{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K4QUIWSNT3BDDXVY3ZLT5EIXJ3","short_pith_number":"pith:K4QUIWSN","schema_version":"1.0","canonical_sha256":"5721445a4d9ec231deb8de573e91174ed4a689d200ebfe585af6de2e634c7cf6","source":{"kind":"arxiv","id":"2508.18018","version":1},"attestation_state":"computed","paper":{"title":"Learning from nature: insights into GraphDOP's representations of the Earth System","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.ao-ph","authors_text":"Anthony McNally, Eulalie Boucher, Ewan Pinnington, Mihai Alexe, Niels Bormann, Patrick Laloyaux, Peter Lean, Simon Lang","submitted_at":"2025-08-25T13:33:23Z","abstract_excerpt":"Through a series of experiments, we provide evidence that the GraphDOP model - trained solely on meteorological observations, using no prior knowledge - develops internal representations of the Earth System state, structure and dynamics as well as the characteristics of different observing systems. Firstly, we demonstrate that the network constructs a unified latent representation of the Earth System state which is common across different observation types. For example, cloud structures maintain physical consistency whether viewed in predictions for satellite radiances from different sensors, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.18018","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"physics.ao-ph","submitted_at":"2025-08-25T13:33:23Z","cross_cats_sorted":[],"title_canon_sha256":"e9cd572f436620a56b6a75a5d15c296e017eb0e2c9fb1fc35655c2ecf175e9b4","abstract_canon_sha256":"e6ba7e36a550ba61dc1848da7949b4b750c0025a56f66494f9741be88be75051"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:52.141821Z","signature_b64":"4LXLmit8/Pe2e6ErlwaA9S2QgskTzqfHbVKoIeV2muPZCcH6O5tDKOsIs05jmC/TCNsLvN1tR5e+x5iLKB/jDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5721445a4d9ec231deb8de573e91174ed4a689d200ebfe585af6de2e634c7cf6","last_reissued_at":"2026-07-05T11:58:52.141337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:52.141337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from nature: insights into GraphDOP's representations of the Earth System","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.ao-ph","authors_text":"Anthony McNally, Eulalie Boucher, Ewan Pinnington, Mihai Alexe, Niels Bormann, Patrick Laloyaux, Peter Lean, Simon Lang","submitted_at":"2025-08-25T13:33:23Z","abstract_excerpt":"Through a series of experiments, we provide evidence that the GraphDOP model - trained solely on meteorological observations, using no prior knowledge - develops internal representations of the Earth System state, structure and dynamics as well as the characteristics of different observing systems. Firstly, we demonstrate that the network constructs a unified latent representation of the Earth System state which is common across different observation types. For example, cloud structures maintain physical consistency whether viewed in predictions for satellite radiances from different sensors, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18018","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.18018/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.18018","created_at":"2026-07-05T11:58:52.141404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18018v1","created_at":"2026-07-05T11:58:52.141404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18018","created_at":"2026-07-05T11:58:52.141404+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4QUIWSNT3BD","created_at":"2026-07-05T11:58:52.141404+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4QUIWSNT3BDDXVY","created_at":"2026-07-05T11:58:52.141404+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4QUIWSN","created_at":"2026-07-05T11:58:52.141404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07879","citing_title":"Global reanalysis from observations alone with machine learning","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19093","citing_title":"AIFS-DOP: End-to-End Medium-Range Weather Prediction from Observations Alone with Machine Learning","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4QUIWSNT3BDDXVY3ZLT5EIXJ3","json":"https://pith.science/pith/K4QUIWSNT3BDDXVY3ZLT5EIXJ3.json","graph_json":"https://pith.science/api/pith-number/K4QUIWSNT3BDDXVY3ZLT5EIXJ3/graph.json","events_json":"https://pith.science/api/pith-number/K4QUIWSNT3BDDXVY3ZLT5EIXJ3/events.json","paper":"https://pith.science/paper/K4QUIWSN"},"agent_actions":{"view_html":"https://pith.science/pith/K4QUIWSNT3BDDXVY3ZLT5EIXJ3","download_json":"https://pith.science/pith/K4QUIWSNT3BDDXVY3ZLT5EIXJ3.json","view_paper":"https://pith.science/paper/K4QUIWSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18018&json=true","fetch_graph":"https://pith.science/api/pith-number/K4QUIWSNT3BDDXVY3ZLT5EIXJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/K4QUIWSNT3BDDXVY3ZLT5EIXJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4QUIWSNT3BDDXVY3ZLT5EIXJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4QUIWSNT3BDDXVY3ZLT5EIXJ3/action/storage_attestation","attest_author":"https://pith.science/pith/K4QUIWSNT3BDDXVY3ZLT5EIXJ3/action/author_attestation","sign_citation":"https://pith.science/pith/K4QUIWSNT3BDDXVY3ZLT5EIXJ3/action/citation_signature","submit_replication":"https://pith.science/pith/K4QUIWSNT3BDDXVY3ZLT5EIXJ3/action/replication_record"}},"created_at":"2026-07-05T11:58:52.141404+00:00","updated_at":"2026-07-05T11:58:52.141404+00:00"}