{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TD7DYQAMHNZO5SAQO4BD4754MK","short_pith_number":"pith:TD7DYQAM","schema_version":"1.0","canonical_sha256":"98fe3c400c3b72eec81077023e7fbc6281077b14fdc8e7a151bba92dabc899d7","source":{"kind":"arxiv","id":"2606.14081","version":3},"attestation_state":"computed","paper":{"title":"Clay-CNN Hybrids: Leveraging Geospatial Foundation Models as Auxiliary Context for Landslide Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Huong Binh Vu","submitted_at":"2026-06-12T03:57:18Z","abstract_excerpt":"Rapid post-event landslide mapping is essential for disaster response but remains difficult to automate due to extreme class imbalance. This study evaluates whether Clay v1.5, a Geospatial Foundation Model (GFM), can improve pixel-level landslide segmentation on the Landslide4Sense (L4S) benchmark, which contains 3,799 training chips with 14 Sentinel-2 and terrain bands and approximately 2% positive pixels. We compare three strategies: Clay as the primary encoder with multi-scale residual terrain fusion, a U-Net backbone augmented with Clay semantic context at the bottleneck, and a standard U-"},"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":"2606.14081","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-12T03:57:18Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"title_canon_sha256":"4bca8af276a6d299973b6b46246ab25ea37a4456b900e12248ade737a3585b61","abstract_canon_sha256":"6499c3e5888f5450d36d768683fca669e759f7f1edcda2b651546ff2e6c78bd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:00.655557Z","signature_b64":"h8mgsLny6/Nlz1i1NhY0cZccUQRE9MM82G4iTzXS9LnLnnQVJf1uOrWgcqQsmi2+1aZY9C5/0CquihXgolqyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98fe3c400c3b72eec81077023e7fbc6281077b14fdc8e7a151bba92dabc899d7","last_reissued_at":"2026-06-19T16:10:00.655102Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:00.655102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clay-CNN Hybrids: Leveraging Geospatial Foundation Models as Auxiliary Context for Landslide Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Huong Binh Vu","submitted_at":"2026-06-12T03:57:18Z","abstract_excerpt":"Rapid post-event landslide mapping is essential for disaster response but remains difficult to automate due to extreme class imbalance. This study evaluates whether Clay v1.5, a Geospatial Foundation Model (GFM), can improve pixel-level landslide segmentation on the Landslide4Sense (L4S) benchmark, which contains 3,799 training chips with 14 Sentinel-2 and terrain bands and approximately 2% positive pixels. We compare three strategies: Clay as the primary encoder with multi-scale residual terrain fusion, a U-Net backbone augmented with Clay semantic context at the bottleneck, and a standard U-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.14081","kind":"arxiv","version":3},"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/2606.14081/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":"2606.14081","created_at":"2026-06-19T16:10:00.655158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.14081v3","created_at":"2026-06-19T16:10:00.655158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.14081","created_at":"2026-06-19T16:10:00.655158+00:00"},{"alias_kind":"pith_short_12","alias_value":"TD7DYQAMHNZO","created_at":"2026-06-19T16:10:00.655158+00:00"},{"alias_kind":"pith_short_16","alias_value":"TD7DYQAMHNZO5SAQ","created_at":"2026-06-19T16:10:00.655158+00:00"},{"alias_kind":"pith_short_8","alias_value":"TD7DYQAM","created_at":"2026-06-19T16:10:00.655158+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TD7DYQAMHNZO5SAQO4BD4754MK","json":"https://pith.science/pith/TD7DYQAMHNZO5SAQO4BD4754MK.json","graph_json":"https://pith.science/api/pith-number/TD7DYQAMHNZO5SAQO4BD4754MK/graph.json","events_json":"https://pith.science/api/pith-number/TD7DYQAMHNZO5SAQO4BD4754MK/events.json","paper":"https://pith.science/paper/TD7DYQAM"},"agent_actions":{"view_html":"https://pith.science/pith/TD7DYQAMHNZO5SAQO4BD4754MK","download_json":"https://pith.science/pith/TD7DYQAMHNZO5SAQO4BD4754MK.json","view_paper":"https://pith.science/paper/TD7DYQAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.14081&json=true","fetch_graph":"https://pith.science/api/pith-number/TD7DYQAMHNZO5SAQO4BD4754MK/graph.json","fetch_events":"https://pith.science/api/pith-number/TD7DYQAMHNZO5SAQO4BD4754MK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TD7DYQAMHNZO5SAQO4BD4754MK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TD7DYQAMHNZO5SAQO4BD4754MK/action/storage_attestation","attest_author":"https://pith.science/pith/TD7DYQAMHNZO5SAQO4BD4754MK/action/author_attestation","sign_citation":"https://pith.science/pith/TD7DYQAMHNZO5SAQO4BD4754MK/action/citation_signature","submit_replication":"https://pith.science/pith/TD7DYQAMHNZO5SAQO4BD4754MK/action/replication_record"}},"created_at":"2026-06-19T16:10:00.655158+00:00","updated_at":"2026-06-19T16:10:00.655158+00:00"}