{"as_of":"2026-08-10T14:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:04dea81979fad7f1e7070b131757f6228d5ef92257f6a63252140d1ac27b9df9","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T12:35:53.136160Z","state":"measured"},{"denominator":49,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":49,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2607.24892/citation-record","integrity":"/paper/2607.24892/integrity","json":"/paper/2607.24892/citation-record.json","paper":"/paper/2607.24892"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T12:35:49.043980Z","title":"Gonzalez and Ion Stoica , booktitle=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.043980Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:a55c5cc2851bdaf7314d092a2ae9a7933ca7b324b6a6cd5e9f189f8fe0348df5","observation_id":"c34da049-e8b3-4503-a0ed-fd0d9f43784c","resolution":{"observed_at":"2026-07-31T12:35:49.043980Z","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":"2026-07-31T12:35:49.122927Z","title":"CoRR , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.122927Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:d3f70e3567ac2b1036e62ea6aa63a52ff6158ec469011e56db005def8abb34f8","observation_id":"db7451ef-d663-4cb7-8a43-c3bc1b2bfa67","resolution":{"observed_at":"2026-07-31T12:35:49.122927Z","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":"2026-07-31T12:35:49.208895Z","title":"The Twelfth International Conference on Learning Representations , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.208895Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:9462a06b8f1d8e04254bdbaedcdc07dc4a2502b8dfa4425fd55c3ba3db8734f3","observation_id":"945442c2-862c-47a3-a183-5decfdf87f08","resolution":{"observed_at":"2026-07-31T12:35:49.208895Z","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":"2026-07-31T12:35:49.284241Z","title":"Transactions on Machine Learning Research , issn=","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.284241Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:220167963ab3482295131abd61e749904856a40924ba2b83af590930a59f7e09","observation_id":"e824b892-1826-4adb-9f1b-07d9bf1248b2","resolution":{"observed_at":"2026-07-31T12:35:49.284241Z","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":"2026-07-31T12:35:49.370171Z","title":"Proceedings of the 41st International Conference on Machine Learning , pages =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.370171Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:032c699cd56f413f540d7bfdb5f8ce579e6f956c31d88b9f6c2c1677612040bf","observation_id":"3d809b97-4f5b-41d0-8726-1115a6bba4d0","resolution":{"observed_at":"2026-07-31T12:35:49.370171Z","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":"2026-07-31T12:35:49.446469Z","title":"Proceedings of the 41st International Conference on Machine Learning , pages =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.446469Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:552d33cf13cbee421c795a755a40fd1bed4bcf4da0321f5ff4da575e06ce63b9","observation_id":"152c99ab-9cf9-44f6-9134-12e747b2ee42","resolution":{"observed_at":"2026-07-31T12:35:49.446469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08278","last_updated":"2024-02-08T05:49:04Z","snapshot_observed_at":"2026-08-07T22:30:30.596133Z","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":"2026-07-31T12:35:49.533118Z","title":"arXiv preprint arXiv:2310.08278 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.533118Z"},"links":{"cited_paper":"/paper/2310.08278","citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:2626c71e18f34c44f1edd90db35da6c034ebece073ac18bc9be539b216f366a4","observation_id":"a62ce960-f5ab-4534-8266-1e8adc6372a8","resolution":{"observed_at":"2026-07-31T12:35:49.533118Z","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":"2026-07-31T12:35:49.610848Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.610848Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:a46dfd0f5625bf755faa5aadb324b549a83d0baba1033a80c7fa1dbb15ab9322","observation_id":"152187a1-a688-40cc-8860-5674aeed0e9d","resolution":{"observed_at":"2026-07-31T12:35:49.610848Z","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":"2026-07-31T12:35:49.678603Z","title":"Attention is All you Need , url =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.678603Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:eb2d03e677c7b626fcf3654d7aed501dc3297eed19735253927db04ce8a227e6","observation_id":"12fa130d-3f4d-41c6-b7ae-381f454974fc","resolution":{"observed_at":"2026-07-31T12:35:49.678603Z","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":"2026-07-31T12:35:49.773984Z","title":"Forty-second International Conference on Machine Learning , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.773984Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:45ba86bf4d9e91997791ab37ff264b4500014006b353e2da594397e3ef50cd22","observation_id":"00bb9ac3-ee08-46f0-8069-895a55cb2b12","resolution":{"observed_at":"2026-07-31T12:35:49.773984Z","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":"2026-07-31T12:35:49.864513Z","title":"Sasanur and Megha Sharma and Jiaming Cui and Qingsong Wen and Chao Zhang and B","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.864513Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:d6b433b3b3f0b13b551da809c1ca190e03c3e1b5261ae6272681bdc0d9b2fd89","observation_id":"0823e89a-80eb-4b0d-9ec9-94f07ddd154d","resolution":{"observed_at":"2026-07-31T12:35:49.864513Z","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":"2026-07-31T12:35:49.950395Z","title":"Zhang and Xiaoming Shi and Pin-Yu Chen and Yuxuan Liang and Yuan-Fang Li and Shirui Pan and Qingsong Wen , booktitle=","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:49.950395Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:5126a18f3a11e70b6f1387d5855234fd1d6e863badd78b34365fcbd872f1d6ce","observation_id":"be3cdc81-1a4a-4a5f-870f-b1c89049dc31","resolution":{"observed_at":"2026-07-31T12:35:49.950395Z","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":"2026-07-31T12:35:50.041265Z","title":"Thirty-seventh Conference on Neural Information Processing Systems , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.041265Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:14a873e5384178a5c919a137aa7a413ccb7361cfdc2dd9cbfd9003246550ea92","observation_id":"ad09d009-deb5-4106-a41e-f9c3a93b1f7f","resolution":{"observed_at":"2026-07-31T12:35:50.041265Z","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":"2026-07-31T12:35:50.117762Z","title":"Beyond Na","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.117762Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:030a9b2c17caf9e485f00f0ac25d6bd79a1bb41e87727975f61243edb08614a9","observation_id":"8f21485d-2a6e-4fbc-9eed-a02e93c40e26","resolution":{"observed_at":"2026-07-31T12:35:50.117762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-07-31T12:35:50.205975Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.205975Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:d96052e5a823e05b50709c493777d61ed732a02fcd0426fa7fd274da1b6d96e7","observation_id":"2069853a-adb4-43ac-bf5b-5615ea243ca7","resolution":{"observed_at":"2026-07-31T12:35:50.205975Z","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":"2026-07-31T12:35:50.284568Z","title":"Lillicrap and Fan Hui and Laurent Sifre and George van den Driessche and Thore Graepel and Demis Hassabis , title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.284568Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:0f273d9003986f631731fad67a1fbe6421a81623b4847dd9b3892ef242dbbb55","observation_id":"0ba6f38e-f883-4ada-98af-20686b5120e9","resolution":{"observed_at":"2026-07-31T12:35:50.284568Z","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":"2026-07-31T12:35:50.375766Z","title":"European Conference on Machine Learning , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.375766Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:6de530bb7c2b88798cf79b5b7be48896aef00fd3fb2e01b3f0fcdeaa98e17512","observation_id":"baf6f859-3324-4e49-925c-a45b319e2dc8","resolution":{"observed_at":"2026-07-31T12:35:50.375766Z","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":"2026-07-31T12:35:50.451744Z","title":"Annals of Mathematics and Artificial Intelligence , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.451744Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:6a3114bdc622cba85b4cc2f1b4b0deb56c6158834f247e3664de352277d67dc0","observation_id":"ede454e7-9fac-4bbe-b980-f990aa4370f2","resolution":{"observed_at":"2026-07-31T12:35:50.451744Z","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":"2026-07-31T12:35:50.526495Z","title":"Reasoning with Language Model is Planning with World Model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.526495Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:9660f19899eb714789cb65f632acb1623daa3f6ab1116f5f24c22ee101ad9f29","observation_id":"8e492b11-550e-4530-862e-5e0aafc3cb42","resolution":{"observed_at":"2026-07-31T12:35:50.526495Z","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":"2026-07-31T12:35:50.619491Z","title":"2023 , isbn =","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.619491Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:509ac1a9944c90d322a04e01d526fb349f252a8837ac742d7aa9b79c34b2097b","observation_id":"46c0aa86-1d7c-4080-8aa8-7e98ab943554","resolution":{"observed_at":"2026-07-31T12:35:50.619491Z","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":"2026-07-31T12:35:50.707889Z","title":"Journal of the American Statistical Association , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.707889Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:60b6d04df34916b344195506dc084f69fde9bc4f21a45afdfb07b359dab6aee0","observation_id":"7153b1f2-d5ff-437f-8b79-82c35551d23c","resolution":{"observed_at":"2026-07-31T12:35:50.707889Z","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":"2026-07-31T12:35:50.834608Z","title":"International Journal of Forecasting , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.834608Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:de5dce42f3c1f0728c212ac3471bb86731a03f3aa24ed68bc1b9d7df00b719ca","observation_id":"0ea22fcd-bc2e-49ca-9721-c735009d8cba","resolution":{"observed_at":"2026-07-31T12:35:50.834608Z","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":"2026-07-31T12:35:50.915872Z","title":"Matheson and Robert L","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:50.915872Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:b87d6dd9565117f47d6c1fe791312df6858959c66090c3a91e68a4995ad2c29f","observation_id":"37bee400-8546-48c6-826a-6b9253a699f6","resolution":{"observed_at":"2026-07-31T12:35:50.915872Z","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":"2026-07-31T12:35:51.006527Z","title":"The Eleventh International Conference on Learning Representations , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.006527Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:dec9a5ac1fb49ae481e6e923ce6ccfd9ddc03a324f89833d2592f62b2ae3e6f9","observation_id":"6e54fdb6-f414-4578-bffa-5f1bd12b1bf2","resolution":{"observed_at":"2026-07-31T12:35:51.006527Z","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":"2026-07-31T12:35:51.090061Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.090061Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:d891f77288016ba0fbd2fb9f4144e442a95da62a6465f527c2bf736eb9a857a8","observation_id":"8db60513-ba48-41e8-9363-53491949dc07","resolution":{"observed_at":"2026-07-31T12:35:51.090061Z","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":"2026-07-31T12:35:51.175852Z","title":"Nexus : An Agentic Framework for Time Series Forecasting , journal =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.175852Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:2187f3a05a2e1bf300ce046c8bd57e6d258001dc36f3bd2007a8aad0333b8359","observation_id":"4cf1d1de-829b-4b20-8ff6-6a35e8bb78a8","resolution":{"observed_at":"2026-07-31T12:35:51.175852Z","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":"2026-07-31T12:35:51.252555Z","title":"CoRR , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.252555Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:4ac2a345e4f1a5244b33ed0a28439e05075e1e9207ace2c0db22da98b7b6bb7d","observation_id":"760d6a8e-2cec-49d2-8a29-6959a952f103","resolution":{"observed_at":"2026-07-31T12:35:51.252555Z","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":"2026-07-31T12:35:51.335586Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.335586Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:01add0261411da3bd8055d55d488732b91dee66ab17595e216c0d33454ed607b","observation_id":"7749582e-4597-4b46-a2d1-84646bad3a79","resolution":{"observed_at":"2026-07-31T12:35:51.335586Z","resolver_source":null,"status":"parse_uncertain"},"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":"2026-07-31T12:35:51.394170Z","title":"One Fits All: Power General Time Series Analysis by Pretrained","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.394170Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:5b20211c5b53976b6d3bf6a5d88890369a169509c297b01016e52d218023e8be","observation_id":"bc0e9071-b105-4601-be4a-fe42ff54afbc","resolution":{"observed_at":"2026-07-31T12:35:51.394170Z","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":"2026-07-31T12:35:51.452166Z","title":", title =","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.452166Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:3891386a1f8d44bf4d9751796c8e6d991000f75bb9ca36e3090eed29ff664be6","observation_id":"77714e61-0d12-4343-b2ed-0bea322606a9","resolution":{"observed_at":"2026-07-31T12:35:51.452166Z","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":"2026-07-31T12:35:51.528648Z","title":"International Conference on Algorithmic Learning Theory , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.528648Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:099de0433e8813e4ed05e4803739f2fdd1c58b140080e328388629f1252f6c99","observation_id":"45f92cf5-0ffd-47a9-b402-4a4d98afd4c0","resolution":{"observed_at":"2026-07-31T12:35:51.528648Z","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":"2026-07-31T12:35:51.653196Z","title":"Selective Classification for Deep Neural Networks , url =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.653196Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:aa29ccec64a1f91e303958af4eb627e75ca056875915175cb863d800e3085c29","observation_id":"096a69aa-1587-4a62-9fb2-1a49427c3f9d","resolution":{"observed_at":"2026-07-31T12:35:51.653196Z","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":"2026-07-31T12:35:51.745062Z","title":"Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer , url =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.745062Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:4f213d4c7b9336811714f54a5f01f23526599a19d6f173bb812aa968e0ef45f6","observation_id":"71f51e40-9edb-486d-a732-467adb66a02d","resolution":{"observed_at":"2026-07-31T12:35:51.745062Z","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":"2026-07-31T12:35:51.822333Z","title":"Proceedings of the 37th International Conference on Machine Learning , pages =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.822333Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:51cbe98f499909d56178e6680a1e209fb18890f79ce47567df1dc626916c2ee6","observation_id":"e0a234ae-db92-43cc-a198-4f3f769f3006","resolution":{"observed_at":"2026-07-31T12:35:51.822333Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.findings-emnlp.201","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Language Models Still Struggle to Zero-shot Reason about Time Series","venue":null,"work_id":"377df975-0de1-4c9b-a7ab-4d6f329629ef","year":2024},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.902801Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:f6d228582cae0d69071e92c45267c5d56222e73e0c40d50efba6338d4e83dfcc","observation_id":"5e438b86-eafc-47c6-9df0-99f83bb638b5","resolution":{"observed_at":"2026-07-31T12:40:57.101901Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-31T12:35:51.999641Z","title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:51.999641Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:8c05bc2b5cbf2d89b5f2f8db87538563a190c7c93a3666ac5266a41157bfbbde","observation_id":"b2a93de5-044d-4a81-a3d9-dcc4b3ba9cc7","resolution":{"observed_at":"2026-07-31T12:35:51.999641Z","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":"2026-07-31T12:35:52.085591Z","title":"The Fourteenth International Conference on Learning Representations , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.085591Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:ca3763a102212312484de64f1cb6703aaa8d9657affdf2d457f03ee6ffc814f9","observation_id":"6892a0af-601d-44ed-8adc-23cabba1f658","resolution":{"observed_at":"2026-07-31T12:35:52.085591Z","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":"2026-07-31T12:35:52.140748Z","title":"The 29th International Conference on Artificial Intelligence and Statistics , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.140748Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:d04ae17d734bef16e75e4983443f8e2338cf30e04dfab407f01a4b1574f7421c","observation_id":"999c582f-8157-41dd-b559-bd016eaf5074","resolution":{"observed_at":"2026-07-31T12:35:52.140748Z","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":"2026-07-31T12:35:52.230734Z","title":"Lillicrap and Karen Simonyan and Demis Hassabis , title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.230734Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:7cdb7906e543b87343526f63938abb1cf5091d177bee4fdeb553d98b95bea126","observation_id":"c5c1d82f-8a27-445a-bf65-7c6effed2106","resolution":{"observed_at":"2026-07-31T12:35:52.230734Z","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":"2026-07-31T12:35:52.318500Z","title":"Thirty-seventh Conference on Neural Information Processing Systems , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.318500Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:f207be79572d6ce1f736d81e41b686e28e566aed93d1a19b8c685bdc1320c464","observation_id":"6e061219-24d0-45aa-9b7a-c151b67c57b6","resolution":{"observed_at":"2026-07-31T12:35:52.318500Z","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":"2026-07-31T12:35:52.407112Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.407112Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:6a7a2ab9cf088549982ce77dca3019f110d25df2b14b39f95364236afbd9db2f","observation_id":"c749fa71-9a39-4bae-9ae5-dcd6b47f8945","resolution":{"observed_at":"2026-07-31T12:35:52.407112Z","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":"2026-07-31T12:35:52.495588Z","title":"Learning to summarize with human feedback , url =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.495588Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:a202bdc63ceeb241d8a01b81186643f44fc4b3ab1304017e0331931c882b8200","observation_id":"b6158140-2aa6-4ea0-8a1d-77b483d47620","resolution":{"observed_at":"2026-07-31T12:35:52.495588Z","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":"2026-07-31T12:35:52.577877Z","title":"CoRR , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.577877Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:9ff98d6046a88aae6e29dd84e809421f63afe7f420b53bc466f35c733ae78cf7","observation_id":"bed14ce0-3f1c-4b6e-937d-cadc536c3f6c","resolution":{"observed_at":"2026-07-31T12:35:52.577877Z","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":"2026-07-31T12:35:52.684635Z","title":"2026 , eprint=","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.684635Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:a609c5a3af492f84e4ccd65c7c4da4c7f8762ea1cbb3902ec97a49117259b7d0","observation_id":"957c6a32-0260-42b4-b58d-b997d5dc6d97","resolution":{"observed_at":"2026-07-31T12:35:52.684635Z","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":"2026-07-31T12:35:52.728216Z","title":"Estimation of the Continuous Ranked Probability Score with Limited Information and Applications to Ensemble Weather Forecasts , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.728216Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:0fdb60409a86b95aff20253a9fedbfd48c7d7b193f6e94b8db8f4c5609b555f5","observation_id":"d6f1a009-035d-4ded-9821-03bdd4b54554","resolution":{"observed_at":"2026-07-31T12:35:52.728216Z","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":"2026-07-31T12:35:52.896554Z","title":"Evaluating Forecasts for High-Impact Events Using Transformed Kernel Scores , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.896554Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:604f102b04506cc528eef7d1fe1c9319a571d18281cad1bf5d66c5dbccf436fe","observation_id":"98b82fda-2e65-467b-b2e3-71b254e943e6","resolution":{"observed_at":"2026-07-31T12:35:52.896554Z","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":"2026-07-31T12:35:52.984693Z","title":"Aditya Prakash and Abhimanyu Das , title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:52.984693Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:eaacdfbbed449d126cead13d1fea4bf15cf692f76a77aa5890b2b6c94e1ec400","observation_id":"fa9a29a2-f439-4fe8-b71d-2916682f4f62","resolution":{"observed_at":"2026-07-31T12:35:52.984693Z","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":"2026-07-31T12:35:53.075946Z","title":"Proceedings of the 43rd International Conference on Machine Learning , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:53.075946Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:cc770a8009a8bce139e256f73afb23032c7922b5c3f7ba74b9202df88b9ce0ec","observation_id":"d8d6517c-b561-4380-afc0-003e184cf914","resolution":{"observed_at":"2026-07-31T12:35:53.075946Z","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":"2026-07-31T12:35:53.136160Z","title":"Advances in Neural Information Processing Systems , editor=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-07-31T12:35:53.136160Z"},"links":{"citing_paper":"/paper/2607.24892"},"observation_digest":"sha256:2c6b21f6a849395a7f42204fb940606f639cc41653c3e5dce71d9c36d24de026","observation_id":"37dcd0b4-768e-4813-a765-c8acdc872eba","resolution":{"observed_at":"2026-07-31T12:35:53.136160Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.24892","last_updated":"2026-07-27T15:02:40Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T22:31:10.378244Z","submitted_at":"2026-07-27T15:02:40Z","title":"LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":47,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":49},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2607.24892."}