{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:62G7WC4BNBMCLTHKFVNNLZM4NA","short_pith_number":"pith:62G7WC4B","schema_version":"1.0","canonical_sha256":"f68dfb0b81685825ccea2d5ad5e59c68358bb69ff8e04aae3076c8cd9314a277","source":{"kind":"arxiv","id":"2412.13394","version":2},"attestation_state":"computed","paper":{"title":"Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Burak Ekim, Caleb Robinson, Gilles Hacheme, Girmaw Abebe Tadesse, Juan M. Lavista Ferres, Michael Schmitt, Rahul Dodhia","submitted_at":"2024-12-18T00:10:44Z","abstract_excerpt":"Training robust deep learning models is crucial in Earth Observation, where globally deployed models often face distribution shifts that degrade performance, especially in low-data regions. Out-of-distribution (OOD) detection addresses this by identifying inputs that deviate from in-distribution (ID) data. However, existing methods either assume access to OOD data or compromise primary task performance, limiting real-world use. We introduce TARDIS, a post-hoc OOD detection method designed for scalable geospatial deployment. Our core innovation lies in generating surrogate distribution labels b"},"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":"2412.13394","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T00:10:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"90aa870b5282ebd0a300a9b2528fa54739b6423100a22415a1caa1062c94ab48","abstract_canon_sha256":"e0005716844624c8ed1b0523be1a5fa104dd847b79e12f3084a152885c5cc20d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:22.164807Z","signature_b64":"m9rqUr9pHed1zVHIn1L87bJp55vp5vEI66PsJUOrlWmbqbUFFI06rAAUFqeqgTpg0SSxoA3X/VhvWRxCWFrjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f68dfb0b81685825ccea2d5ad5e59c68358bb69ff8e04aae3076c8cd9314a277","last_reissued_at":"2026-07-05T10:46:22.164262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:22.164262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Burak Ekim, Caleb Robinson, Gilles Hacheme, Girmaw Abebe Tadesse, Juan M. Lavista Ferres, Michael Schmitt, Rahul Dodhia","submitted_at":"2024-12-18T00:10:44Z","abstract_excerpt":"Training robust deep learning models is crucial in Earth Observation, where globally deployed models often face distribution shifts that degrade performance, especially in low-data regions. Out-of-distribution (OOD) detection addresses this by identifying inputs that deviate from in-distribution (ID) data. However, existing methods either assume access to OOD data or compromise primary task performance, limiting real-world use. We introduce TARDIS, a post-hoc OOD detection method designed for scalable geospatial deployment. Our core innovation lies in generating surrogate distribution labels b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13394","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/2412.13394/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":"2412.13394","created_at":"2026-07-05T10:46:22.164326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13394v2","created_at":"2026-07-05T10:46:22.164326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13394","created_at":"2026-07-05T10:46:22.164326+00:00"},{"alias_kind":"pith_short_12","alias_value":"62G7WC4BNBMC","created_at":"2026-07-05T10:46:22.164326+00:00"},{"alias_kind":"pith_short_16","alias_value":"62G7WC4BNBMCLTHK","created_at":"2026-07-05T10:46:22.164326+00:00"},{"alias_kind":"pith_short_8","alias_value":"62G7WC4B","created_at":"2026-07-05T10:46:22.164326+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/62G7WC4BNBMCLTHKFVNNLZM4NA","json":"https://pith.science/pith/62G7WC4BNBMCLTHKFVNNLZM4NA.json","graph_json":"https://pith.science/api/pith-number/62G7WC4BNBMCLTHKFVNNLZM4NA/graph.json","events_json":"https://pith.science/api/pith-number/62G7WC4BNBMCLTHKFVNNLZM4NA/events.json","paper":"https://pith.science/paper/62G7WC4B"},"agent_actions":{"view_html":"https://pith.science/pith/62G7WC4BNBMCLTHKFVNNLZM4NA","download_json":"https://pith.science/pith/62G7WC4BNBMCLTHKFVNNLZM4NA.json","view_paper":"https://pith.science/paper/62G7WC4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13394&json=true","fetch_graph":"https://pith.science/api/pith-number/62G7WC4BNBMCLTHKFVNNLZM4NA/graph.json","fetch_events":"https://pith.science/api/pith-number/62G7WC4BNBMCLTHKFVNNLZM4NA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62G7WC4BNBMCLTHKFVNNLZM4NA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62G7WC4BNBMCLTHKFVNNLZM4NA/action/storage_attestation","attest_author":"https://pith.science/pith/62G7WC4BNBMCLTHKFVNNLZM4NA/action/author_attestation","sign_citation":"https://pith.science/pith/62G7WC4BNBMCLTHKFVNNLZM4NA/action/citation_signature","submit_replication":"https://pith.science/pith/62G7WC4BNBMCLTHKFVNNLZM4NA/action/replication_record"}},"created_at":"2026-07-05T10:46:22.164326+00:00","updated_at":"2026-07-05T10:46:22.164326+00:00"}