","year":2018},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:038f62481f82f653f119b987154c024b3c5054e4e29a3e1b1f0b81fc8dd77e4c","observation_id":"9138b701-1159-4669-b278-eb44e32578b0","resolution":{"observed_at":"2026-07-09T21:16:34.064030Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-10T21:38:27.565725+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-10T21:38:27.565725+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.12471","last_updated":"2019-10-01T18:41:05Z","snapshot_observed_at":"2026-08-14T19:09:01.924152Z","submitted_at":"2018-05-31T13:52:06Z","title":"Neural Network Acceptability Judgments","version":3},"cited_work":{"arxiv_id":"1805.12471","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.12471","snapshot_observed_at":"2026-07-09T21:16:34.237758Z","title":"Neural Network Ac- ceptability Judgments","venue":"cs.CL","work_id":"ee6536e2-986a-4e85-877b-cd6cf6b9219e","year":2018},"citing_paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-07-09T21:11:02.461038Z"},"links":{"cited_paper":"/paper/1805.12471","citing_paper":"/paper/2607.07047"},"observation_digest":"sha256:d5c5cf42c3f6e202b816151ad5f19ede91686e16bbbd2f0d8deee3e610ef7ff8","observation_id":"3a8cd40f-d486-4e07-9006-bd4e5cf6934e","resolution":{"observed_at":"2026-07-09T21:16:34.238910Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2607.07047","last_updated":"2026-07-08T06:23:46Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-17T11:48:36.105240Z","submitted_at":"2026-07-08T06:23:46Z","title":"Riemannian Geometry for Pre-trained Language Model Embeddings"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":6,"verified_exact":48,"verified_fuzzy":1},"total_outbound_references":56},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 0 inbound Pith citation observations for arXiv:2607.07047."}