{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2LNTFXFRTAMCPQD4IHH7VH3VWK","short_pith_number":"pith:2LNTFXFR","schema_version":"1.0","canonical_sha256":"d2db32dcb1981827c07c41cffa9f75b290d032bd0c23a7d325dfebdb36ecb352","source":{"kind":"arxiv","id":"2503.20563","version":1},"attestation_state":"computed","paper":{"title":"TerraTorch: The Geospatial Foundation Models Toolkit","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Benedikt Blumenstiel, Bianca Zadrozny, Carlos Gomes, Daniela Szwarcman, Francesc Marti Escofet, Joao Lucas de Sousa Almeida, Naomi Simumba, Paolo Fraccaro, Pedro Henrique de Oliveira, Romeo Kienzler","submitted_at":"2025-03-26T13:59:29Z","abstract_excerpt":"TerraTorch is a fine-tuning and benchmarking toolkit for Geospatial Foundation Models built on PyTorch Lightning and tailored for satellite, weather, and climate data. It integrates domain-specific data modules, pre-defined tasks, and a modular model factory that pairs any backbone with diverse decoder heads. These components allow researchers and practitioners to fine-tune supported models in a no-code fashion by simply editing a training configuration. By consolidating best practices for model development and incorporating the automated hyperparameter optimization extension Iterate, TerraTor"},"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":"2503.20563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T13:59:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b28e21006b7a6f1f6d772063a2e961f41e824962b6a203fb8d427b181cb8f305","abstract_canon_sha256":"9360b405d15d534e926b1e26c510fdee2f9a00c967676ad0f84089e81b1abe2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:40.403839Z","signature_b64":"nF1tEr0azzOuRTmiN/PGJEipBKfhmyMF8pxsaaJUUBFQNvUAAlmnxBVIYZaRQkrG8JIyQEko4Zzw7qyKr/2rAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2db32dcb1981827c07c41cffa9f75b290d032bd0c23a7d325dfebdb36ecb352","last_reissued_at":"2026-07-05T10:39:40.403311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:40.403311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TerraTorch: The Geospatial Foundation Models Toolkit","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Benedikt Blumenstiel, Bianca Zadrozny, Carlos Gomes, Daniela Szwarcman, Francesc Marti Escofet, Joao Lucas de Sousa Almeida, Naomi Simumba, Paolo Fraccaro, Pedro Henrique de Oliveira, Romeo Kienzler","submitted_at":"2025-03-26T13:59:29Z","abstract_excerpt":"TerraTorch is a fine-tuning and benchmarking toolkit for Geospatial Foundation Models built on PyTorch Lightning and tailored for satellite, weather, and climate data. It integrates domain-specific data modules, pre-defined tasks, and a modular model factory that pairs any backbone with diverse decoder heads. These components allow researchers and practitioners to fine-tune supported models in a no-code fashion by simply editing a training configuration. By consolidating best practices for model development and incorporating the automated hyperparameter optimization extension Iterate, TerraTor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20563","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/2503.20563/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":"2503.20563","created_at":"2026-07-05T10:39:40.403378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20563v1","created_at":"2026-07-05T10:39:40.403378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20563","created_at":"2026-07-05T10:39:40.403378+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LNTFXFRTAMC","created_at":"2026-07-05T10:39:40.403378+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LNTFXFRTAMCPQD4","created_at":"2026-07-05T10:39:40.403378+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LNTFXFR","created_at":"2026-07-05T10:39:40.403378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12595","citing_title":"Emerging Flexible Designs for Geospatial Multimodal Foundation Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29134","citing_title":"Beyond Backscatter: AlphaEarth Land-Cover Priors for Rapid SAR Flood Segmentation Across Foundation Backbones","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10658","citing_title":"How to Embed Matters: Evaluation of EO Embedding Design Choices","ref_index":12,"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":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LNTFXFRTAMCPQD4IHH7VH3VWK","json":"https://pith.science/pith/2LNTFXFRTAMCPQD4IHH7VH3VWK.json","graph_json":"https://pith.science/api/pith-number/2LNTFXFRTAMCPQD4IHH7VH3VWK/graph.json","events_json":"https://pith.science/api/pith-number/2LNTFXFRTAMCPQD4IHH7VH3VWK/events.json","paper":"https://pith.science/paper/2LNTFXFR"},"agent_actions":{"view_html":"https://pith.science/pith/2LNTFXFRTAMCPQD4IHH7VH3VWK","download_json":"https://pith.science/pith/2LNTFXFRTAMCPQD4IHH7VH3VWK.json","view_paper":"https://pith.science/paper/2LNTFXFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20563&json=true","fetch_graph":"https://pith.science/api/pith-number/2LNTFXFRTAMCPQD4IHH7VH3VWK/graph.json","fetch_events":"https://pith.science/api/pith-number/2LNTFXFRTAMCPQD4IHH7VH3VWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LNTFXFRTAMCPQD4IHH7VH3VWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LNTFXFRTAMCPQD4IHH7VH3VWK/action/storage_attestation","attest_author":"https://pith.science/pith/2LNTFXFRTAMCPQD4IHH7VH3VWK/action/author_attestation","sign_citation":"https://pith.science/pith/2LNTFXFRTAMCPQD4IHH7VH3VWK/action/citation_signature","submit_replication":"https://pith.science/pith/2LNTFXFRTAMCPQD4IHH7VH3VWK/action/replication_record"}},"created_at":"2026-07-05T10:39:40.403378+00:00","updated_at":"2026-07-05T10:39:40.403378+00:00"}