{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FSM6DRXMSAXOYPL432CJNTUZCG","short_pith_number":"pith:FSM6DRXM","canonical_record":{"source":{"id":"2605.14317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T03:27:54Z","cross_cats_sorted":["physics.ao-ph"],"title_canon_sha256":"336d4d37ae7b8481d5675cd68be33a33e0c4f39e53b30e4e6e4f6190eec22c5f","abstract_canon_sha256":"035c646a70cc5c55539f134c244fc95e1f1f838be561024f7321c038fae5da57"},"schema_version":"1.0"},"canonical_sha256":"2c99e1c6ec902eec3d7cde8496ce9911b5252cf2a23e186323786f6542468d07","source":{"kind":"arxiv","id":"2605.14317","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14317","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14317v1","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14317","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"pith_short_12","alias_value":"FSM6DRXMSAXO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"FSM6DRXMSAXOYPL4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"FSM6DRXM","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FSM6DRXMSAXOYPL432CJNTUZCG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T03:27:54Z","cross_cats_sorted":["physics.ao-ph"],"title_canon_sha256":"336d4d37ae7b8481d5675cd68be33a33e0c4f39e53b30e4e6e4f6190eec22c5f","abstract_canon_sha256":"035c646a70cc5c55539f134c244fc95e1f1f838be561024f7321c038fae5da57"},"schema_version":"1.0"},"canonical_sha256":"2c99e1c6ec902eec3d7cde8496ce9911b5252cf2a23e186323786f6542468d07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:09.885652Z","signature_b64":"kqtqmfYwo4I2sltM6dPvAZ1xz9H1wECMzCVAK6KOGJZLOGFppg7V3DNg4hcSm/Ws/bqBA0swSoLlWjQa/DupBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c99e1c6ec902eec3d7cde8496ce9911b5252cf2a23e186323786f6542468d07","last_reissued_at":"2026-05-17T23:39:09.885188Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:09.885188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14317","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S8f5EITCJru8jaV1pDwIfhAw2oXIAm2X1U4mKsZPVr2Gy9Nu+a83iByDzY4P2BxVMjNnElMqiFoQXpv6uajDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T22:44:00.685485Z"},"content_sha256":"997a3dca4738e6c44f95270a14f5408e6d3d43c515ccd8c66838242d473f7b9b","schema_version":"1.0","event_id":"sha256:997a3dca4738e6c44f95270a14f5408e6d3d43c515ccd8c66838242d473f7b9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FSM6DRXMSAXOYPL432CJNTUZCG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Guided Diffusion Sampling for Precipitation Forecast Interventions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Gradient-guided diffusion sampling steers weather model trajectories to reduce extreme precipitation forecasts while preserving physical consistency.","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Ayumu Ueyama, Hiroshi Kera, Kazuhiko Kawamoto","submitted_at":"2026-05-14T03:27:54Z","abstract_excerpt":"Extreme precipitation causes severe societal and economic damage, and weather control has long been discussed as a potential mitigation strategy. However, to the best of our knowledge, perturbation-based interventions for weather control using data-driven weather forecasting models have not yet been explored. While adversarial attacks also generate perturbations that alter forecasts, they aim to exploit model artifacts and do not account for physical plausibility. In this paper, we propose a gradient-based guidance framework for precipitation-reduction interventions through diffusion sampling "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on extreme precipitation events from WeatherBench2 demonstrate that our method achieves effective precipitation reduction while yielding more physically plausible interventions than adversarial perturbations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That steering the diffusion sampling trajectory via gradients maintains consistency with the learned atmospheric distribution and produces interventions that remain physically plausible under the three evaluation perspectives.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Gradient-guided diffusion sampling reduces extreme precipitation forecasts in data-driven weather models while producing more physically plausible changes than adversarial perturbations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Gradient-guided diffusion sampling steers weather model trajectories to reduce extreme precipitation forecasts while preserving physical consistency.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5de70c9e00912b96337a744ed9fe454838de6f02a0fb35ac7905d009178bdafc"},"source":{"id":"2605.14317","kind":"arxiv","version":1},"verdict":{"id":"f7a6069b-2bba-48da-81ed-312f52456e2f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:50:24.095337Z","strongest_claim":"Experiments on extreme precipitation events from WeatherBench2 demonstrate that our method achieves effective precipitation reduction while yielding more physically plausible interventions than adversarial perturbations.","one_line_summary":"Gradient-guided diffusion sampling reduces extreme precipitation forecasts in data-driven weather models while producing more physically plausible changes than adversarial perturbations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That steering the diffusion sampling trajectory via gradients maintains consistency with the learned atmospheric distribution and produces interventions that remain physically plausible under the three evaluation perspectives.","pith_extraction_headline":"Gradient-guided diffusion sampling steers weather model trajectories to reduce extreme precipitation forecasts while preserving physical consistency."},"references":{"count":42,"sample":[{"doi":"","year":2025,"title":"Historical review of research activities toward typhoons/hurricanes modification in japan and the united states.Journal of the Meteorological Society of Japan","work_id":"7a3db458-123b-490a-83c9-0775b674ecc2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"Moshe Alamaro, Juergen Michele, and Vladimir Pudov. A preliminary assessment of inducing anthro- pogenic tropical cyclones using compressible free jets and the potential for hurricane mitigation.The J","work_id":"ce5078b6-2443-4979-bfff-fa553654b11f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Forecasting fails: Unveiling evasion attacks in weather prediction models.arXiv preprint arXiv:2512.08832, 2025","work_id":"a391f07d-d7f9-45d7-8e38-575f993a1ebe","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"R. N. Bannister. A review of operational methods of variational and ensemble-variational data assimilation. Quarterly Journal of the Royal Meteorological Society, 143(703):607–633, 2017","work_id":"74270681-efad-4dda-82ae-f33e92f1a07a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"The quiet revolution of numerical weather prediction","work_id":"eb983249-e4e5-411b-b0a1-e756de8f7011","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":42,"snapshot_sha256":"9ed1bfa99771e12ca2bc7605af095c15325a197283006704c05ce11bbb558d0e","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1b8836b4079e8ddc9cddc255111c2cf08e8fdafb935e1d3fe69f62c67d1c9640"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"f7a6069b-2bba-48da-81ed-312f52456e2f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DYE+ZRPHP1k/mnR721YeZyQmzAoJdZPJHVjquxzfI+4D1iLpUqPiSrK+QZ20KlrcbgFSXCBnp6ok+J5ZqkWsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T22:44:00.686742Z"},"content_sha256":"0f98ad5ef4060ca556ff0c57f43260ffe50fcc47048054ff78257473df99a725","schema_version":"1.0","event_id":"sha256:0f98ad5ef4060ca556ff0c57f43260ffe50fcc47048054ff78257473df99a725"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSM6DRXMSAXOYPL432CJNTUZCG/bundle.json","state_url":"https://pith.science/pith/FSM6DRXMSAXOYPL432CJNTUZCG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSM6DRXMSAXOYPL432CJNTUZCG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-29T22:44:00Z","links":{"resolver":"https://pith.science/pith/FSM6DRXMSAXOYPL432CJNTUZCG","bundle":"https://pith.science/pith/FSM6DRXMSAXOYPL432CJNTUZCG/bundle.json","state":"https://pith.science/pith/FSM6DRXMSAXOYPL432CJNTUZCG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSM6DRXMSAXOYPL432CJNTUZCG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FSM6DRXMSAXOYPL432CJNTUZCG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"035c646a70cc5c55539f134c244fc95e1f1f838be561024f7321c038fae5da57","cross_cats_sorted":["physics.ao-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T03:27:54Z","title_canon_sha256":"336d4d37ae7b8481d5675cd68be33a33e0c4f39e53b30e4e6e4f6190eec22c5f"},"schema_version":"1.0","source":{"id":"2605.14317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14317","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14317v1","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14317","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"pith_short_12","alias_value":"FSM6DRXMSAXO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"FSM6DRXMSAXOYPL4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"FSM6DRXM","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:0f98ad5ef4060ca556ff0c57f43260ffe50fcc47048054ff78257473df99a725","target":"graph","created_at":"2026-05-17T23:39:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on extreme precipitation events from WeatherBench2 demonstrate that our method achieves effective precipitation reduction while yielding more physically plausible interventions than adversarial perturbations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That steering the diffusion sampling trajectory via gradients maintains consistency with the learned atmospheric distribution and produces interventions that remain physically plausible under the three evaluation perspectives."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Gradient-guided diffusion sampling reduces extreme precipitation forecasts in data-driven weather models while producing more physically plausible changes than adversarial perturbations."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Gradient-guided diffusion sampling steers weather model trajectories to reduce extreme precipitation forecasts while preserving physical consistency."}],"snapshot_sha256":"5de70c9e00912b96337a744ed9fe454838de6f02a0fb35ac7905d009178bdafc"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1b8836b4079e8ddc9cddc255111c2cf08e8fdafb935e1d3fe69f62c67d1c9640"},"paper":{"abstract_excerpt":"Extreme precipitation causes severe societal and economic damage, and weather control has long been discussed as a potential mitigation strategy. However, to the best of our knowledge, perturbation-based interventions for weather control using data-driven weather forecasting models have not yet been explored. While adversarial attacks also generate perturbations that alter forecasts, they aim to exploit model artifacts and do not account for physical plausibility. In this paper, we propose a gradient-based guidance framework for precipitation-reduction interventions through diffusion sampling ","authors_text":"Ayumu Ueyama, Hiroshi Kera, Kazuhiko Kawamoto","cross_cats":["physics.ao-ph"],"headline":"Gradient-guided diffusion sampling steers weather model trajectories to reduce extreme precipitation forecasts while preserving physical consistency.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T03:27:54Z","title":"Guided Diffusion Sampling for Precipitation Forecast Interventions"},"references":{"count":42,"internal_anchors":2,"resolved_work":42,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Historical review of research activities toward typhoons/hurricanes modification in japan and the united states.Journal of the Meteorological Society of Japan","work_id":"7a3db458-123b-490a-83c9-0775b674ecc2","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Moshe Alamaro, Juergen Michele, and Vladimir Pudov. A preliminary assessment of inducing anthro- pogenic tropical cyclones using compressible free jets and the potential for hurricane mitigation.The J","work_id":"ce5078b6-2443-4979-bfff-fa553654b11f","year":2006},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Forecasting fails: Unveiling evasion attacks in weather prediction models.arXiv preprint arXiv:2512.08832, 2025","work_id":"a391f07d-d7f9-45d7-8e38-575f993a1ebe","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"R. N. Bannister. A review of operational methods of variational and ensemble-variational data assimilation. Quarterly Journal of the Royal Meteorological Society, 143(703):607–633, 2017","work_id":"74270681-efad-4dda-82ae-f33e92f1a07a","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"The quiet revolution of numerical weather prediction","work_id":"eb983249-e4e5-411b-b0a1-e756de8f7011","year":2015}],"snapshot_sha256":"9ed1bfa99771e12ca2bc7605af095c15325a197283006704c05ce11bbb558d0e"},"source":{"id":"2605.14317","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T01:50:24.095337Z","id":"f7a6069b-2bba-48da-81ed-312f52456e2f","model_set":{"reader":"grok-4.3"},"one_line_summary":"Gradient-guided diffusion sampling reduces extreme precipitation forecasts in data-driven weather models while producing more physically plausible changes than adversarial perturbations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Gradient-guided diffusion sampling steers weather model trajectories to reduce extreme precipitation forecasts while preserving physical consistency.","strongest_claim":"Experiments on extreme precipitation events from WeatherBench2 demonstrate that our method achieves effective precipitation reduction while yielding more physically plausible interventions than adversarial perturbations.","weakest_assumption":"That steering the diffusion sampling trajectory via gradients maintains consistency with the learned atmospheric distribution and produces interventions that remain physically plausible under the three evaluation perspectives."}},"verdict_id":"f7a6069b-2bba-48da-81ed-312f52456e2f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:997a3dca4738e6c44f95270a14f5408e6d3d43c515ccd8c66838242d473f7b9b","target":"record","created_at":"2026-05-17T23:39:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"035c646a70cc5c55539f134c244fc95e1f1f838be561024f7321c038fae5da57","cross_cats_sorted":["physics.ao-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T03:27:54Z","title_canon_sha256":"336d4d37ae7b8481d5675cd68be33a33e0c4f39e53b30e4e6e4f6190eec22c5f"},"schema_version":"1.0","source":{"id":"2605.14317","kind":"arxiv","version":1}},"canonical_sha256":"2c99e1c6ec902eec3d7cde8496ce9911b5252cf2a23e186323786f6542468d07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c99e1c6ec902eec3d7cde8496ce9911b5252cf2a23e186323786f6542468d07","first_computed_at":"2026-05-17T23:39:09.885188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:09.885188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kqtqmfYwo4I2sltM6dPvAZ1xz9H1wECMzCVAK6KOGJZLOGFppg7V3DNg4hcSm/Ws/bqBA0swSoLlWjQa/DupBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:09.885652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:997a3dca4738e6c44f95270a14f5408e6d3d43c515ccd8c66838242d473f7b9b","sha256:0f98ad5ef4060ca556ff0c57f43260ffe50fcc47048054ff78257473df99a725"],"state_sha256":"78f494b3a05551cc30b69ce01740bbabe700fb743932a1702c81d782b958b125"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Dx92NjJxcmpL/7WU2AQfrDwmlkQTaqgHR6efhKWYNMaOov2CeiEbGR4vETfsaKMFUl63yilEvYF6+KHLeX6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T22:44:00.691297Z","bundle_sha256":"8ed2454226f5c618b8e16386ad5ef9b15abb7dca2b0cb8348150c068de8bca35"}}