{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F77BNENJ2I4QN5POWH6I7MCYB5","short_pith_number":"pith:F77BNENJ","schema_version":"1.0","canonical_sha256":"2ffe1691a9d23906f5eeb1fc8fb0580f53f1d05b6e78b5ea7047c4310458aa8f","source":{"kind":"arxiv","id":"2312.03606","version":2},"attestation_state":"computed","paper":{"title":"DiffusionSat: A Generative Foundation Model for Satellite Imagery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenlin Meng, David Lobell, Linqi Zhou, Marshall Burke, Patrick Liu, Robin Rombach, Samar Khanna, Stefano Ermon","submitted_at":"2023-12-06T16:53:17Z","abstract_excerpt":"Diffusion models have achieved state-of-the-art results on many modalities including images, speech, and video. However, existing models are not tailored to support remote sensing data, which is widely used in important applications including environmental monitoring and crop-yield prediction. Satellite images are significantly different from natural images -- they can be multi-spectral, irregularly sampled across time -- and existing diffusion models trained on images from the Web do not support them. Furthermore, remote sensing data is inherently spatio-temporal, requiring conditional genera"},"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":"2312.03606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T16:53:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b9196c15c0f98f74d7155faf82389ad3a6b3f3c948e53bdbfbd5d44bac5bd0d4","abstract_canon_sha256":"f2b66e0bec164e2b92bd9f5495bee436234323e00fffab7839724ee9675581f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:14.503785Z","signature_b64":"hT94pMfe5jBB+wY9oF5f2TK7pIeItLnAsNcPIbeQJBLqNwRHix2PjSCZD/GC0JSP/j1cD3Fe8Ng4/gWap9oGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ffe1691a9d23906f5eeb1fc8fb0580f53f1d05b6e78b5ea7047c4310458aa8f","last_reissued_at":"2026-07-05T08:23:14.503242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:14.503242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffusionSat: A Generative Foundation Model for Satellite Imagery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenlin Meng, David Lobell, Linqi Zhou, Marshall Burke, Patrick Liu, Robin Rombach, Samar Khanna, Stefano Ermon","submitted_at":"2023-12-06T16:53:17Z","abstract_excerpt":"Diffusion models have achieved state-of-the-art results on many modalities including images, speech, and video. However, existing models are not tailored to support remote sensing data, which is widely used in important applications including environmental monitoring and crop-yield prediction. Satellite images are significantly different from natural images -- they can be multi-spectral, irregularly sampled across time -- and existing diffusion models trained on images from the Web do not support them. Furthermore, remote sensing data is inherently spatio-temporal, requiring conditional genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03606","kind":"arxiv","version":2},"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/2312.03606/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":"2312.03606","created_at":"2026-07-05T08:23:14.503298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03606v2","created_at":"2026-07-05T08:23:14.503298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03606","created_at":"2026-07-05T08:23:14.503298+00:00"},{"alias_kind":"pith_short_12","alias_value":"F77BNENJ2I4Q","created_at":"2026-07-05T08:23:14.503298+00:00"},{"alias_kind":"pith_short_16","alias_value":"F77BNENJ2I4QN5PO","created_at":"2026-07-05T08:23:14.503298+00:00"},{"alias_kind":"pith_short_8","alias_value":"F77BNENJ","created_at":"2026-07-05T08:23:14.503298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05319","citing_title":"Steering Optimisation Trajectories in Diffusion Representation Learning","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31029","citing_title":"TerraDiT-$\\Omega$: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30168","citing_title":"OmniCD: A Foundational Framework for Remote Sensing Image Change Detection Guided by Multimodal Semantics","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00548","citing_title":"CAFOSat: A Strongly Annotated Dataset for Infrastructure-Aware CAFO Mapping Using High-Resolution Imagery","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02198","citing_title":"SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20090","citing_title":"MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modeling","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04678","citing_title":"ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2507.22101","citing_title":"AI in Agriculture: A Survey of Deep Learning Techniques for Crops, Fisheries and Livestock","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03239","citing_title":"COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02198","citing_title":"SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07092","citing_title":"Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Data","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22828","citing_title":"MetaEarth3D: Unlocking World-scale 3D Generation with Spatially Scalable Generative Modeling","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F77BNENJ2I4QN5POWH6I7MCYB5","json":"https://pith.science/pith/F77BNENJ2I4QN5POWH6I7MCYB5.json","graph_json":"https://pith.science/api/pith-number/F77BNENJ2I4QN5POWH6I7MCYB5/graph.json","events_json":"https://pith.science/api/pith-number/F77BNENJ2I4QN5POWH6I7MCYB5/events.json","paper":"https://pith.science/paper/F77BNENJ"},"agent_actions":{"view_html":"https://pith.science/pith/F77BNENJ2I4QN5POWH6I7MCYB5","download_json":"https://pith.science/pith/F77BNENJ2I4QN5POWH6I7MCYB5.json","view_paper":"https://pith.science/paper/F77BNENJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03606&json=true","fetch_graph":"https://pith.science/api/pith-number/F77BNENJ2I4QN5POWH6I7MCYB5/graph.json","fetch_events":"https://pith.science/api/pith-number/F77BNENJ2I4QN5POWH6I7MCYB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F77BNENJ2I4QN5POWH6I7MCYB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F77BNENJ2I4QN5POWH6I7MCYB5/action/storage_attestation","attest_author":"https://pith.science/pith/F77BNENJ2I4QN5POWH6I7MCYB5/action/author_attestation","sign_citation":"https://pith.science/pith/F77BNENJ2I4QN5POWH6I7MCYB5/action/citation_signature","submit_replication":"https://pith.science/pith/F77BNENJ2I4QN5POWH6I7MCYB5/action/replication_record"}},"created_at":"2026-07-05T08:23:14.503298+00:00","updated_at":"2026-07-05T08:23:14.503298+00:00"}