{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AM3Q4NFCJTHNUHCDOSXZ5LXHJB","short_pith_number":"pith:AM3Q4NFC","canonical_record":{"source":{"id":"2604.16238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-17T16:58:06Z","cross_cats_sorted":["physics.ao-ph","stat.ML"],"title_canon_sha256":"bc2e2f8ed910dc823254bde7e59596f7dab2a7728f1c9b569576cb91074d6beb","abstract_canon_sha256":"bfd64ae730373de9ce0ff248ef05f37ebba4b35cfa64bd22f6083f87bab306ea"},"schema_version":"1.0"},"canonical_sha256":"03370e34a24cceda1c4374af9eaee7484c051016661caa9a05f7cfb0f7c86824","source":{"kind":"arxiv","id":"2604.16238","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.16238","created_at":"2026-07-13T01:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2604.16238v2","created_at":"2026-07-13T01:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.16238","created_at":"2026-07-13T01:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"AM3Q4NFCJTHN","created_at":"2026-07-13T01:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"AM3Q4NFCJTHNUHCD","created_at":"2026-07-13T01:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"AM3Q4NFC","created_at":"2026-07-13T01:20:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AM3Q4NFCJTHNUHCDOSXZ5LXHJB","target":"record","payload":{"canonical_record":{"source":{"id":"2604.16238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-17T16:58:06Z","cross_cats_sorted":["physics.ao-ph","stat.ML"],"title_canon_sha256":"bc2e2f8ed910dc823254bde7e59596f7dab2a7728f1c9b569576cb91074d6beb","abstract_canon_sha256":"bfd64ae730373de9ce0ff248ef05f37ebba4b35cfa64bd22f6083f87bab306ea"},"schema_version":"1.0"},"canonical_sha256":"03370e34a24cceda1c4374af9eaee7484c051016661caa9a05f7cfb0f7c86824","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:20:08.381182Z","signature_b64":"eHyPS2v3eEnbtBioHPFsdy7Le0FB9cN9JTGPB4gw/mx6uRVS3gYh/pfMt1UWuMAUmP+kEEWTuva4pxJxQFAdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03370e34a24cceda1c4374af9eaee7484c051016661caa9a05f7cfb0f7c86824","last_reissued_at":"2026-07-13T01:20:08.379558Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:20:08.379558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.16238","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-13T01:20:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CVdyUmbluxXxj40NZ1urvprcdEanH1gwK5m2pknMLWcIg4/kfg25SRTK7uotNQ+AwmkR3CxJbeaNVHYOIgD5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T21:06:54.574019Z"},"content_sha256":"8caf7e005b7934ae2486975a3778d6119911ae16f3e29976868db905e085cb10","schema_version":"1.0","event_id":"sha256:8caf7e005b7934ae2486975a3778d6119911ae16f3e29976868db905e085cb10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AM3Q4NFCJTHNUHCDOSXZ5LXHJB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing AI and Dynamical Subseasonal Forecasts with Probabilistic Bias Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Probabilistic bias correction doubles the subseasonal skill of AI weather forecasts and improves dynamical models for over 90 percent of key targets, winning an international competition.","cross_cats":["physics.ao-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Lu, Genevieve Flaspohler, Haiyu Dong, Hannah Guan, Jakob Schloer, Jeremy Berman, Jonathan A. Weyn, Joshua Talib, Judah Cohen, Lester Mackey, Paulo Orenstein, Soukayna Mouatadid, Zekun Ni","submitted_at":"2026-04-17T16:58:06Z","abstract_excerpt":"Decision-makers rely on weather forecasts to plant crops, manage wildfires, allocate water and energy, and prepare for weather extremes. Today, such forecasts enjoy unprecedented accuracy out to two weeks thanks to steady advances in physics-based dynamical models and data-driven artificial intelligence (AI) models. However, model skill drops precipitously at subseasonal timescales (2 - 6 weeks ahead), due to compounding errors, systemic model biases, and the chaotic nature of the atmosphere. To counter this degradation, we introduce probabilistic bias correction (PBC), a machine learning fram"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PBC doubles the subseasonal skill of the AI Forecasting System and improves the skill of the operationally-debiased dynamical model for 91% of pressure, 92% of temperature, and 98% of precipitation targets. In ECMWF's 2025 real-time forecasting competition, its global forecasts placed first for all weather variables and lead times.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That corrections learned from historical probabilistic forecasts will generalize to future unseen forecasts without overfitting or creating new biases at subseasonal lead times.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Probabilistic bias correction doubles AI subseasonal forecast skill and wins a 2025 international competition by correcting biases in ECMWF models for pressure, temperature, and precipitation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Probabilistic bias correction doubles the subseasonal skill of AI weather forecasts and improves dynamical models for over 90 percent of key targets, winning an international competition.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cdafd607319082811a7e66ded2d608c952a5b460f02c6c7999d0e3fd793edef2"},"source":{"id":"2604.16238","kind":"arxiv","version":2},"verdict":{"id":"88bc5755-8d03-4fd0-b94e-e0e563f615bd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T08:20:13.841874Z","strongest_claim":"PBC doubles the subseasonal skill of the AI Forecasting System and improves the skill of the operationally-debiased dynamical model for 91% of pressure, 92% of temperature, and 98% of precipitation targets. In ECMWF's 2025 real-time forecasting competition, its global forecasts placed first for all weather variables and lead times.","one_line_summary":"Probabilistic bias correction doubles AI subseasonal forecast skill and wins a 2025 international competition by correcting biases in ECMWF models for pressure, temperature, and precipitation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That corrections learned from historical probabilistic forecasts will generalize to future unseen forecasts without overfitting or creating new biases at subseasonal lead times.","pith_extraction_headline":"Probabilistic bias correction doubles the subseasonal skill of AI weather forecasts and improves dynamical models for over 90 percent of key targets, winning an international competition."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.16238/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"88bc5755-8d03-4fd0-b94e-e0e563f615bd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-13T01:20:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MMPN1v2Zdq/o/8/WA8MAdZU51q+CnkI9BGYXFrGE522sNvSClo8y6/ETOfnCDLraQDQ6+qCaXTEZFCQQHyRUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T21:06:54.574478Z"},"content_sha256":"a604b4d5c83a5408fab0b7718b9305885611f1cc6b5a600f6efc7b4b2d479a00","schema_version":"1.0","event_id":"sha256:a604b4d5c83a5408fab0b7718b9305885611f1cc6b5a600f6efc7b4b2d479a00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AM3Q4NFCJTHNUHCDOSXZ5LXHJB/bundle.json","state_url":"https://pith.science/pith/AM3Q4NFCJTHNUHCDOSXZ5LXHJB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AM3Q4NFCJTHNUHCDOSXZ5LXHJB/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":"2026-07-21T21:06:54Z","links":{"resolver":"https://pith.science/pith/AM3Q4NFCJTHNUHCDOSXZ5LXHJB","bundle":"https://pith.science/pith/AM3Q4NFCJTHNUHCDOSXZ5LXHJB/bundle.json","state":"https://pith.science/pith/AM3Q4NFCJTHNUHCDOSXZ5LXHJB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AM3Q4NFCJTHNUHCDOSXZ5LXHJB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AM3Q4NFCJTHNUHCDOSXZ5LXHJB","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":"bfd64ae730373de9ce0ff248ef05f37ebba4b35cfa64bd22f6083f87bab306ea","cross_cats_sorted":["physics.ao-ph","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-17T16:58:06Z","title_canon_sha256":"bc2e2f8ed910dc823254bde7e59596f7dab2a7728f1c9b569576cb91074d6beb"},"schema_version":"1.0","source":{"id":"2604.16238","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.16238","created_at":"2026-07-13T01:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2604.16238v2","created_at":"2026-07-13T01:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.16238","created_at":"2026-07-13T01:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"AM3Q4NFCJTHN","created_at":"2026-07-13T01:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"AM3Q4NFCJTHNUHCD","created_at":"2026-07-13T01:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"AM3Q4NFC","created_at":"2026-07-13T01:20:08Z"}],"graph_snapshots":[{"event_id":"sha256:a604b4d5c83a5408fab0b7718b9305885611f1cc6b5a600f6efc7b4b2d479a00","target":"graph","created_at":"2026-07-13T01:20:08Z","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":"PBC doubles the subseasonal skill of the AI Forecasting System and improves the skill of the operationally-debiased dynamical model for 91% of pressure, 92% of temperature, and 98% of precipitation targets. In ECMWF's 2025 real-time forecasting competition, its global forecasts placed first for all weather variables and lead times."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That corrections learned from historical probabilistic forecasts will generalize to future unseen forecasts without overfitting or creating new biases at subseasonal lead times."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Probabilistic bias correction doubles AI subseasonal forecast skill and wins a 2025 international competition by correcting biases in ECMWF models for pressure, temperature, and precipitation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Probabilistic bias correction doubles the subseasonal skill of AI weather forecasts and improves dynamical models for over 90 percent of key targets, winning an international competition."}],"snapshot_sha256":"cdafd607319082811a7e66ded2d608c952a5b460f02c6c7999d0e3fd793edef2"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.16238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decision-makers rely on weather forecasts to plant crops, manage wildfires, allocate water and energy, and prepare for weather extremes. Today, such forecasts enjoy unprecedented accuracy out to two weeks thanks to steady advances in physics-based dynamical models and data-driven artificial intelligence (AI) models. However, model skill drops precipitously at subseasonal timescales (2 - 6 weeks ahead), due to compounding errors, systemic model biases, and the chaotic nature of the atmosphere. To counter this degradation, we introduce probabilistic bias correction (PBC), a machine learning fram","authors_text":"Alex Lu, Genevieve Flaspohler, Haiyu Dong, Hannah Guan, Jakob Schloer, Jeremy Berman, Jonathan A. Weyn, Joshua Talib, Judah Cohen, Lester Mackey, Paulo Orenstein, Soukayna Mouatadid, Zekun Ni","cross_cats":["physics.ao-ph","stat.ML"],"headline":"Probabilistic bias correction doubles the subseasonal skill of AI weather forecasts and improves dynamical models for over 90 percent of key targets, winning an international competition.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-17T16:58:06Z","title":"Enhancing AI and Dynamical Subseasonal Forecasts with Probabilistic Bias Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.16238","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T08:20:13.841874Z","id":"88bc5755-8d03-4fd0-b94e-e0e563f615bd","model_set":{"reader":"grok-4.3"},"one_line_summary":"Probabilistic bias correction doubles AI subseasonal forecast skill and wins a 2025 international competition by correcting biases in ECMWF models for pressure, temperature, and precipitation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Probabilistic bias correction doubles the subseasonal skill of AI weather forecasts and improves dynamical models for over 90 percent of key targets, winning an international competition.","strongest_claim":"PBC doubles the subseasonal skill of the AI Forecasting System and improves the skill of the operationally-debiased dynamical model for 91% of pressure, 92% of temperature, and 98% of precipitation targets. In ECMWF's 2025 real-time forecasting competition, its global forecasts placed first for all weather variables and lead times.","weakest_assumption":"That corrections learned from historical probabilistic forecasts will generalize to future unseen forecasts without overfitting or creating new biases at subseasonal lead times."}},"verdict_id":"88bc5755-8d03-4fd0-b94e-e0e563f615bd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8caf7e005b7934ae2486975a3778d6119911ae16f3e29976868db905e085cb10","target":"record","created_at":"2026-07-13T01:20:08Z","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":"bfd64ae730373de9ce0ff248ef05f37ebba4b35cfa64bd22f6083f87bab306ea","cross_cats_sorted":["physics.ao-ph","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-17T16:58:06Z","title_canon_sha256":"bc2e2f8ed910dc823254bde7e59596f7dab2a7728f1c9b569576cb91074d6beb"},"schema_version":"1.0","source":{"id":"2604.16238","kind":"arxiv","version":2}},"canonical_sha256":"03370e34a24cceda1c4374af9eaee7484c051016661caa9a05f7cfb0f7c86824","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03370e34a24cceda1c4374af9eaee7484c051016661caa9a05f7cfb0f7c86824","first_computed_at":"2026-07-13T01:20:08.379558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:20:08.379558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eHyPS2v3eEnbtBioHPFsdy7Le0FB9cN9JTGPB4gw/mx6uRVS3gYh/pfMt1UWuMAUmP+kEEWTuva4pxJxQFAdCw==","signature_status":"signed_v1","signed_at":"2026-07-13T01:20:08.381182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.16238","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8caf7e005b7934ae2486975a3778d6119911ae16f3e29976868db905e085cb10","sha256:a604b4d5c83a5408fab0b7718b9305885611f1cc6b5a600f6efc7b4b2d479a00"],"state_sha256":"81080412a0ba5d82d33c7185b0198619aea6cb4e052c19de1adc6f8c049085b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2LKXgpBEauAmwzEWEgYHmNTG1ttP/MROPEzHv1tq6qOR/EO2MnR50nbcAMgYwLbdc5jJnB1woh2+q4jv15duBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T21:06:54.577067Z","bundle_sha256":"ff7116df4843e07e1d794188e0dd1001a726d200bf6e63923eb49054f03249f1"}}