{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EWKWJLMRXVAW5YBV3VNOLV5V4K","short_pith_number":"pith:EWKWJLMR","canonical_record":{"source":{"id":"2605.14285","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-14T02:34:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8a47747834d1180158498360f4ce7d9ea9c50abd86059acc879bcd8c53a4a070","abstract_canon_sha256":"9235ac073178336799eb257266eaee1579541f398321039cf17d6ab7d971d59f"},"schema_version":"1.0"},"canonical_sha256":"259564ad91bd416ee035dd5ae5d7b5e2988b855f0a2cccb0e315e23cbe32a573","source":{"kind":"arxiv","id":"2605.14285","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14285","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14285v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14285","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"EWKWJLMRXVAW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"EWKWJLMRXVAW5YBV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"EWKWJLMR","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EWKWJLMRXVAW5YBV3VNOLV5V4K","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14285","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-14T02:34:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8a47747834d1180158498360f4ce7d9ea9c50abd86059acc879bcd8c53a4a070","abstract_canon_sha256":"9235ac073178336799eb257266eaee1579541f398321039cf17d6ab7d971d59f"},"schema_version":"1.0"},"canonical_sha256":"259564ad91bd416ee035dd5ae5d7b5e2988b855f0a2cccb0e315e23cbe32a573","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:10.249241Z","signature_b64":"uXdT0a1obZPNpXv/l1UNah+xZ/QEiJvmI/8ghUj7vC+oCjj+OmhT4gkO+/9VawXttDWnC8QwqPHI3DiTl/v6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"259564ad91bd416ee035dd5ae5d7b5e2988b855f0a2cccb0e315e23cbe32a573","last_reissued_at":"2026-05-17T23:39:10.248725Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:10.248725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14285","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":"2026-05-17T23:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tpilHP4Tq8Q8rTIo5EM3LAwB7pZH+p11Fc9BJ6l2g3tMw2oskzVZiJ3ckYqIk8Goa4M4ydMlW34vWqOJwGQICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T05:53:07.623156Z"},"content_sha256":"5f7bfa2d214b7ff99b332ce4d9a00e01a7515eca4e4cd7c5db9876a4d9057341","schema_version":"1.0","event_id":"sha256:5f7bfa2d214b7ff99b332ce4d9a00e01a7515eca4e4cd7c5db9876a4d9057341"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EWKWJLMRXVAW5YBV3VNOLV5V4K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A single diffusion model learns joint trajectory priors to unify filtering and smoothing in data assimilation.","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Chanyong Jung, Haijie Yuan, Ismail Alkhouri, Jeffrey A Fessler, Lianghe Shi, Qing Qu, Saiprasad Ravishankar, Siyi Chen, Xiao Li, Yida Pan, Yixuan Jia, Yue Cynthia Wu","submitted_at":"2026-05-14T02:34:33Z","abstract_excerpt":"Data assimilation (DA) estimates the state of an evolving dynamical system from noisy, partial observations, and is widely used in scientific simulation as well as weather and climate science. In practice, filtering methods rely on frame-to-frame transition models. However, these models are fragile when observations are non-Markovian (when they form only a partial slice of a higher-dimensional latent state as in real-world weather data): they tend to accumulate errors over long horizons. At the same time, learned DA methods typically commit to a single regime, either filtering (nowcasting, rea"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across all settings, a single model is competitive with or outperforms both learned and classical baselines that are specialized for individual regimes, with the largest gains observed on real-world weather benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That assigning independent noise levels to each frame in a diffusion process allows the model to learn a joint-trajectory prior that captures long-horizon dependencies and avoids error accumulation for non-Markovian observations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ForcingDAS is a single diffusion-based model for data assimilation that unifies filtering and smoothing regimes via per-frame noise scheduling and reduces long-horizon error accumulation on non-Markovian observations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single diffusion model learns joint trajectory priors to unify filtering and smoothing in data assimilation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"061ec561a9e48d0c5d8cc7db60bf6a6c506f30c52d5e923f4fefd5877c92695b"},"source":{"id":"2605.14285","kind":"arxiv","version":1},"verdict":{"id":"d450ce24-a082-4740-b257-2c762b211566","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:34:43.689559Z","strongest_claim":"Across all settings, a single model is competitive with or outperforms both learned and classical baselines that are specialized for individual regimes, with the largest gains observed on real-world weather benchmarks.","one_line_summary":"ForcingDAS is a single diffusion-based model for data assimilation that unifies filtering and smoothing regimes via per-frame noise scheduling and reduces long-horizon error accumulation on non-Markovian observations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That assigning independent noise levels to each frame in a diffusion process allows the model to learn a joint-trajectory prior that captures long-horizon dependencies and avoids error accumulation for non-Markovian observations.","pith_extraction_headline":"A single diffusion model learns joint trajectory priors to unify filtering and smoothing in data assimilation."},"references":{"count":17,"sample":[{"doi":"10.48550/arxiv.2504.18720","year":2025,"title":"Appa: Bending weather dynamics with latent diffusion models for global data assimilation","work_id":"f6906f9b-4a55-40fc-8bf4-bf8c340a91c5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Sharp failure rates for the bootstrap particle filter in high dimensions","work_id":"e10c77c0-a0fb-4010-83b8-08b75b30c96c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2008,"title":"Closed-loop turbulence control: Progress and challenges","work_id":"8a875644-5d63-435e-ab63-45944934ba23","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1126/sciadv.aea4248","year":2025,"title":"Dataassimilation in the geosciences: An overview of methods, issues, and perspectives","work_id":"57822bc9-25cb-434c-9dc9-a44eec7e3786","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/tmi","year":1999,"title":"Efficient medical vision-language alignment through adapting masked vision models.IEEE Transactions on Medical Imaging, 44(11):4499–4510, November 2025","work_id":"5412d374-c88e-49c0-918b-a3e53568db59","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":17,"snapshot_sha256":"65906ab01ebf25ea43c89329980876215217847bd0d6f063dc818869554af35a","internal_anchors":1},"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":"d450ce24-a082-4740-b257-2c762b211566"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YamXtIP5XpC24poyBd0Pl35RIIeKb0wD1FPoT8hgDnMrD76f/wnL+tDnxqHPbEkw/v0KMd/I0CP1XIoQVp1kCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T05:53:07.623974Z"},"content_sha256":"48e0ca69522b34f89714af25723aae1a1d2eb12c31c6d48c0175d210daebf4ef","schema_version":"1.0","event_id":"sha256:48e0ca69522b34f89714af25723aae1a1d2eb12c31c6d48c0175d210daebf4ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWKWJLMRXVAW5YBV3VNOLV5V4K/bundle.json","state_url":"https://pith.science/pith/EWKWJLMRXVAW5YBV3VNOLV5V4K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWKWJLMRXVAW5YBV3VNOLV5V4K/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":"2026-06-04T05:53:07Z","links":{"resolver":"https://pith.science/pith/EWKWJLMRXVAW5YBV3VNOLV5V4K","bundle":"https://pith.science/pith/EWKWJLMRXVAW5YBV3VNOLV5V4K/bundle.json","state":"https://pith.science/pith/EWKWJLMRXVAW5YBV3VNOLV5V4K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWKWJLMRXVAW5YBV3VNOLV5V4K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EWKWJLMRXVAW5YBV3VNOLV5V4K","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":"9235ac073178336799eb257266eaee1579541f398321039cf17d6ab7d971d59f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-14T02:34:33Z","title_canon_sha256":"8a47747834d1180158498360f4ce7d9ea9c50abd86059acc879bcd8c53a4a070"},"schema_version":"1.0","source":{"id":"2605.14285","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14285","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14285v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14285","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"EWKWJLMRXVAW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"EWKWJLMRXVAW5YBV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"EWKWJLMR","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:48e0ca69522b34f89714af25723aae1a1d2eb12c31c6d48c0175d210daebf4ef","target":"graph","created_at":"2026-05-17T23:39:10Z","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":"Across all settings, a single model is competitive with or outperforms both learned and classical baselines that are specialized for individual regimes, with the largest gains observed on real-world weather benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That assigning independent noise levels to each frame in a diffusion process allows the model to learn a joint-trajectory prior that captures long-horizon dependencies and avoids error accumulation for non-Markovian observations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ForcingDAS is a single diffusion-based model for data assimilation that unifies filtering and smoothing regimes via per-frame noise scheduling and reduces long-horizon error accumulation on non-Markovian observations."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single diffusion model learns joint trajectory priors to unify filtering and smoothing in data assimilation."}],"snapshot_sha256":"061ec561a9e48d0c5d8cc7db60bf6a6c506f30c52d5e923f4fefd5877c92695b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Data assimilation (DA) estimates the state of an evolving dynamical system from noisy, partial observations, and is widely used in scientific simulation as well as weather and climate science. In practice, filtering methods rely on frame-to-frame transition models. However, these models are fragile when observations are non-Markovian (when they form only a partial slice of a higher-dimensional latent state as in real-world weather data): they tend to accumulate errors over long horizons. At the same time, learned DA methods typically commit to a single regime, either filtering (nowcasting, rea","authors_text":"Chanyong Jung, Haijie Yuan, Ismail Alkhouri, Jeffrey A Fessler, Lianghe Shi, Qing Qu, Saiprasad Ravishankar, Siyi Chen, Xiao Li, Yida Pan, Yixuan Jia, Yue Cynthia Wu","cross_cats":["cs.LG"],"headline":"A single diffusion model learns joint trajectory priors to unify filtering and smoothing in data assimilation.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-14T02:34:33Z","title":"ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing"},"references":{"count":17,"internal_anchors":1,"resolved_work":17,"sample":[{"cited_arxiv_id":"","doi":"10.48550/arxiv.2504.18720","is_internal_anchor":false,"ref_index":1,"title":"Appa: Bending weather dynamics with latent diffusion models for global data assimilation","work_id":"f6906f9b-4a55-40fc-8bf4-bf8c340a91c5","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Sharp failure rates for the bootstrap particle filter in high dimensions","work_id":"e10c77c0-a0fb-4010-83b8-08b75b30c96c","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Closed-loop turbulence control: Progress and challenges","work_id":"8a875644-5d63-435e-ab63-45944934ba23","year":2008},{"cited_arxiv_id":"","doi":"10.1126/sciadv.aea4248","is_internal_anchor":false,"ref_index":4,"title":"Dataassimilation in the geosciences: An overview of methods, issues, and perspectives","work_id":"57822bc9-25cb-434c-9dc9-a44eec7e3786","year":2025},{"cited_arxiv_id":"","doi":"10.1109/tmi","is_internal_anchor":false,"ref_index":5,"title":"Efficient medical vision-language alignment through adapting masked vision models.IEEE Transactions on Medical Imaging, 44(11):4499–4510, November 2025","work_id":"5412d374-c88e-49c0-918b-a3e53568db59","year":1999}],"snapshot_sha256":"65906ab01ebf25ea43c89329980876215217847bd0d6f063dc818869554af35a"},"source":{"id":"2605.14285","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:34:43.689559Z","id":"d450ce24-a082-4740-b257-2c762b211566","model_set":{"reader":"grok-4.3"},"one_line_summary":"ForcingDAS is a single diffusion-based model for data assimilation that unifies filtering and smoothing regimes via per-frame noise scheduling and reduces long-horizon error accumulation on non-Markovian observations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single diffusion model learns joint trajectory priors to unify filtering and smoothing in data assimilation.","strongest_claim":"Across all settings, a single model is competitive with or outperforms both learned and classical baselines that are specialized for individual regimes, with the largest gains observed on real-world weather benchmarks.","weakest_assumption":"That assigning independent noise levels to each frame in a diffusion process allows the model to learn a joint-trajectory prior that captures long-horizon dependencies and avoids error accumulation for non-Markovian observations."}},"verdict_id":"d450ce24-a082-4740-b257-2c762b211566"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5f7bfa2d214b7ff99b332ce4d9a00e01a7515eca4e4cd7c5db9876a4d9057341","target":"record","created_at":"2026-05-17T23:39:10Z","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":"9235ac073178336799eb257266eaee1579541f398321039cf17d6ab7d971d59f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-14T02:34:33Z","title_canon_sha256":"8a47747834d1180158498360f4ce7d9ea9c50abd86059acc879bcd8c53a4a070"},"schema_version":"1.0","source":{"id":"2605.14285","kind":"arxiv","version":1}},"canonical_sha256":"259564ad91bd416ee035dd5ae5d7b5e2988b855f0a2cccb0e315e23cbe32a573","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"259564ad91bd416ee035dd5ae5d7b5e2988b855f0a2cccb0e315e23cbe32a573","first_computed_at":"2026-05-17T23:39:10.248725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:10.248725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uXdT0a1obZPNpXv/l1UNah+xZ/QEiJvmI/8ghUj7vC+oCjj+OmhT4gkO+/9VawXttDWnC8QwqPHI3DiTl/v6Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:10.249241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14285","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f7bfa2d214b7ff99b332ce4d9a00e01a7515eca4e4cd7c5db9876a4d9057341","sha256:48e0ca69522b34f89714af25723aae1a1d2eb12c31c6d48c0175d210daebf4ef"],"state_sha256":"9ae6da3824920cbacbd78568bf646e550b851469083b66e2e9e0db00c548de0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4s2VhVjeVHCzN3ixBxsnprRmSK0TnGKm60WQ2lwYtaw6uaCcLDxEVfav5ewUzarw/hWJCaHOkOkmvg2nwbikCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T05:53:07.627478Z","bundle_sha256":"e3f3357f0167dec56b1b923e05a5b9191a3e7674a842eac12d83a16e9af5f988"}}