{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BKO3MWU3RHAC7FWWYLHQ4ZZGFE","short_pith_number":"pith:BKO3MWU3","schema_version":"1.0","canonical_sha256":"0a9db65a9b89c02f96d6c2cf0e672629000136cf48832da2209d3e6e3d7e78b0","source":{"kind":"arxiv","id":"2309.07207","version":2},"attestation_state":"computed","paper":{"title":"EarthPT: a time series foundation model for Earth Observation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["physics.geo-ph"],"primary_cat":"cs.LG","authors_text":"James E. Geach, Luke Fleming, Michael J. Smith","submitted_at":"2023-09-13T18:00:00Z","abstract_excerpt":"We introduce EarthPT -- an Earth Observation (EO) pretrained transformer. EarthPT is a 700 million parameter decoding transformer foundation model trained in an autoregressive self-supervised manner and developed specifically with EO use-cases in mind. We demonstrate that EarthPT is an effective forecaster that can accurately predict future pixel-level surface reflectances across the 400-2300 nm range well into the future. For example, forecasts of the evolution of the Normalised Difference Vegetation Index (NDVI) have a typical error of approximately 0.05 (over a natural range of -1 -> 1) at "},"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":"2309.07207","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-13T18:00:00Z","cross_cats_sorted":["physics.geo-ph"],"title_canon_sha256":"d9a3c99c0f99462bad8562f5e31f087a09453bf6da8f010ff421ce42c4686af4","abstract_canon_sha256":"225424d471febb7496f36cb2e7f11f1e1055109e23758107eacc2c621337a553"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:23.292246Z","signature_b64":"xpClekVPG7pNR5BnugE8kjdaVMpJLoc9NZJmErjdsO31F4tHsm6fCuoMwvqXn9WQdUd93NTi4+oyLczUucRLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a9db65a9b89c02f96d6c2cf0e672629000136cf48832da2209d3e6e3d7e78b0","last_reissued_at":"2026-07-05T07:32:23.291798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:23.291798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EarthPT: a time series foundation model for Earth Observation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["physics.geo-ph"],"primary_cat":"cs.LG","authors_text":"James E. Geach, Luke Fleming, Michael J. Smith","submitted_at":"2023-09-13T18:00:00Z","abstract_excerpt":"We introduce EarthPT -- an Earth Observation (EO) pretrained transformer. EarthPT is a 700 million parameter decoding transformer foundation model trained in an autoregressive self-supervised manner and developed specifically with EO use-cases in mind. We demonstrate that EarthPT is an effective forecaster that can accurately predict future pixel-level surface reflectances across the 400-2300 nm range well into the future. For example, forecasts of the evolution of the Normalised Difference Vegetation Index (NDVI) have a typical error of approximately 0.05 (over a natural range of -1 -> 1) at "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07207","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/2309.07207/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":"2309.07207","created_at":"2026-07-05T07:32:23.291852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07207v2","created_at":"2026-07-05T07:32:23.291852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07207","created_at":"2026-07-05T07:32:23.291852+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKO3MWU3RHAC","created_at":"2026-07-05T07:32:23.291852+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKO3MWU3RHAC7FWW","created_at":"2026-07-05T07:32:23.291852+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKO3MWU3","created_at":"2026-07-05T07:32:23.291852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20380","citing_title":"TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2511.10370","citing_title":"SHRUG-FM: Reliability-Aware Foundation Models for Earth Observation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24919","citing_title":"Agentic AI for Remote Sensing: Technical Challenges and Research Directions","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24919","citing_title":"Agentic AI for Remote Sensing: Technical Challenges and Research Directions","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21032","citing_title":"Unlocking Multi-Spectral Data for Multi-Modal Models with Guided Inputs and Chain-of-Thought Reasoning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKO3MWU3RHAC7FWWYLHQ4ZZGFE","json":"https://pith.science/pith/BKO3MWU3RHAC7FWWYLHQ4ZZGFE.json","graph_json":"https://pith.science/api/pith-number/BKO3MWU3RHAC7FWWYLHQ4ZZGFE/graph.json","events_json":"https://pith.science/api/pith-number/BKO3MWU3RHAC7FWWYLHQ4ZZGFE/events.json","paper":"https://pith.science/paper/BKO3MWU3"},"agent_actions":{"view_html":"https://pith.science/pith/BKO3MWU3RHAC7FWWYLHQ4ZZGFE","download_json":"https://pith.science/pith/BKO3MWU3RHAC7FWWYLHQ4ZZGFE.json","view_paper":"https://pith.science/paper/BKO3MWU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07207&json=true","fetch_graph":"https://pith.science/api/pith-number/BKO3MWU3RHAC7FWWYLHQ4ZZGFE/graph.json","fetch_events":"https://pith.science/api/pith-number/BKO3MWU3RHAC7FWWYLHQ4ZZGFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKO3MWU3RHAC7FWWYLHQ4ZZGFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKO3MWU3RHAC7FWWYLHQ4ZZGFE/action/storage_attestation","attest_author":"https://pith.science/pith/BKO3MWU3RHAC7FWWYLHQ4ZZGFE/action/author_attestation","sign_citation":"https://pith.science/pith/BKO3MWU3RHAC7FWWYLHQ4ZZGFE/action/citation_signature","submit_replication":"https://pith.science/pith/BKO3MWU3RHAC7FWWYLHQ4ZZGFE/action/replication_record"}},"created_at":"2026-07-05T07:32:23.291852+00:00","updated_at":"2026-07-05T07:32:23.291852+00:00"}