{"as_of":"2026-08-14T14:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:34f89f091a5136d2f7a272363c975e3810dfef8a9a583e806ba76dd85eded2fa","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:09:52.504548Z","state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+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/2505.17135/citation-record","integrity":"/paper/2505.17135/integrity","json":"/paper/2505.17135/citation-record.json","paper":"/paper/2505.17135"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.07815","last_updated":"2024-11-04T17:42:45Z","snapshot_observed_at":"2026-08-14T11:34:28.022352Z","submitted_at":"2024-03-12T16:53:54Z","title":"Chronos: Learning the Language of Time Series","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07815","snapshot_observed_at":"2026-08-07T15:09:51.837623Z","title":"Chronos: Learning the language of time series.arXiv preprint arXiv:2403.07815,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:51.837623Z"},"links":{"cited_paper":"/paper/2403.07815","citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:c34b416b986c39c41c391734f061f6c543b77dcaf551f559cfe6b2aa2ffd5600","observation_id":"e0bc10e2-cc14-4ece-b889-c70b747eeabb","resolution":{"observed_at":"2026-08-07T15:09:51.837623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.07820","last_updated":"2024-08-12T00:43:56Z","snapshot_observed_at":"2026-08-13T05:51:51.719336Z","submitted_at":"2023-10-11T19:01:28Z","title":"Large Language Models Are Zero-Shot Time Series Forecasters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.07820","snapshot_observed_at":"2026-08-07T15:09:52.131991Z","title":"Ming Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu, James Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:52.131991Z"},"links":{"cited_paper":"/paper/2310.07820","citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:fcca1081e7f439ddd6b0ac78f611a9c042419807fe235a4afba51c6202ac0ded","observation_id":"bd321e73-4f1f-4080-8a03-9e661eb963f0","resolution":{"observed_at":"2026-08-07T15:09:52.131991Z","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":"2024.10582","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:09:52.913604Z","title":"Jiaqi Mu and Pramod Viswanath","venue":null,"work_id":"0c019bc1-70cb-4262-b438-70bd2e399ae8","year":2024},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:52.178631Z"},"links":{"citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:5e194cb8c395a035bc190543d66281f0a0beffc13a0d3700feb7b5ded1f24cea","observation_id":"716995c2-1dda-4d4b-9013-2edf51f8e8f3","resolution":{"observed_at":"2026-08-07T15:09:52.985641Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08278","last_updated":"2024-02-08T05:49:04Z","snapshot_observed_at":"2026-08-13T05:50:42.943963Z","submitted_at":"2023-10-12T12:29:32Z","title":"Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08278","snapshot_observed_at":"2026-08-07T15:09:52.227014Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:52.227014Z"},"links":{"cited_paper":"/paper/2310.08278","citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:b28fec66363ece3e5b15fdaa18dea1f63b6a1146e194ccaed801f03da9db14b0","observation_id":"c76d0102-3221-45f7-b6a2-149fa04c746b","resolution":{"observed_at":"2026-08-07T15:09:52.227014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02592","last_updated":"2024-05-22T11:49:59Z","snapshot_observed_at":"2026-08-13T04:27:14.899922Z","submitted_at":"2024-02-04T20:00:45Z","title":"Unified Training of Universal Time Series Forecasting Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.02592","snapshot_observed_at":"2026-08-07T15:09:52.339883Z","title":"org/abs/2402.02592","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:52.339883Z"},"links":{"cited_paper":"/paper/2402.02592","citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:6c5dc12332b926bba282ca5981a2cfadf06670681888e9ef8116c10e8a78c127","observation_id":"e1e42048-78d4-41a2-93a7-d42f057c30cf","resolution":{"observed_at":"2026-08-07T15:09:52.339883Z","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":"2026-08-07T15:09:52.394426Z","title":"doi: 10.1109/MNET.2024.3427313","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:52.394426Z"},"links":{"citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:bcf62f7fc2ffc46a7d38e9e44003e31ed6734c4a5426338daf231d75b7f36313","observation_id":"485a900d-5f30-43e6-8537-f9657e2b5b99","resolution":{"observed_at":"2026-08-07T15:09:52.394426Z","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":"2026-08-07T15:09:53.374492Z","title":null,"venue":null,"work_id":"a85aec10-34e1-4d2e-a624-4974bf2cbd29","year":1996},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:52.449773Z"},"links":{"citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:e98f16aa46f76e62793ef19f09a7783d6c02a1636cd22d03b45859df92fa80bc","observation_id":"f64a7447-6959-403b-9068-83006cbed4e5","resolution":{"observed_at":"2026-08-07T15:09:53.421018Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T15:09:53.222362Z","title":"After performing K-means clustering, each observation p (i.e., one of the J vector representations in V) is assigned to one of C clusters","venue":null,"work_id":"2c6eb44e-81bc-46fe-98d5-855d8ad3e739","year":2024},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":1987,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:52.504548Z"},"links":{"citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:9cbfc642cc7a70a2cab6626f06ef30c21a5818ad0bcf0a3bbaa1b2d1247adf01","observation_id":"c7984bf4-de21-4ad9-b929-172f937c9b15","resolution":{"observed_at":"2026-08-07T15:09:53.284786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T15:09:51.921252Z","title":"doi: 10.1162/tacl_a_00106","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:51.921252Z"},"links":{"citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:c29f4b9bd99b4a37b08439c4d822770c3831a668ae4a901838fc610634729005","observation_id":"8b72ad0f-9538-44c7-87b8-eca973075e96","resolution":{"observed_at":"2026-08-07T15:09:51.921252Z","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":"2026-08-07T15:09:53.512070Z","title":"Gerald Woo, Chenghao Liu, Akshat Kumar, Caiming Xiong, Silvio Savarese, and Doyen Sahoo","venue":null,"work_id":"d7863b4e-dacc-478e-94e8-09cd8c1616db","year":2021},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:52.275295Z"},"links":{"citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:8714489ddc0b5a7661f24267ad0bfcfb50ea62da5d8b08456b21fe62e00de76e","observation_id":"ca6cd2c2-6c76-430f-898b-21ef070d719f","resolution":{"observed_at":"2026-08-07T15:09:53.576214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.01933","last_updated":"2023-11-03T14:17:11Z","snapshot_observed_at":"2026-08-13T05:33:24.921649Z","submitted_at":"2023-11-03T14:17:11Z","title":"ForecastPFN: Synthetically-Trained Zero-Shot Forecasting","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.01933","snapshot_observed_at":"2026-08-07T15:09:51.984783Z","title":"Martin Ester, Hans-Peter Kriegel, Jörg Sander, and Xiaowei Xu","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:51.984783Z"},"links":{"cited_paper":"/paper/2311.01933","citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:4959ecf5d36d17996faf29bdbdf5fdd3bfbaca29ca8f7748ae02fa74e977cbe4","observation_id":"d307a292-d4e8-4b86-8ce0-d11e97b4e2a5","resolution":{"observed_at":"2026-08-07T15:09:51.984783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03589","last_updated":"2024-05-27T23:34:15Z","snapshot_observed_at":"2026-08-13T05:56:47.281396Z","submitted_at":"2023-10-05T15:14:00Z","title":"TimeGPT-1","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03589","snapshot_observed_at":"2026-08-07T15:09:52.058405Z","title":"Timegpt-1.arXiv preprint arXiv:2310.03589,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","version":4},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:52.058405Z"},"links":{"cited_paper":"/paper/2310.03589","citing_paper":"/paper/2505.17135"},"observation_digest":"sha256:673dd536a19d18d5e78fb7d928c4f35584ef9e6ac49451ad1ad9ee8fc4de3062","observation_id":"6d0bac1d-27dc-4e3e-b8b4-0ae36e08de12","resolution":{"observed_at":"2026-08-07T15:09:52.058405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.17135","last_updated":"2025-06-20T21:50:22Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-14T00:13:18.048157Z","submitted_at":"2025-05-22T05:10:34Z","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":2},"total_outbound_references":12},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2505.17135."}