{"as_of":"2026-08-18T20:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f9eff53511c87894f4fef3570db128043d21a4e5e194329c27e92704714d0b9f","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T07:51:15.259452Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T14:34:14.984415Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-15T14:34:15.131489Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"cited_work":{"arxiv_id":"2607.08940","doi":null,"metadata_source":"pith","pith_arxiv_id":"2607.08940","snapshot_observed_at":"2026-08-15T14:34:15.131489Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","venue":"cs.LG","work_id":"36b05462-9075-40aa-85e7-c6a4c00c550c","year":2026},"citing_paper":{"arxiv_id":"2608.06867","last_updated":"2026-08-07T06:46:58Z","snapshot_observed_at":"2026-08-18T09:08:26.674854Z","submitted_at":"2026-08-07T06:46:58Z","title":"LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers","version":1},"reference_index":293,"source":"arxiv_source","source_observed_at":"2026-08-15T14:34:14.984415Z"},"links":{"cited_paper":"/paper/2607.08940","citing_paper":"/paper/2608.06867"},"observation_digest":"sha256:e0773f6c31b75a023a5d835c80878aba253a666ec2a7c0b0b99c92966abec871","observation_id":"6bb4c2ac-6f26-4673-925f-54846524fc96","resolution":{"observed_at":"2026-08-15T14:34:15.138056Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2607.08940/citation-record","integrity":"/paper/2607.08940/integrity","json":"/paper/2607.08940/citation-record.json","paper":"/paper/2607.08940"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.11860","last_updated":"2023-11-16T16:47:05Z","snapshot_observed_at":"2026-08-16T15:31:37.025401Z","submitted_at":"2023-05-19T17:49:25Z","title":"Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.11860","snapshot_observed_at":"2026-08-02T07:51:11.404084Z","title":"Let’s sample step by step: Adaptive- consistency for efficient reasoning and coding with llms.arXiv preprint arXiv:2305.11860,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:11.404084Z"},"links":{"cited_paper":"/paper/2305.11860","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:6de482acf0bc45c1a3c4bb2fa304f4c5f347463b829285edf4ab9d057e540d45","observation_id":"9236b78a-69af-4b58-a81c-2414b1d9caf3","resolution":{"observed_at":"2026-08-02T07:51:11.404084Z","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":"2026-08-02T07:51:15.180148Z","title":"✓ Qwen3-VL-8B(Text+Vision) Ans: (D)— The data shows a clear progression through multiple trend phases","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:15.180148Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:006ba6f937cb6ca340df0216ec7168b2de2926740c2e3efab18051cdad503d12","observation_id":"b8774cf8-e36d-4298-b103-767e4a6cf5e0","resolution":{"observed_at":"2026-08-02T07:51:15.180148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04948","last_updated":"2024-04-02T04:39:08Z","snapshot_observed_at":"2026-08-18T14:31:02.753428Z","submitted_at":"2023-10-08T00:02:25Z","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04948","snapshot_observed_at":"2026-08-02T07:51:11.920174Z","title":"Tempo: Prompt-based generative pre-trained transformer for time series forecasting","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:11.920174Z"},"links":{"cited_paper":"/paper/2310.04948","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:6617568da27e5d6035026e30c3b0c1e445c67341808c96e5937ce53d2a864fa4","observation_id":"bf7f08f0-f680-4a02-b9ac-cf8563d664c9","resolution":{"observed_at":"2026-08-02T07:51:11.920174Z","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":"2026-08-02T07:51:12.013364Z","title":"Mtbench: A multimodal time series benchmark for temporal reasoning and question answering.arXiv preprint arXiv:2503.16858,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:12.013364Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:c57690b65d035cec1f92ec04a676e362f8367234865a8435e6b5b7f422397c68","observation_id":"d94e7079-f9ce-49ff-ad8e-23d8d0ae334d","resolution":{"observed_at":"2026-08-02T07:51:12.013364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.17253","last_updated":"2025-06-06T14:46:28Z","snapshot_observed_at":"2026-08-16T13:22:39.139670Z","submitted_at":"2024-08-30T12:51:55Z","title":"VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.17253","snapshot_observed_at":"2026-08-02T07:51:12.170031Z","title":"Visionts: Visual masked autoencoders are free-lunch zero-shot time series forecasters","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:12.170031Z"},"links":{"cited_paper":"/paper/2408.17253","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:f5618704bc3f565ffbb28dc215a14e23fd067ebe165af2cebccb6c56c500c609","observation_id":"23909df9-a53f-4ef1-ab81-a0061a003ec1","resolution":{"observed_at":"2026-08-02T07:51:12.170031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14618","last_updated":"2024-04-22T23:06:42Z","snapshot_observed_at":"2026-08-16T23:10:32.223527Z","submitted_at":"2024-04-22T23:06:42Z","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14618","snapshot_observed_at":"2026-08-02T07:51:12.437343Z","title":"Hybrid llm: Cost-efficient and quality-aware query routing.arXiv preprint arXiv:2404.14618, 2024a","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:12.437343Z"},"links":{"cited_paper":"/paper/2404.14618","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:9883087e59fa3d07192a26a8b63cadc5efd9ad1305e7d48a66544119cef06699","observation_id":"d8f93125-a4b0-41b5-afd2-83c97395bbed","resolution":{"observed_at":"2026-08-02T07:51:12.437343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03834","last_updated":"2025-03-17T15:08:47Z","snapshot_observed_at":"2026-08-16T23:11:21.187774Z","submitted_at":"2024-10-04T18:02:48Z","title":"GraphRouter: A Graph-based Router for LLM Selections","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.03834","snapshot_observed_at":"2026-08-02T07:51:12.547698Z","title":"Graphrouter: A graph-based router for llm selections.arXiv preprint arXiv:2410.03834,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:12.547698Z"},"links":{"cited_paper":"/paper/2410.03834","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:a0c724cb5079ccb7c9656f915aa3dc30d5d0eaf3dc7e18e1e8cfa1a3214ed26a","observation_id":"5e7b9e10-cf53-478e-9925-80902aea1c1b","resolution":{"observed_at":"2026-08-02T07:51:12.547698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.23626","last_updated":"2026-04-26T09:38:32Z","snapshot_observed_at":"2026-08-14T00:58:36.531615Z","submitted_at":"2026-04-26T09:38:32Z","title":"GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.23626","snapshot_observed_at":"2026-08-02T07:51:12.700912Z","title":"Tao Feng, Haozhen Zhang, Zijie Lei, Peixuan Han, and Jiaxuan You","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:12.700912Z"},"links":{"cited_paper":"/paper/2604.23626","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:fe4b67382d35a300211bb838db4bf914dc602ae8b4e5747cfc9f73c0b94f221a","observation_id":"aaa7683f-f078-425b-b0ea-da31256f1bad","resolution":{"observed_at":"2026-08-02T07:51:12.700912Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.02428","last_updated":"2019-04-25T10:06:09Z","snapshot_observed_at":"2026-08-02T18:54:43.326912Z","submitted_at":"2019-03-06T14:50:02Z","title":"Fast Graph Representation Learning with PyTorch Geometric","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.02428","snapshot_observed_at":"2026-08-02T07:51:12.817955Z","title":"Fast graph representation learning with pytorch geo- metric.arXiv preprint arXiv:1903.02428,","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:12.817955Z"},"links":{"cited_paper":"/paper/1903.02428","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:d1d807dd7569c368733681a1c8666711adc43bc64d5f66a71392bede159162d6","observation_id":"c329a9d8-8bf1-4a1d-a4b4-225a08e85a94","resolution":{"observed_at":"2026-08-02T07:51:12.817955Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.24803","last_updated":"2026-02-24T10:03:33Z","snapshot_observed_at":"2026-07-06T22:31:05.409865Z","submitted_at":"2025-09-29T13:54:34Z","title":"TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.24803","snapshot_observed_at":"2026-08-02T07:51:13.031013Z","title":"Timeomni-1: Incen- tivizing complex reasoning with time series in large language models.arXiv preprint arXiv:2509.24803,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.031013Z"},"links":{"cited_paper":"/paper/2509.24803","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:f0d79c60deb68dd4be4a1ba218807ed26fd38bd1feb2f2cc4579682c1a0806aa","observation_id":"e51b15f6-da45-4615-aae3-555785b151c7","resolution":{"observed_at":"2026-08-02T07:51:13.031013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.17149","last_updated":"2026-06-02T10:31:16Z","snapshot_observed_at":"2026-08-13T08:49:01.655390Z","submitted_at":"2026-02-19T07:50:11Z","title":"TimeOmni-VL: Unified Models for Time Series Understanding and Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.17149","snapshot_observed_at":"2026-08-02T07:51:13.110516Z","title":"Timeomni-vl: Unified models for time series understanding and generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.110516Z"},"links":{"cited_paper":"/paper/2602.17149","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:8ec6e07a163a788faf5c88d0858b496b76dbdbce7d296a6e702ce71e1aea1c0a","observation_id":"0ac8d810-e1af-42a5-9183-5ed9acf488e2","resolution":{"observed_at":"2026-08-02T07:51:13.110516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14992","last_updated":"2023-10-23T07:24:28Z","snapshot_observed_at":"2026-08-15T11:39:07.998070Z","submitted_at":"2023-05-24T10:28:28Z","title":"Reasoning with Language Model is Planning with World Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14992","snapshot_observed_at":"2026-08-02T07:51:13.172119Z","title":"Reasoning with language model is planning with world model.arXiv preprint arXiv:2305.14992,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.172119Z"},"links":{"cited_paper":"/paper/2305.14992","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:89a65dce210d2194dccb272019e66f968879bc23c77f8bf9332f8d412692bc2c","observation_id":"8b6b2fb9-b281-44eb-a99d-c0dc21899489","resolution":{"observed_at":"2026-08-02T07:51:13.172119Z","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":"2026-08-02T07:51:13.224527Z","title":"Arcmemo: Abstract reasoning composition with lifelong llm memory.arXiv preprint arXiv:2509.04439,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.224527Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:6d5777762f079a742f337a1649dfc4819b3dd7e6e708c77ed283a9659ecf6f9c","observation_id":"9ea61da3-5cc7-4352-a16b-f2ee2571349d","resolution":{"observed_at":"2026-08-02T07:51:13.224527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.01006","last_updated":"2026-01-01T13:07:25Z","snapshot_observed_at":"2026-08-03T18:50:30.558321Z","submitted_at":"2025-07-01T17:55:04Z","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.01006","snapshot_observed_at":"2026-08-02T07:51:13.275479Z","title":"Glm-4.5 v and glm-4.1 v-thinking: Towards versatile multimodal reasoning with scalable reinforcement learning.arXiv preprint arXiv:2507.01006,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.275479Z"},"links":{"cited_paper":"/paper/2507.01006","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:01707ea88669e2994b98d9ba9b3496f8897710a58d3bff6e78039126e22940a1","observation_id":"f34caf6a-99e1-40ed-9320-702c458f8809","resolution":{"observed_at":"2026-08-02T07:51:13.275479Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12031","last_updated":"2024-03-28T17:56:28Z","snapshot_observed_at":"2026-08-16T16:38:21.205977Z","submitted_at":"2024-03-18T17:59:04Z","title":"RouterBench: A Benchmark for Multi-LLM Routing System","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12031","snapshot_observed_at":"2026-08-02T07:51:13.336001Z","title":"Routerbench: A benchmark for multi- llm routing system.arXiv preprint arXiv:2403.12031,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.336001Z"},"links":{"cited_paper":"/paper/2403.12031","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:dccef5960f19ca600a925dd74de9f18a4ed0555f5d15170f15b49afd98abba83","observation_id":"9e51d9d2-dacd-4f6e-abda-bffefa71dfa9","resolution":{"observed_at":"2026-08-02T07:51:13.336001Z","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":"2026-08-02T07:51:13.390327Z","title":"Heterogeneous graph trans- former","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.390327Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:85e6a578f7e914b7a650a27159dff657963ad10dde7626242c3ec27b14f54e45","observation_id":"a840040a-2bc8-4978-850a-16856819d3a7","resolution":{"observed_at":"2026-08-02T07:51:13.390327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01728","last_updated":"2024-01-29T06:27:53Z","snapshot_observed_at":"2026-08-16T11:06:17.042878Z","submitted_at":"2023-10-03T01:31:25Z","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01728","snapshot_observed_at":"2026-08-02T07:51:13.494793Z","title":"Time-llm: Time series forecasting by reprogramming large language models.arXiv preprint arXiv:2310.01728,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.494793Z"},"links":{"cited_paper":"/paper/2310.01728","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:9260009974c4cbe5451297c5460512528d7d42a55c054fabb41faef11648c2cc","observation_id":"03d67b81-d5a5-4de0-89a0-f929bd5d5b9b","resolution":{"observed_at":"2026-08-02T07:51:13.494793Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.14901","last_updated":"2025-10-16T17:18:11Z","snapshot_observed_at":"2026-08-17T01:33:28.883972Z","submitted_at":"2025-10-16T17:18:11Z","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.14901","snapshot_observed_at":"2026-08-02T07:51:13.573397Z","title":"Reasoning with sampling: Your base model is smarter than you think.arXiv preprint arXiv:2510.14901,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.573397Z"},"links":{"cited_paper":"/paper/2510.14901","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:f836e06e8d71b821edce880b477e41978edb45a5e3d646c96905a8907457f403","observation_id":"382de849-6e48-4b74-97ee-89ec4a29320b","resolution":{"observed_at":"2026-08-02T07:51:13.573397Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-02T07:51:13.635262Z","title":"Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.635262Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:cb5d246a576c8ad428da26c03d84df8c0739c1bd3674148e34dd5f880cee5683","observation_id":"d066b844-2144-4baf-9dca-fe7cf398bfe0","resolution":{"observed_at":"2026-08-02T07:51:13.635262Z","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":"2026-08-02T07:51:13.943504Z","title":"Qinghua Liu, Sam Heshmati, Zheda Mai, Zubin Abraham, John Paparrizos, and Liu Ren","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.943504Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:f51a60487b0e19c4c0ea2b4100bed7ab7ea81fa0397d5a2b9cca50074fe27cfc","observation_id":"9ddccd15-0f5c-4b25-a6fb-129adaeb6c13","resolution":{"observed_at":"2026-08-02T07:51:13.943504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11757","last_updated":"2024-04-17T21:27:33Z","snapshot_observed_at":"2026-08-16T17:50:31.858323Z","submitted_at":"2024-04-17T21:27:33Z","title":"Language Models Still Struggle to Zero-shot Reason about Time Series","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11757","snapshot_observed_at":"2026-08-02T07:51:14.067963Z","title":"Lan- guage models still struggle to zero-shot reason about time series.arXiv preprint arXiv:2404.11757,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.067963Z"},"links":{"cited_paper":"/paper/2404.11757","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:cb63ac3b57ff3ff2c030625cea4d4bd9f15ce7925575e09c4c7ef357675f293e","observation_id":"56f75502-927e-4305-ba18-efcf6c45e5f4","resolution":{"observed_at":"2026-08-02T07:51:14.067963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.17672","last_updated":"2026-05-17T22:04:11Z","snapshot_observed_at":"2026-08-15T13:34:04.737039Z","submitted_at":"2026-05-17T22:04:11Z","title":"Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.17672","snapshot_observed_at":"2026-08-02T07:51:14.115517Z","title":"Stop when reasoning converges: Semantic-preserving early exit for reasoning models.arXiv preprint arXiv:2605.17672,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.115517Z"},"links":{"cited_paper":"/paper/2605.17672","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:5edaa2422742b428b303d9d9e53f404ebeb0a26ad56950d0bf4fdff410b44105","observation_id":"8bd44b6a-a62a-4be7-bf4b-2bf8d207ca47","resolution":{"observed_at":"2026-08-02T07:51:14.115517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18665","last_updated":"2025-02-23T08:50:33Z","snapshot_observed_at":"2026-08-16T00:08:23.767909Z","submitted_at":"2024-06-26T18:10:22Z","title":"RouteLLM: Learning to Route LLMs with Preference Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.18665","snapshot_observed_at":"2026-08-02T07:51:14.177023Z","title":"Routellm: Learning to route llms with preference data.arXiv preprint arXiv:2406.18665,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.177023Z"},"links":{"cited_paper":"/paper/2406.18665","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:5b67b8632ef77d5e30fb6a1865e2fa914f931e40f78f815eba20ef3ef53f17fe","observation_id":"0177097a-7f18-4c92-8602-ca128615150c","resolution":{"observed_at":"2026-08-02T07:51:14.177023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.07608","last_updated":"2025-04-28T18:35:59Z","snapshot_observed_at":"2026-08-17T19:59:05.022400Z","submitted_at":"2025-02-11T14:58:54Z","title":"Time2Lang: Bridging Time-Series Foundation Models and Large Language Models for Health Sensing Beyond Prompting","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.07608","snapshot_observed_at":"2026-08-02T07:51:14.276059Z","title":"Time2lang: Bridging time-series foundation models and large language models for health sensing beyond prompting.arXiv preprint arXiv:2502.07608,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.276059Z"},"links":{"cited_paper":"/paper/2502.07608","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:8d3bc99e64cf3dd228f63d88e0f9944454a79b06bc6827150c08c96b81934674","observation_id":"6e60d083-c47b-4ed0-8504-3850ea0bcf77","resolution":{"observed_at":"2026-08-02T07:51:14.276059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15789","last_updated":"2023-09-27T17:08:40Z","snapshot_observed_at":"2026-08-16T14:57:08.067521Z","submitted_at":"2023-09-27T17:08:40Z","title":"Large Language Model Routing with Benchmark Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15789","snapshot_observed_at":"2026-08-02T07:51:14.388178Z","title":"Large language model routing with benchmark datasets.arXiv preprint arXiv:2309.15789,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.388178Z"},"links":{"cited_paper":"/paper/2309.15789","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:62a62d579279eb26d70af9496c5f6d8a191d9f7fbff5644e04ba30aa9120ba1d","observation_id":"83fbe965-1f97-443c-be53-ccb8d86110cd","resolution":{"observed_at":"2026-08-02T07:51:14.388178Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.02276","last_updated":"2026-02-02T16:17:38Z","snapshot_observed_at":"2026-08-12T00:25:39.214406Z","submitted_at":"2026-02-02T16:17:38Z","title":"Kimi K2.5: Visual Agentic Intelligence","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.02276","snapshot_observed_at":"2026-08-02T07:51:14.445961Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.445961Z"},"links":{"cited_paper":"/paper/2602.02276","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:8c27d620e56097c8be099779c3d746393f5f408e3e7174f9af89f9ebbf1f8ae4","observation_id":"add633f4-cf08-4ded-8ae0-b783d117cfad","resolution":{"observed_at":"2026-08-02T07:51:14.445961Z","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":"2026-08-02T07:51:14.523043Z","title":"Chatts: Aligning time series with llms via synthetic data for enhanced understanding and reasoning.arXiv preprint arXiv:2412.03104,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.523043Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:2f585c3cc3ad11d68673fe1c14688b73245f8d87f32e123b643885a27acdba95","observation_id":"91e0ff98-08cd-4529-87cf-384f8bcd9229","resolution":{"observed_at":"2026-08-02T07:51:14.523043Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-02T07:51:14.579552Z","title":"Qwen3 technical report.arXiv preprint arXiv:2505.09388,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.579552Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:32660d3fb057d7e91e19268c4a6a2ed87b4dc042c3d5763ed99e3ff1ed9c7776","observation_id":"615964aa-d62b-465a-b227-d4656a9769b0","resolution":{"observed_at":"2026-08-02T07:51:14.579552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.03128","last_updated":"2026-04-08T08:22:36Z","snapshot_observed_at":"2026-08-03T04:49:13.270533Z","submitted_at":"2026-04-03T15:50:07Z","title":"Self-Distilled RLVR","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.03128","snapshot_observed_at":"2026-08-02T07:51:14.629934Z","title":"Self-distilled rlvr.arXiv preprint arXiv:2604.03128,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.629934Z"},"links":{"cited_paper":"/paper/2604.03128","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:28e47a99cd0bea44e4704b4e0b7e071486cc173527bc02cd03c22881297f282c","observation_id":"e948ad28-7085-42d4-9a90-a50f049638f8","resolution":{"observed_at":"2026-08-02T07:51:14.629934Z","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":"2026-08-02T07:51:14.736822Z","title":"Ts-reasoner: Aligning time series foundation models with llm reasoning.arXiv preprint arXiv:2510.03519, 2025a","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.736822Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:96c5e40d59e7d860bab50931b5e4f83db8b3e0321de168f59646094926e07ba3","observation_id":"772c211b-e20b-46ea-bea7-b47d568d47e4","resolution":{"observed_at":"2026-08-02T07:51:14.736822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04395","last_updated":"2025-05-26T14:45:18Z","snapshot_observed_at":"2026-08-10T10:47:28.325406Z","submitted_at":"2025-02-06T05:59:45Z","title":"Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04395","snapshot_observed_at":"2026-08-02T07:51:14.811916Z","title":"Time-vlm: Exploring multimodal vision-language models for augmented time series forecasting","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.811916Z"},"links":{"cited_paper":"/paper/2502.04395","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:d143f215756723f85d2ce2db5c38ff000c9cfe098a88c990b780d07131cf3c1e","observation_id":"f00a7f7a-cd43-4b67-9ff7-14a765116739","resolution":{"observed_at":"2026-08-02T07:51:14.811916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.10625","last_updated":"2023-04-16T22:08:08Z","snapshot_observed_at":"2026-08-16T05:27:41.446467Z","submitted_at":"2022-05-21T15:34:53Z","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.10625","snapshot_observed_at":"2026-08-02T07:51:14.896665Z","title":"Least-to-most prompting enables complex reasoning in large language models.arXiv preprint arXiv:2205.10625,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.896665Z"},"links":{"cited_paper":"/paper/2205.10625","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:334ce5cb7d4b37d8f6c1acad3fedd6ff1d5e87ea1ceab111bc893c26880a9d08","observation_id":"0692c5d8-152e-4a8e-892d-2fb2bf959292","resolution":{"observed_at":"2026-08-02T07:51:14.896665Z","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":"2026-08-02T07:51:14.958782Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.958782Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:70843906bd970dcd317bcb1484cc5eef325ba9e3b73e6de6aef048281ba4854c","observation_id":"17466f7e-26fb-4f5e-9f7e-d8db267ef154","resolution":{"observed_at":"2026-08-02T07:51:14.958782Z","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":"2026-08-02T07:51:15.010970Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:15.010970Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:99b1d6b2f815c5e817eeef49964b458d1e5a212d29aa4b811ba1af9577710e32","observation_id":"2fe29b0f-efd7-4739-a06d-be27d5174e71","resolution":{"observed_at":"2026-08-02T07:51:15.010970Z","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":"2026-08-02T07:51:15.090321Z","title":"Given a query withNchannels, we plot each channel as a separate subplot, with a shared x-axis (time/index) and individual y-axes","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:15.090321Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:8ed90d076ab0973f1d904c035e507730dff14c8d1aab92aa9ceb006bfd59711c","observation_id":"b0d0f3ea-14f1-46cf-84e1-8b4d3283bc00","resolution":{"observed_at":"2026-08-02T07:51:15.090321Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T07:51:15.259452Z","title":"In contrast, all three VLMs correctly identify the trend ordering from the visual plot, where the curvature of each regime is di- rectly observable","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:15.259452Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:3fc2cb1283f8f736c6fd67ca560d5494afde8d59e1fa351150932cbe1a3235e0","observation_id":"7e8fa8fa-dc29-42c7-9192-a47bc85574c8","resolution":{"observed_at":"2026-08-02T07:51:15.259452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.19897","last_updated":"2026-08-07T16:19:50Z","snapshot_observed_at":"2026-08-15T04:42:50.651833Z","submitted_at":"2026-01-27T18:59:08Z","title":"Self-Distillation Enables Continual Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.19897","snapshot_observed_at":"2026-08-02T07:51:14.333017Z","title":"Self-distillation en- ables continual learning.arXiv preprint arXiv:2601.19897,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":1990,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.333017Z"},"links":{"cited_paper":"/paper/2601.19897","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:bb4998f941e0ac832c679485d4e37d1944b4567a23a4237e872ccda8dda39810","observation_id":"81ddd3e4-a26e-4aef-a1eb-a845e58486d0","resolution":{"observed_at":"2026-08-02T07:51:14.333017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-17T10:49:36.026134Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-02T07:51:13.771917Z","title":"Semi-supervised classification with graph convolutional networks.arXiv preprint arXiv:1609.02907,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.771917Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:e6bddc917474f265c6fb3da5d7d8bb47c39677d9047afef6561a08b4359bd6fb","observation_id":"33793d2f-40c3-439b-a4da-f89f1394bd8b","resolution":{"observed_at":"2026-08-02T07:51:13.771917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.01875","last_updated":"2025-06-28T18:42:47Z","snapshot_observed_at":"2026-08-18T07:07:49.600640Z","submitted_at":"2025-02-26T13:47:13Z","title":"Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.01875","snapshot_observed_at":"2026-08-02T07:51:13.857375Z","title":"Time-mqa: Time series multi-task question answering with context enhancement.arXiv preprint arXiv:2503.01875, 2025a","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.857375Z"},"links":{"cited_paper":"/paper/2503.01875","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:8ecbbc809f80195e13be7ff9a692630adb6ef24e63f7d9912902d928ebfa568a","observation_id":"55c6cffe-e696-441e-8f33-d8e1e0dc1bbc","resolution":{"observed_at":"2026-08-02T07:51:13.857375Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-02T07:51:12.974025Z","title":"The llama 3 herd of models.arXiv preprint arXiv:2407.21783,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:12.974025Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:7e45d07cb57eb3646409ede33979ea5ac139294d2912ebf9e991cc23efaf4709","observation_id":"6af9c81d-b149-435e-977c-19245db82119","resolution":{"observed_at":"2026-08-02T07:51:12.974025Z","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":"2026-08-02T07:51:13.445232Z","title":"Timexl: Explainable multi-modal time series prediction with llm-in- the-loop.arXiv preprint arXiv:2503.01013,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:13.445232Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:f707d9302d01ef6c45e3ac493e26e4a31d1c8bab6b56c8c5d09ed07f9a43610a","observation_id":"2c47c604-b89d-461b-ab31-ecc2592a7064","resolution":{"observed_at":"2026-08-02T07:51:13.445232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13960","last_updated":"2024-08-27T15:06:17Z","snapshot_observed_at":"2026-08-18T05:44:06.895140Z","submitted_at":"2024-08-25T23:48:11Z","title":"Time Series Analysis for Education: Methods, Applications, and Future Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.13960","snapshot_observed_at":"2026-08-02T07:51:14.002876Z","title":"Time series analysis for education: Methods, applications, and fu- ture directions.arXiv preprint arXiv:2408.13960,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.002876Z"},"links":{"cited_paper":"/paper/2408.13960","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:1b3c76917f701faff5070ef4bc22f8fcfeae7380ab59630e6d872f70a07ca5d6","observation_id":"aee0e35d-c416-4889-bee9-984dd4de2fb0","resolution":{"observed_at":"2026-08-02T07:51:14.002876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05673","last_updated":"2025-05-27T03:51:13Z","snapshot_observed_at":"2026-08-16T18:34:57.835818Z","submitted_at":"2024-06-09T07:06:58Z","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.05673","snapshot_observed_at":"2026-08-02T07:51:14.686446Z","title":"Flow of reason- ing: Training llms for divergent reasoning with minimal examples.arXiv preprint arXiv:2406.05673,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:14.686446Z"},"links":{"cited_paper":"/paper/2406.05673","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:b8f5911a91b62c6a192e66aa21ae791608fc30e13fd717b9fc3d8656142496fa","observation_id":"10ff0623-4e5b-4213-8f30-0c0d18132869","resolution":{"observed_at":"2026-08-02T07:51:14.686446Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.21631","last_updated":"2025-11-27T12:16:54Z","snapshot_observed_at":"2026-08-17T13:26:10.378579Z","submitted_at":"2025-11-26T17:59:08Z","title":"Qwen3-VL Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.21631","snapshot_observed_at":"2026-08-02T07:51:11.550407Z","title":"Qwen3-vl technical report.arXiv preprint arXiv:2511.21631,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:11.550407Z"},"links":{"cited_paper":"/paper/2511.21631","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:cfe2286c6bd67623babb2202f0d1d8e5709ad7f404c5bc4251c92e95c4e58f33","observation_id":"38d8f79e-e8f2-492b-8647-fd294ba3e52b","resolution":{"observed_at":"2026-08-02T07:51:11.550407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21787","last_updated":"2024-12-30T19:03:24Z","snapshot_observed_at":"2026-08-14T10:00:52.343929Z","submitted_at":"2024-07-31T17:57:25Z","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21787","snapshot_observed_at":"2026-08-02T07:51:11.857581Z","title":"Large language monkeys: Scaling inference compute with re- peated sampling.arXiv preprint arXiv:2407.21787,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:11.857581Z"},"links":{"cited_paper":"/paper/2407.21787","citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:51d182afb3f1d237ff3258fe88e4cdbe6ad9933ffd71827ceeab95449a980f1b","observation_id":"16d03c42-6903-4f86-abba-d6780f0b0e98","resolution":{"observed_at":"2026-08-02T07:51:11.857581Z","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":"2026-08-02T07:51:11.722284Z","title":"Graph of thoughts: Solving elaborate problems with large language models","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:11.722284Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:543e279eeb6f09ccbf215d86c4851cb27af38c33801225355591b17518962626","observation_id":"c865e19c-c78c-4253-81f7-b53482cb0993","resolution":{"observed_at":"2026-08-02T07:51:11.722284Z","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":"2026-08-02T07:51:12.324778Z","title":"Under- standing different design choices in training large time series models.arXiv preprint arXiv:2406.14045,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","version":2},"reference_index":2026,"source":"pdf_text","source_observed_at":"2026-08-02T07:51:12.324778Z"},"links":{"citing_paper":"/paper/2607.08940"},"observation_digest":"sha256:cb42c51cd01b7b5123db5c16518addcb261854ba0be458d993a3a864e9b49c6c","observation_id":"b4a218ac-051f-442a-ad70-85b44b4e1470","resolution":{"observed_at":"2026-08-02T07:51:12.324778Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.08940","last_updated":"2026-07-18T17:05:31Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T10:36:09.131665Z","submitted_at":"2026-07-09T21:09:05Z","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":46,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":47},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 1 inbound Pith citation observation for arXiv:2607.08940."}