{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B6M2GK3HSWITOILC2DO2X45THV","short_pith_number":"pith:B6M2GK3H","schema_version":"1.0","canonical_sha256":"0f99a32b679591372162d0ddabf3b33d67c76e92c13cbb518e41e4f3e1f7847a","source":{"kind":"arxiv","id":"2409.09907","version":1},"attestation_state":"computed","paper":{"title":"Rapid Adaptation of Earth Observation Foundation Models for Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Freddie Kalaitzis, Karthick Panner Selvam, Raul Ramos-Pollan","submitted_at":"2024-09-16T00:42:45Z","abstract_excerpt":"This study investigates the efficacy of Low-Rank Adaptation (LoRA) in fine-tuning Earth Observation (EO) foundation models for flood segmentation. We hypothesize that LoRA, a parameter-efficient technique, can significantly accelerate the adaptation of large-scale EO models to this critical task while maintaining high performance. We apply LoRA to fine-tune a state-of-the-art EO foundation model pre-trained on diverse satellite imagery, using a curated dataset of flood events. Our results demonstrate that LoRA-based fine-tuning (r-256) improves F1 score by 6.66 points and IoU by 0.11 compared "},"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":"2409.09907","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T00:42:45Z","cross_cats_sorted":[],"title_canon_sha256":"c8eeaef97e6c1b2c1ece031156ed94f6b27d3b1ecd852d422eb000767994e5e2","abstract_canon_sha256":"b9d0cee8d2e43d717e34e714d3b1d2307e9b2b322dabcbc5527609e03f9727e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:16.120826Z","signature_b64":"bekmnuIwKkfRgbxjvzZecg4v/q4GyJRuALZvT10xirjNXkuuZlVvQcqR2cXJubHrJqiax7sNYkYfGlszQYKpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f99a32b679591372162d0ddabf3b33d67c76e92c13cbb518e41e4f3e1f7847a","last_reissued_at":"2026-07-05T09:07:16.120367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:16.120367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rapid Adaptation of Earth Observation Foundation Models for Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Freddie Kalaitzis, Karthick Panner Selvam, Raul Ramos-Pollan","submitted_at":"2024-09-16T00:42:45Z","abstract_excerpt":"This study investigates the efficacy of Low-Rank Adaptation (LoRA) in fine-tuning Earth Observation (EO) foundation models for flood segmentation. We hypothesize that LoRA, a parameter-efficient technique, can significantly accelerate the adaptation of large-scale EO models to this critical task while maintaining high performance. We apply LoRA to fine-tune a state-of-the-art EO foundation model pre-trained on diverse satellite imagery, using a curated dataset of flood events. Our results demonstrate that LoRA-based fine-tuning (r-256) improves F1 score by 6.66 points and IoU by 0.11 compared "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09907","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/2409.09907/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":"2409.09907","created_at":"2026-07-05T09:07:16.120426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09907v1","created_at":"2026-07-05T09:07:16.120426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09907","created_at":"2026-07-05T09:07:16.120426+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6M2GK3HSWIT","created_at":"2026-07-05T09:07:16.120426+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6M2GK3HSWITOILC","created_at":"2026-07-05T09:07:16.120426+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6M2GK3H","created_at":"2026-07-05T09:07:16.120426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24120","citing_title":"Flood Mapping from RGB imagery using a Vision Foundation Model","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6M2GK3HSWITOILC2DO2X45THV","json":"https://pith.science/pith/B6M2GK3HSWITOILC2DO2X45THV.json","graph_json":"https://pith.science/api/pith-number/B6M2GK3HSWITOILC2DO2X45THV/graph.json","events_json":"https://pith.science/api/pith-number/B6M2GK3HSWITOILC2DO2X45THV/events.json","paper":"https://pith.science/paper/B6M2GK3H"},"agent_actions":{"view_html":"https://pith.science/pith/B6M2GK3HSWITOILC2DO2X45THV","download_json":"https://pith.science/pith/B6M2GK3HSWITOILC2DO2X45THV.json","view_paper":"https://pith.science/paper/B6M2GK3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09907&json=true","fetch_graph":"https://pith.science/api/pith-number/B6M2GK3HSWITOILC2DO2X45THV/graph.json","fetch_events":"https://pith.science/api/pith-number/B6M2GK3HSWITOILC2DO2X45THV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6M2GK3HSWITOILC2DO2X45THV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6M2GK3HSWITOILC2DO2X45THV/action/storage_attestation","attest_author":"https://pith.science/pith/B6M2GK3HSWITOILC2DO2X45THV/action/author_attestation","sign_citation":"https://pith.science/pith/B6M2GK3HSWITOILC2DO2X45THV/action/citation_signature","submit_replication":"https://pith.science/pith/B6M2GK3HSWITOILC2DO2X45THV/action/replication_record"}},"created_at":"2026-07-05T09:07:16.120426+00:00","updated_at":"2026-07-05T09:07:16.120426+00:00"}