{"as_of":"2026-08-05T15:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b4114c92ebf2b2199f92e89f67ba0c8df924f397428744700c58f4208570b05c","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T05:45:48.655352Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+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/2606.05404/citation-record","integrity":"/paper/2606.05404/integrity","json":"/paper/2606.05404/citation-record.json","paper":"/paper/2606.05404"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.07407","last_updated":"2025-08-31T14:55:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-08-10T16:07:32Z","title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","version":2},"cited_work":{"arxiv_id":"2508.07407","doi":"10.48550/arxiv.2508.07407","metadata_source":"pith","pith_arxiv_id":"2508.07407","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","venue":"cs.AI","work_id":"10037f9e-62d9-4dd1-a9c1-44be77032524","year":2025},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"cited_paper":"/paper/2508.07407","citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:d8ad533487d8995264856aa68c50d9fae8c3d0983cd1c422313164eaa225a5cf","observation_id":"70b1930b-c34c-4810-84d5-aca8e9d70d67","resolution":{"observed_at":"2026-07-02T08:46:49.087671Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11341","last_updated":"2024-08-26T12:14:31Z","snapshot_observed_at":"2026-07-30T19:27:20.943432Z","submitted_at":"2024-04-17T13:00:52Z","title":"The Causal Chambers: Real Physical Systems as a Testbed for AI Methodology","version":2},"cited_work":{"arxiv_id":"2404.11341","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.11341","snapshot_observed_at":"2026-07-02T08:46:49.116201Z","title":"Azul Garza, Cristian Challu, and Max Mergenthaler- Canseco","venue":null,"work_id":"d545a7b2-6113-4825-b94b-dda46bcfcd25","year":2023},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"cited_paper":"/paper/2404.11341","citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:7a567ee86dd15abf072e4ea6c2f1a89a81bc8de03ea5a1887e42b507ef3dbb45","observation_id":"79e7a665-2bbe-4466-a6c8-d86294aea8de","resolution":{"observed_at":"2026-07-02T08:46:49.117583Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.06643","last_updated":"2021-05-14T04:49:58Z","snapshot_observed_at":"2026-08-05T05:36:13.294437Z","submitted_at":"2021-05-14T04:49:58Z","title":"Monash Time Series Forecasting Archive","version":1},"cited_work":{"arxiv_id":"2105.06643","doi":null,"metadata_source":"pith","pith_arxiv_id":"2105.06643","snapshot_observed_at":"2026-07-08T04:14:29.621429Z","title":"Monash time series forecasting archive","venue":"cs.LG","work_id":"d95cde79-a4c5-456d-be01-f0a990e948da","year":2021},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"cited_paper":"/paper/2105.06643","citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:cb2c06d4a36bb3d9450ecd1a457387e610e29e2204ceec819ca7c161bd5bf883","observation_id":"245cf93e-abdc-4c82-9f56-1e27b9a21c09","resolution":{"observed_at":"2026-07-02T08:46:49.110736Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2512.13564","last_updated":"2026-01-13T09:33:57Z","snapshot_observed_at":"2026-07-30T04:57:05.391864Z","submitted_at":"2025-12-15T17:22:34Z","title":"Memory in the Age of AI Agents","version":2},"cited_work":{"arxiv_id":"2512.13564","doi":"10.48550/arxiv.2512.13564","metadata_source":"pith","pith_arxiv_id":"2512.13564","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Memory in the Age of AI Agents","venue":"cs.CL","work_id":"1ff75a14-302e-4906-aa86-1f96fbcf12ff","year":2025},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"cited_paper":"/paper/2512.13564","citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:6fd0ecc7d531b5fe8bffddafcc51a46e93e6819faaca05dcc63dc9a26f49f654","observation_id":"d039e4c0-1a46-42a8-bc12-e724899b7c85","resolution":{"observed_at":"2026-07-02T08:46:49.112455Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2602.06052","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T10:17:57.832911Z","title":"Rethinking memory mechanisms of foundation agents in the second half","venue":null,"work_id":"639480bb-7fee-4f7e-ac4f-23006d622bd4","year":2026},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:33035c8c81f8bdb012a10182ec2ed6894c1609f492c1af67c0e37111ea42a09c","observation_id":"f368d4d6-4217-4199-8ea5-0b68ca553bb1","resolution":{"observed_at":"2026-07-02T08:46:49.115053Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.23204","last_updated":"2026-06-05T09:20:33Z","snapshot_observed_at":"2026-08-03T06:16:21.975585Z","submitted_at":"2026-01-30T17:28:56Z","title":"TSAQA: Time Series Analysis Question And Answering Benchmark","version":2},"cited_work":{"arxiv_id":"2601.23204","doi":"10.48550/arxiv.2601.23204","metadata_source":"pith","pith_arxiv_id":"2601.23204","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"TSAQA: time series analysis question and answering benchmark.CoRR, abs/2601.23204","venue":"cs.AI","work_id":"07959329-45b8-4d40-b530-e217f9ba66d1","year":2026},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"cited_paper":"/paper/2601.23204","citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:a0bb1b35a240a2f208f1c35eff75c87f25810e684c4ceaf0f8f6610f4cf2e9f0","observation_id":"c100b35d-70ab-4814-b380-404daa2e7d6a","resolution":{"observed_at":"2026-07-02T08:46:49.094581Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2605.18661","last_updated":"2026-07-20T17:24:03Z","snapshot_observed_at":"2026-08-02T13:43:29.187658Z","submitted_at":"2026-05-18T17:08:26Z","title":"AI for Auto-Research: Roadmap & User Guide","version":2},"cited_work":{"arxiv_id":"2605.18661","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.18661","snapshot_observed_at":"2026-07-04T13:49:51.423665Z","title":"AI for Auto-Research: Roadmap & User Guide","venue":"cs.AI","work_id":"fd36f848-f5c6-4a81-b81b-b4bd053e9390","year":2026},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"cited_paper":"/paper/2605.18661","citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:0060381f9ae9a3cc7ccbb905506e7cbefa95e74c46263c1d7fb5f8caaf04b5ce","observation_id":"fa7b5c90-abbc-4b7b-b476-735afd25957a","resolution":{"observed_at":"2026-07-02T08:46:49.113088Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2502.08942","doi":"10.48550/arxiv.2502.08942","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"InProceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining, pages 5351–5362","venue":"ArXiv.org","work_id":"1f0effe7-36be-4e8e-bb79-7ef67192972c","year":2024},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:73c09f747d9bb50611ccf2ebdb67e5ff2617a8231278b4fe1388d975516e8683","observation_id":"5ba24063-614b-4f1f-8993-db01a43de80f","resolution":{"observed_at":"2026-07-02T08:46:49.110259Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.08309","last_updated":"2025-06-11T03:31:52Z","snapshot_observed_at":"2026-08-02T18:59:33.305482Z","submitted_at":"2025-06-10T00:35:53Z","title":"Learnable Spatial-Temporal Positional Encoding for Link Prediction","version":2},"cited_work":{"arxiv_id":"2506.08309","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.08309","snapshot_observed_at":"2026-07-02T08:46:49.106072Z","title":"InInternational Conference on Learning Representations, volume 2024, pages 37854–37881","venue":null,"work_id":"bbe0ef18-6947-4804-b9e3-e61073d89216","year":2024},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"cited_paper":"/paper/2506.08309","citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:65690274bf4ccbcc71083948ccb6aaa6cf7cc29db7469650bc87c2cecf85ce46","observation_id":"9e47920c-560c-41d9-a8a9-3ed3e8c39885","resolution":{"observed_at":"2026-07-02T08:46:49.107529Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.13653","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T08:19:44.551372Z","title":"TimeART: Towards agentic time series reasoning via tool-augmentation","venue":null,"work_id":"6cce6e3a-1ae6-400b-90ee-269c965b33ed","year":2026},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:5cc59fdd648a9b932275db3049344f9bdc9e4f8961d15c66191f07239b06483e","observation_id":"f0a21c4b-e803-435c-85b7-d088f58db8e2","resolution":{"observed_at":"2026-07-02T08:46:49.099616Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20138","last_updated":"2025-06-03T05:45:06Z","snapshot_observed_at":"2026-07-06T20:14:03.824268Z","submitted_at":"2024-12-28T12:54:06Z","title":"TradingAgents: Multi-Agents LLM Financial Trading Framework","version":7},"cited_work":{"arxiv_id":"2412.20138","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.20138","snapshot_observed_at":"2026-07-04T20:00:07.722366Z","title":"Hongyang Yang, Xiao-Yang Liu, and Christina Dan Wang","venue":null,"work_id":"e792c1b3-342a-4de2-98eb-fa551be974af","year":2024},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"cited_paper":"/paper/2412.20138","citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:c45988d6f1eb66871034aedf93b3cec10b02b4deb5f46e4b885ee99a04fc56c9","observation_id":"a2ff5a6b-21dc-4665-bddd-47856009417f","resolution":{"observed_at":"2026-07-02T08:46:49.100535Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.01822","last_updated":"2025-09-01T22:58:57Z","snapshot_observed_at":"2026-08-05T12:12:24.063098Z","submitted_at":"2025-09-01T22:58:57Z","title":"When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference","version":1},"cited_work":{"arxiv_id":"2509.01822","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2509.01822","snapshot_observed_at":"2026-07-04T12:59:52.930071Z","title":"When LLM meets time series: Can LLMs perform multi-step time series reasoning and inference","venue":null,"work_id":"10d0ae15-3882-4520-b83d-e0abd1fe719f","year":2025},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"cited_paper":"/paper/2509.01822","citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:4cf731fdec08240fb9b562f26702b03b172d717777c995a199d77a2c2237c776","observation_id":"1b9c9b6f-3dc8-4b81-bf61-54b869f79cf3","resolution":{"observed_at":"2026-07-02T08:46:49.087019Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07209","last_updated":"2025-05-19T09:44:19Z","snapshot_observed_at":"2026-08-04T10:05:13.497222Z","submitted_at":"2023-06-12T16:12:56Z","title":"Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow","version":8},"cited_work":{"arxiv_id":"2306.07209","doi":"10.48550/arxiv.2306.07209","metadata_source":"arxiv_reference","pith_arxiv_id":"2306.07209","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2306.07209 , year=","venue":"arXiv (Cornell University)","work_id":"567aaa63-da15-49df-a37e-843fccb3f726","year":2023},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"cited_paper":"/paper/2306.07209","citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:5e9f710309bdc42cdba43f9b04dce839e34d41d0a5f7721ab12e4201e3b9a8ef","observation_id":"d941330a-4f25-4b84-a263-b14a671bd07e","resolution":{"observed_at":"2026-07-02T08:46:49.103046Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2504.01346","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T12:49:52.116121Z","title":"arXiv preprint arXiv:2504.01346 , year =","venue":null,"work_id":"96278dbd-9cd6-4190-81f1-cf390f93bb41","year":2025},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:4d8c877ae3f0ab8b063540716ed2deff73946223f1aa982fa8c8c61c723cac6c","observation_id":"d489e22c-6841-48fa-ac94-f718be6974aa","resolution":{"observed_at":"2026-07-02T08:46:49.104825Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2480.1332","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T08:46:49.118709Z","title":"struct” features describe the channel pool as a whole; “per-ch","venue":null,"work_id":"1af04273-0849-4192-884f-f2acf5ca8f43","year":2023},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:54ad9ab315b8db4d2aaca49348ac9c4d64e60f8712441458a8e8688091f0aec5","observation_id":"fa7e01f4-8eb4-439e-839c-8f313b07f9e1","resolution":{"observed_at":"2026-07-02T08:46:49.120050Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-28T05:45:48.655352Z","title":"Withk= 1on this task both stages converge on the same family (FULLCAUSALCONTEXTIMPLICITEQUATIONBIVARLINSVAR) seen during training","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:379b2eaec50120237150cb20de4a32fe1c85470f91d8df109ec8108d6f44deb3","observation_id":"cd68ac15-36d1-4b4e-a710-99c8e03fb5cf","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:3ea5d707efba6e3345a25639f0ba2668f50b8f487651a6a410d3ec6fd76d3bdc","observation_id":"f0e39870-e0ba-42df-85c4-ae434ef5c181","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:550eb2dbd3cd4c014b32fe542c9fbbe7f13518a98780e7ff6d2559240b5f1e3f","observation_id":"96ff5fcc-2bf2-4424-8432-e41ee141bb56","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"1\")→compute_acf(","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:645372e06f1269f499b49089bbba262b1f78b2df7cb099bc956036b3f95a14a6","observation_id":"c570d6a3-191d-4f4c-b969-edad76f8449b","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"parents forX1 at lagk∈ {1,2,3}areX0, X1,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:867be4c291d9f9253da5a6f8f0dad34f374558b265862a07352c5c18759a8bc6","observation_id":"6a8bc3df-c982-4090-b9c5-3a224c68c3e1","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"Then TIMECLAWretrievesk=3records","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:1c1dd6373e0fee0661288a0be019d63fe6916f203b079b102468a60e167a48ea","observation_id":"917406c6-9344-4995-89e3-ce335f8a9662","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"the mechanism mapping is upstream-to-downstream edges","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:8764f25bbc0690bc37233412ab37c59833b608b4654610b17592cc071887a9bf","observation_id":"dd71cb93-98c8-476b-8d99-cca852f312bb","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"Execution Stage","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:ca780f04c1433fa433090d212765cf9a350358e70be394129aefd547dcae7d57","observation_id":"143d9b5e-78d8-4518-8c49-8ba0538aa802","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"It skips the exhaustive per- channel statistics, peak-finding, and periodicity-detection that the no-memory agent runs through","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:1957b6609127960479f0324231809d998438ce1dbc32286f12b9cfcb082106bf","observation_id":"605ec016-6cd0-43db-bf57-69591edccc6c","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"The rule then determines option D, in which the sink row R176 is densely populated with parents from the tributaries and the tributaries themselves are source rows","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:42b11d01b8403a392bc2663b7b797c85a6bf7909f64cc07322caf5b98cbb72f7","observation_id":"c01bce0a-e252-4fa2-ad90-2bdd3b6f554b","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"Counterfactual: Same Series, No Memory.Re-running the identical task atk=0removes only theREFERENCESblock","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:670e6991da3e8e9c33b9b400895bbfb98361f486e04fcba8bbe42779b52dbb8a","observation_id":"37057e61-f43b-46cb-9120-0995487017ff","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"Each successful trajectory is summarized into a compact routine description that records the input conventions, intermediate computations, and final decision rule","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:0780ecd94eb7945299db3d01ef43d89b07d023ae2cba151e93bff840b495dbbf","observation_id":"be276ca8-212d-4352-829c-2106e52bb734","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"parametric","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:959f0a4ce8d1e05e7edb553b806ae57d817ec9d89db3b2147f142ce79eba8e7b","observation_id":"1298b48b-b4c7-46a8-8490-7ddd30ad0e38","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:694b9f2d15681086a207c129b0f274ccfdfbc7d3695692e159f4ee3e6203afc1","observation_id":"ea70fd90-d406-4b62-9632-dcad9847c590","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","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":"2026-06-28T05:45:48.655352Z","title":"scenario says ‘heat wave for 2 hours’→ground truth has a 4×spike at the stated start→because air-conditioning load scales with cooling demand","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-28T05:45:48.655352Z"},"links":{"citing_paper":"/paper/2606.05404"},"observation_digest":"sha256:01a175b306173cf33b7d69fee481ec7104bad91c60ab05a0f4d6172e7db99967","observation_id":"6141292c-0712-4c5d-a06f-b94e9c379c88","resolution":{"observed_at":"2026-06-28T05:45:48.655352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.05404","last_updated":"2026-06-03T20:20:34Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-02T17:37:09.315250Z","submitted_at":"2026-06-03T20:20:34Z","title":"Harnessing Generalist Agents for Contextualized Time Series"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":1,"metadata_mismatch":7,"parse_uncertain":0,"unresolved":15,"verified_exact":7,"verified_fuzzy":0},"total_outbound_references":30},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2606.05404."}