{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M2R3GWYAMU3BR4FDUTFQLUGWW7","short_pith_number":"pith:M2R3GWYA","schema_version":"1.0","canonical_sha256":"66a3b35b00653618f0a3a4cb05d0d6b7ec86cb3b3c22d26121e0e8cd5c9e17bc","source":{"kind":"arxiv","id":"2405.00879","version":1},"attestation_state":"computed","paper":{"title":"Machine Learning Techniques for Data Reduction of Climate Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Anand Rangarajan, Jaemoon Lee, Qian Gong, Sanjay Ranka, Scott Klasky, Xiao Li","submitted_at":"2024-05-01T21:44:47Z","abstract_excerpt":"Scientists conduct large-scale simulations to compute derived quantities-of-interest (QoI) from primary data. Often, QoI are linked to specific features, regions, or time intervals, such that data can be adaptively reduced without compromising the integrity of QoI. For many spatiotemporal applications, these QoI are binary in nature and represent presence or absence of a physical phenomenon. We present a pipelined compression approach that first uses neural-network-based techniques to derive regions where QoI are highly likely to be present. Then, we employ a Guaranteed Autoencoder (GAE) to co"},"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":"2405.00879","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-01T21:44:47Z","cross_cats_sorted":["physics.ao-ph"],"title_canon_sha256":"ebf7a18e16c6df78b65c89a0e5aee647a9f7f1f65a8d6a6f5a0f27677746c41c","abstract_canon_sha256":"5ca09975e717390efdac98751664cd3a669d41572295bd432da5bf2ef0192b29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:27.461741Z","signature_b64":"eZxqDFnC/qEEofnVk7iJMUqWzmo8H0A1vUjbfuh3s4WZvtdf36rQctNd0Ra0TNJoCZTHETmdHmmQmFc7sqRzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66a3b35b00653618f0a3a4cb05d0d6b7ec86cb3b3c22d26121e0e8cd5c9e17bc","last_reissued_at":"2026-07-05T08:14:27.461248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:27.461248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning Techniques for Data Reduction of Climate Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Anand Rangarajan, Jaemoon Lee, Qian Gong, Sanjay Ranka, Scott Klasky, Xiao Li","submitted_at":"2024-05-01T21:44:47Z","abstract_excerpt":"Scientists conduct large-scale simulations to compute derived quantities-of-interest (QoI) from primary data. Often, QoI are linked to specific features, regions, or time intervals, such that data can be adaptively reduced without compromising the integrity of QoI. For many spatiotemporal applications, these QoI are binary in nature and represent presence or absence of a physical phenomenon. We present a pipelined compression approach that first uses neural-network-based techniques to derive regions where QoI are highly likely to be present. Then, we employ a Guaranteed Autoencoder (GAE) to co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00879","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/2405.00879/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":"2405.00879","created_at":"2026-07-05T08:14:27.461311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00879v1","created_at":"2026-07-05T08:14:27.461311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00879","created_at":"2026-07-05T08:14:27.461311+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2R3GWYAMU3B","created_at":"2026-07-05T08:14:27.461311+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2R3GWYAMU3BR4FD","created_at":"2026-07-05T08:14:27.461311+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2R3GWYA","created_at":"2026-07-05T08:14:27.461311+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02129","citing_title":"Generative Latent Diffusion for Efficient Spatiotemporal Data Reduction","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2R3GWYAMU3BR4FDUTFQLUGWW7","json":"https://pith.science/pith/M2R3GWYAMU3BR4FDUTFQLUGWW7.json","graph_json":"https://pith.science/api/pith-number/M2R3GWYAMU3BR4FDUTFQLUGWW7/graph.json","events_json":"https://pith.science/api/pith-number/M2R3GWYAMU3BR4FDUTFQLUGWW7/events.json","paper":"https://pith.science/paper/M2R3GWYA"},"agent_actions":{"view_html":"https://pith.science/pith/M2R3GWYAMU3BR4FDUTFQLUGWW7","download_json":"https://pith.science/pith/M2R3GWYAMU3BR4FDUTFQLUGWW7.json","view_paper":"https://pith.science/paper/M2R3GWYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00879&json=true","fetch_graph":"https://pith.science/api/pith-number/M2R3GWYAMU3BR4FDUTFQLUGWW7/graph.json","fetch_events":"https://pith.science/api/pith-number/M2R3GWYAMU3BR4FDUTFQLUGWW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2R3GWYAMU3BR4FDUTFQLUGWW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2R3GWYAMU3BR4FDUTFQLUGWW7/action/storage_attestation","attest_author":"https://pith.science/pith/M2R3GWYAMU3BR4FDUTFQLUGWW7/action/author_attestation","sign_citation":"https://pith.science/pith/M2R3GWYAMU3BR4FDUTFQLUGWW7/action/citation_signature","submit_replication":"https://pith.science/pith/M2R3GWYAMU3BR4FDUTFQLUGWW7/action/replication_record"}},"created_at":"2026-07-05T08:14:27.461311+00:00","updated_at":"2026-07-05T08:14:27.461311+00:00"}