{"id":"71138e217d1032d21c90fc17f1dffcc4756f1f0356db0332f643400919d06fe7","title":"Luitel and coauthors assess GraphCast’s Indian Summer Monsoon forecasts","argument":"Somnath Luitel, Parthasarathi Mukhopadhyay, Manmeet Singh, Sandeep Juneja and Saptarishi Dhanuka evaluate GraphCast forecasts for the Indian Summer Monsoon against ERA-5 reanalysis and IMERG satellite precipitation. They examine June–September seasons from 2021–2024, at forecast leads of 24, 48 and 72 hours. The authors report that GraphCast reproduces monsoon rainfall’s spatial pattern and annual cycle with high fidelity at short leads, and that daily temporal correlation with IMERG is high. But they also report moderately suppressed temporal variance and underrepresentation of extreme rainfall and the 95th percentile. The results distinguish rainfall’s average spatial pattern from its variability and intensity: stronger performance on the former does not mean the model represents intense events equally well. The study also reports that GraphCast closely captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability. These findings describe the tested forecasts and period; the abstract does not establish whether they extend to other seasons, regions or forecast settings.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The abstract describes deterministic forecasts initialized at 00 UTC, for June–September 2021–2024 and leads of 24, 48 and 72 hours; it does not establish whether the results generalize beyond these settings. The supplied evidence is the paper’s abstract and does not provide further methodological detail or results beyond its summary.","speaker":{"name":"Luitel, Somnath, Mukhopadhyay, Parthasarathi, Singh, Manmeet, Juneja, Sandeep, Dhanuka, Saptarishi","roleAtSource":"Article author"},"source":{"title":"GraphCast Skill and Systematic Biases in Indian Summer Monsoon Forecasts: Evaluation Against ERA5 and IMERG","publisher":"arXiv physics.ao-ph","format":"Article","url":"https://arxiv.org/abs/2607.11905","publishedAt":"2026-06-30","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors evaluated deterministic GraphCast forecasts for the Indian Summer Monsoon against ERA-5 reanalysis and IMERG satellite precipitation for June–September 2021–2024, at 24-, 48- and 72-hour leads.","excerpt":"against ERA-5 reanalysis and IMERG satellite precipitation for the boreal summer season (June-September, JJAS) over 2021-2024","url":"https://arxiv.org/abs/2607.11905","relationship":"Source-stated"},{"text":"The authors report that GraphCast reproduced the spatial pattern and annual cycle of monsoon rainfall with high fidelity at short leads, with high daily temporal correlation with IMERG.","excerpt":"GraphCast reproduces the spatial pattern and annual cycle of monsoon rainfall with high fidelity at short leads","url":"https://arxiv.org/abs/2607.11905","relationship":"Source-stated"},{"text":"The authors report suppressed temporal variance and underrepresentation of extreme rainfall and the 95th percentile.","excerpt":"temporal variance is moderately suppressed across timescales (power-spectrum variance ratio ~0.63), and the intensity distribution systematically underrepresents extreme events and the 95th percentile.","url":"https://arxiv.org/abs/2607.11905","relationship":"Source-stated"},{"text":"The authors report that GraphCast captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability.","excerpt":"GraphCast closely captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability.","url":"https://arxiv.org/abs/2607.11905","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2607.11905","checkedAt":"2026-11-10T08:34:08.788Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Do the reported biases persist for other forecast leads, seasons or evaluation periods?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Luitel and coauthors assess GraphCast’s Indian Summer Monsoon forecasts","summary":"Somnath Luitel, Parthasarathi Mukhopadhyay, Manmeet Singh, Sandeep Juneja and Saptarishi Dhanuka evaluate GraphCast forecasts for the Indian Summer Monsoon against ERA-5 reanalysis and IMERG satellite precipitation. They examine June–September seasons from 2021–2024, at forecast leads of 24, 48 and 72 hours. The authors report that GraphCast reproduces monsoon rainfall’s spatial pattern and annual cycle with high fidelity at short leads, and that daily temporal correlation with IMERG is high. But they also report moderately suppressed temporal variance and underrepresentation of extreme rainfall and the 95th percentile. The results distinguish rainfall’s average spatial pattern from its variability and intensity: stronger performance on the former does not mean the model represents intense events equally well. The study also reports that GraphCast closely captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability. These findings describe the tested forecasts and period; the abstract does not establish whether they extend to other seasons, regions or forecast settings.","question":"Do the reported biases persist for other forecast leads, seasons or evaluation periods?","claims":[{"text":"The authors evaluated deterministic GraphCast forecasts for the Indian Summer Monsoon against ERA-5 reanalysis and IMERG satellite precipitation for June–September 2021–2024, at 24-, 48- and 72-hour leads.","excerpt":"against ERA-5 reanalysis and IMERG satellite precipitation for the boreal summer season (June-September, JJAS) over 2021-2024","support":"source-stated"},{"text":"The authors report that GraphCast reproduced the spatial pattern and annual cycle of monsoon rainfall with high fidelity at short leads, with high daily temporal correlation with IMERG.","excerpt":"GraphCast reproduces the spatial pattern and annual cycle of monsoon rainfall with high fidelity at short leads","support":"source-stated"},{"text":"The authors report suppressed temporal variance and underrepresentation of extreme rainfall and the 95th percentile.","excerpt":"temporal variance is moderately suppressed across timescales (power-spectrum variance ratio ~0.63), and the intensity distribution systematically underrepresents extreme events and the 95th percentile.","support":"source-stated"},{"text":"The authors report that GraphCast captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability.","excerpt":"GraphCast closely captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability.","support":"source-stated"}],"limitations":["The abstract describes deterministic forecasts initialized at 00 UTC, for June–September 2021–2024 and leads of 24, 48 and 72 hours; it does not establish whether the results generalize beyond these settings.","The supplied evidence is the paper’s abstract and does not provide further methodological detail or results beyond its summary."],"mediaId":"a77887e55c971d874fb91aa449b9a43287a7320e94accec199ea4c7d3259e9ea","correctionReason":null,"id":"71138e217d1032d21c90fc17f1dffcc4756f1f0356db0332f643400919d06fe7","publicationId":"e9038532-0eab-4ee2-8668-13a5a82f2c31","version":1,"sourceUrl":"https://arxiv.org/abs/2607.11905","sourceTitle":"GraphCast Skill and Systematic Biases in Indian Summer Monsoon Forecasts: Evaluation Against ERA5 and IMERG","publisher":"arXiv physics.ao-ph","publishedAt":null,"originalPublished":{"value":"2026-06-30","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-03T08:51:12.903Z","createdAt":"2026-11-10T08:02:02.863Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"a77887e55c971d874fb91aa449b9a43287a7320e94accec199ea4c7d3259e9ea","kind":"article","url":"https://arxiv.org/abs/2607.11905","sourceUrl":"https://arxiv.org/abs/2607.11905","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-03T18:01:07.044Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2607.11905","checkedAt":"2026-11-10T08:34:08.788Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"a77887e55c971d874fb91aa449b9a43287a7320e94accec199ea4c7d3259e9ea","confidence":0.8200000000000001,"provider":"typesafe","model":"jev-1.13.0","inputHash":"7ffec4bc5a20da5750f5f8439f2221adc6d6e19a088ffe5a2de3361e32ff8eca","decidedAt":"2026-11-03T18:01:09.120Z"},"provenance":{"textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observationId":"0fa68c90a79262946d8bcba1ec8d72ed6377b27fae6e97c073e9e07cc17d46a0","retrievedAt":"2026-11-03T18:01:06.747Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"e1e77a5d-5145-434b-8b3b-9b677c501911"},"reviewer":{"model":"gpt-6-luna","runId":"3fc17a4a-f202-483f-8395-633dfe6efa27"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-10T08:02:02.863Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Luitel, Somnath","url":null,"kind":"unknown"},{"name":"Mukhopadhyay, Parthasarathi","url":null,"kind":"unknown"},{"name":"Singh, Manmeet","url":null,"kind":"unknown"},{"name":"Juneja, Sandeep","url":null,"kind":"unknown"},{"name":"Dhanuka, Saptarishi","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Luitel, Somnath","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Luitel, Somnath","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2607.11905","locator":"head/meta[name=author|citation_author]"},"assertionId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T08:34:08.788Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","sourceUrl":"https://arxiv.org/abs/2607.11905","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z"}},{"actor":{"name":"Mukhopadhyay, Parthasarathi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Mukhopadhyay, Parthasarathi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2607.11905","locator":"head/meta[name=author|citation_author]"},"assertionId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T08:34:08.788Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","sourceUrl":"https://arxiv.org/abs/2607.11905","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z"}},{"actor":{"name":"Singh, Manmeet","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Singh, Manmeet","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2607.11905","locator":"head/meta[name=author|citation_author]"},"assertionId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T08:34:08.788Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","sourceUrl":"https://arxiv.org/abs/2607.11905","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z"}},{"actor":{"name":"Juneja, Sandeep","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Juneja, Sandeep","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2607.11905","locator":"head/meta[name=author|citation_author]"},"assertionId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T08:34:08.788Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","sourceUrl":"https://arxiv.org/abs/2607.11905","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z"}},{"actor":{"name":"Dhanuka, Saptarishi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Dhanuka, Saptarishi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2607.11905","locator":"head/meta[name=author|citation_author]"},"assertionId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T08:34:08.788Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","sourceUrl":"https://arxiv.org/abs/2607.11905","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z"}}],"participationCoverage":{"total":5,"returned":5,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2607.11905","snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z","basis":"publisher-page-metadata","sourceLinks":45,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/71138e217d1032d21c90fc17f1dffcc4756f1f0356db0332f643400919d06fe7/source"}},"canonicalUrl":"https://escapemeridian.com/readings/luitel-and-coauthors-assess-graphcast-s-indian-summer-monsoon-71138e21","formats":{"html":"/readings/luitel-and-coauthors-assess-graphcast-s-indian-summer-monsoon-71138e21","markdown":"/readings/luitel-and-coauthors-assess-graphcast-s-indian-summer-monsoon-71138e21.md","json":"/readings/luitel-and-coauthors-assess-graphcast-s-indian-summer-monsoon-71138e21.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[],"entities":[{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"71138e217d1032d21c90fc17f1dffcc4756f1f0356db0332f643400919d06fe7","revision":"e9038532-0eab-4ee2-8668-13a5a82f2c31","revisionKind":"publication-id","title":"Luitel and coauthors assess GraphCast’s Indian Summer Monsoon forecasts","url":"https://escapemeridian.com/readings/luitel-and-coauthors-assess-graphcast-s-indian-summer-monsoon-71138e21"},"source":{"type":"source","id":"https://arxiv.org/abs/2607.11905","revision":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","revisionKind":"sha256-source-text","title":"GraphCast Skill and Systematic Biases in Indian Summer Monsoon Forecasts: Evaluation Against ERA5 and IMERG","url":"https://arxiv.org/abs/2607.11905"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"71138e217d1032d21c90fc17f1dffcc4756f1f0356db0332f643400919d06fe7","title":"Luitel and coauthors assess GraphCast’s Indian Summer Monsoon forecasts","argument":"Somnath Luitel, Parthasarathi Mukhopadhyay, Manmeet Singh, Sandeep Juneja and Saptarishi Dhanuka evaluate GraphCast forecasts for the Indian Summer Monsoon against ERA-5 reanalysis and IMERG satellite precipitation. They examine June–September seasons from 2021–2024, at forecast leads of 24, 48 and 72 hours. The authors report that GraphCast reproduces monsoon rainfall’s spatial pattern and annual cycle with high fidelity at short leads, and that daily temporal correlation with IMERG is high. But they also report moderately suppressed temporal variance and underrepresentation of extreme rainfall and the 95th percentile. The results distinguish rainfall’s average spatial pattern from its variability and intensity: stronger performance on the former does not mean the model represents intense events equally well. The study also reports that GraphCast closely captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability. These findings describe the tested forecasts and period; the abstract does not establish whether they extend to other seasons, regions or forecast settings.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The abstract describes deterministic forecasts initialized at 00 UTC, for June–September 2021–2024 and leads of 24, 48 and 72 hours; it does not establish whether the results generalize beyond these settings. The supplied evidence is the paper’s abstract and does not provide further methodological detail or results beyond its summary.","speaker":{"name":"Luitel, Somnath, Mukhopadhyay, Parthasarathi, Singh, Manmeet, Juneja, Sandeep, Dhanuka, Saptarishi","roleAtSource":"Article author"},"source":{"title":"GraphCast Skill and Systematic Biases in Indian Summer Monsoon Forecasts: Evaluation Against ERA5 and IMERG","publisher":"arXiv physics.ao-ph","format":"Article","url":"https://arxiv.org/abs/2607.11905","publishedAt":"2026-06-30","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors evaluated deterministic GraphCast forecasts for the Indian Summer Monsoon against ERA-5 reanalysis and IMERG satellite precipitation for June–September 2021–2024, at 24-, 48- and 72-hour leads.","excerpt":"against ERA-5 reanalysis and IMERG satellite precipitation for the boreal summer season (June-September, JJAS) over 2021-2024","url":"https://arxiv.org/abs/2607.11905","relationship":"Source-stated"},{"text":"The authors report that GraphCast reproduced the spatial pattern and annual cycle of monsoon rainfall with high fidelity at short leads, with high daily temporal correlation with IMERG.","excerpt":"GraphCast reproduces the spatial pattern and annual cycle of monsoon rainfall with high fidelity at short leads","url":"https://arxiv.org/abs/2607.11905","relationship":"Source-stated"},{"text":"The authors report suppressed temporal variance and underrepresentation of extreme rainfall and the 95th percentile.","excerpt":"temporal variance is moderately suppressed across timescales (power-spectrum variance ratio ~0.63), and the intensity distribution systematically underrepresents extreme events and the 95th percentile.","url":"https://arxiv.org/abs/2607.11905","relationship":"Source-stated"},{"text":"The authors report that GraphCast captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability.","excerpt":"GraphCast closely captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability.","url":"https://arxiv.org/abs/2607.11905","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2607.11905","checkedAt":"2026-11-10T08:34:08.788Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Do the reported biases persist for other forecast leads, seasons or evaluation periods?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Luitel and coauthors assess GraphCast’s Indian Summer Monsoon forecasts","summary":"Somnath Luitel, Parthasarathi Mukhopadhyay, Manmeet Singh, Sandeep Juneja and Saptarishi Dhanuka evaluate GraphCast forecasts for the Indian Summer Monsoon against ERA-5 reanalysis and IMERG satellite precipitation. They examine June–September seasons from 2021–2024, at forecast leads of 24, 48 and 72 hours. The authors report that GraphCast reproduces monsoon rainfall’s spatial pattern and annual cycle with high fidelity at short leads, and that daily temporal correlation with IMERG is high. But they also report moderately suppressed temporal variance and underrepresentation of extreme rainfall and the 95th percentile. The results distinguish rainfall’s average spatial pattern from its variability and intensity: stronger performance on the former does not mean the model represents intense events equally well. The study also reports that GraphCast closely captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability. These findings describe the tested forecasts and period; the abstract does not establish whether they extend to other seasons, regions or forecast settings.","question":"Do the reported biases persist for other forecast leads, seasons or evaluation periods?","claims":[{"text":"The authors evaluated deterministic GraphCast forecasts for the Indian Summer Monsoon against ERA-5 reanalysis and IMERG satellite precipitation for June–September 2021–2024, at 24-, 48- and 72-hour leads.","excerpt":"against ERA-5 reanalysis and IMERG satellite precipitation for the boreal summer season (June-September, JJAS) over 2021-2024","support":"source-stated"},{"text":"The authors report that GraphCast reproduced the spatial pattern and annual cycle of monsoon rainfall with high fidelity at short leads, with high daily temporal correlation with IMERG.","excerpt":"GraphCast reproduces the spatial pattern and annual cycle of monsoon rainfall with high fidelity at short leads","support":"source-stated"},{"text":"The authors report suppressed temporal variance and underrepresentation of extreme rainfall and the 95th percentile.","excerpt":"temporal variance is moderately suppressed across timescales (power-spectrum variance ratio ~0.63), and the intensity distribution systematically underrepresents extreme events and the 95th percentile.","support":"source-stated"},{"text":"The authors report that GraphCast captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability.","excerpt":"GraphCast closely captures the vertical structure and seasonal evolution of Q1 and Q2, but degrades in northward-propagating intraseasonal variability.","support":"source-stated"}],"limitations":["The abstract describes deterministic forecasts initialized at 00 UTC, for June–September 2021–2024 and leads of 24, 48 and 72 hours; it does not establish whether the results generalize beyond these settings.","The supplied evidence is the paper’s abstract and does not provide further methodological detail or results beyond its summary."],"mediaId":"a77887e55c971d874fb91aa449b9a43287a7320e94accec199ea4c7d3259e9ea","correctionReason":null,"id":"71138e217d1032d21c90fc17f1dffcc4756f1f0356db0332f643400919d06fe7","publicationId":"e9038532-0eab-4ee2-8668-13a5a82f2c31","version":1,"sourceUrl":"https://arxiv.org/abs/2607.11905","sourceTitle":"GraphCast Skill and Systematic Biases in Indian Summer Monsoon Forecasts: Evaluation Against ERA5 and IMERG","publisher":"arXiv physics.ao-ph","publishedAt":null,"originalPublished":{"value":"2026-06-30","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-03T08:51:12.903Z","createdAt":"2026-11-10T08:02:02.863Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"a77887e55c971d874fb91aa449b9a43287a7320e94accec199ea4c7d3259e9ea","kind":"article","url":"https://arxiv.org/abs/2607.11905","sourceUrl":"https://arxiv.org/abs/2607.11905","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-03T18:01:07.044Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2607.11905","checkedAt":"2026-11-10T08:34:08.788Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"a77887e55c971d874fb91aa449b9a43287a7320e94accec199ea4c7d3259e9ea","confidence":0.8200000000000001,"provider":"typesafe","model":"jev-1.13.0","inputHash":"7ffec4bc5a20da5750f5f8439f2221adc6d6e19a088ffe5a2de3361e32ff8eca","decidedAt":"2026-11-03T18:01:09.120Z"},"provenance":{"textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observationId":"0fa68c90a79262946d8bcba1ec8d72ed6377b27fae6e97c073e9e07cc17d46a0","retrievedAt":"2026-11-03T18:01:06.747Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"e1e77a5d-5145-434b-8b3b-9b677c501911"},"reviewer":{"model":"gpt-6-luna","runId":"3fc17a4a-f202-483f-8395-633dfe6efa27"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-10T08:02:02.863Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Luitel, Somnath","url":null,"kind":"unknown"},{"name":"Mukhopadhyay, Parthasarathi","url":null,"kind":"unknown"},{"name":"Singh, Manmeet","url":null,"kind":"unknown"},{"name":"Juneja, Sandeep","url":null,"kind":"unknown"},{"name":"Dhanuka, Saptarishi","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Luitel, Somnath","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Luitel, Somnath","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2607.11905","locator":"head/meta[name=author|citation_author]"},"assertionId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T08:34:08.788Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","sourceUrl":"https://arxiv.org/abs/2607.11905","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z"}},{"actor":{"name":"Mukhopadhyay, Parthasarathi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Mukhopadhyay, Parthasarathi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2607.11905","locator":"head/meta[name=author|citation_author]"},"assertionId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T08:34:08.788Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","sourceUrl":"https://arxiv.org/abs/2607.11905","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z"}},{"actor":{"name":"Singh, Manmeet","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Singh, Manmeet","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2607.11905","locator":"head/meta[name=author|citation_author]"},"assertionId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T08:34:08.788Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","sourceUrl":"https://arxiv.org/abs/2607.11905","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z"}},{"actor":{"name":"Juneja, Sandeep","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Juneja, Sandeep","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2607.11905","locator":"head/meta[name=author|citation_author]"},"assertionId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T08:34:08.788Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","sourceUrl":"https://arxiv.org/abs/2607.11905","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z"}},{"actor":{"name":"Dhanuka, Saptarishi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Dhanuka, Saptarishi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2607.11905","locator":"head/meta[name=author|citation_author]"},"assertionId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T08:34:08.788Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","sourceUrl":"https://arxiv.org/abs/2607.11905","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z"}}],"participationCoverage":{"total":5,"returned":5,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2607.11905","snapshotId":"b39ba5634290f3137e945c96753a237c516d354d024d156b6f86ede170964101","contentSha256":"e9a7b1634e9d80589b5a8fbcf640004db6bd5a81564dc6658048f608cd6b9868","textHash":"fc59da7efca29f67f3372de717840619db6d6b29e86fc998b768f1a76b6707ba","observedAt":"2026-11-10T08:34:08.788Z","basis":"publisher-page-metadata","sourceLinks":45,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/71138e217d1032d21c90fc17f1dffcc4756f1f0356db0332f643400919d06fe7/source"}}}],"audits":[{"publicationId":"e9038532-0eab-4ee2-8668-13a5a82f2c31","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The draft names the five listed authors and consistently frames the findings as what the authors report or evaluate. It does not present them as Escape Meridian conclusions.","excerpt":"Authors:Somnath Luitel, Parthasarathi Mukhopadhyay, Manmeet Singh, Sandeep Juneja, Saptarishi Dhanuka"},{"dimension":"summary","status":"uncertain","explanation":"The facts are faithful, but a general reader is not told that GraphCast is Google's machine-learning global weather prediction system, which is central to the AI relevance. Q1 and Q2 appear without explanation; the source defines them as the apparent heat source and moisture sink. ERA-5 reanalysis and IMERG are also unexplained. The draft omits the authors' overall framing of moderate underrepresentation rather than a wet bias or variance collapse, and their benchmark purpose for AI weather models. Smallest repair: identify GraphCast, gloss Q1/Q2, and add the authors' concluding characterization.","excerpt":"Google's GraphCast, a machine-learning global weather prediction system"},{"dimension":"date","status":"pass","explanation":"originalPublished is 2026-06-30, which matches the v1 submission date. It is not the date of the later v3 revision or of the feed entry.","excerpt":"[Submitted on 30 Jun 2026 (v1), last revised 30 Oct 2026 (this version, v3)]"},{"dimension":"support","status":"pass","explanation":"Every claim matches the abstract. The interpretive sentence about pattern versus intensity follows from the reported results. The limitations and the question about generalization are appropriately conditional, and the draft does not turn the evaluation into a real-world reliability claim.","excerpt":"the intensity distribution systematically underrepresents extreme events and the 95th percentile"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified, direct arXiv abstract page for this paper, which is the actual source.","excerpt":null}],"createdAt":"2026-11-10T08:02:02.863Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}