{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TG6VGJSH62B4YXEKZQILP7LPOH","short_pith_number":"pith:TG6VGJSH","schema_version":"1.0","canonical_sha256":"99bd532647f683cc5c8acc10b7fd6f71d0c72defc10f2a5c038d455b53fa5dd0","source":{"kind":"arxiv","id":"2201.01203","version":2},"attestation_state":"computed","paper":{"title":"Quantifying Uncertainty in Deep Learning Approaches to Radio Galaxy Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.GA","cs.LG"],"primary_cat":"astro-ph.CO","authors_text":"Anna M. M. Scaife, Devina Mohan, Fiona Porter, Micah Bowles, Mike Walmsley","submitted_at":"2022-01-04T15:31:18Z","abstract_excerpt":"In this work we use variational inference to quantify the degree of uncertainty in deep learning model predictions of radio galaxy classification. We show that the level of model posterior variance for individual test samples is correlated with human uncertainty when labelling radio galaxies. We explore the model performance and uncertainty calibration for different weight priors and suggest that a sparse prior produces more well-calibrated uncertainty estimates. Using the posterior distributions for individual weights, we demonstrate that we can prune 30% of the fully-connected layer weights "},"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":"2201.01203","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.CO","submitted_at":"2022-01-04T15:31:18Z","cross_cats_sorted":["astro-ph.GA","cs.LG"],"title_canon_sha256":"64e69c930306f8cb82403478e79bfdb35772a22ac8071c1b287a5c00cfe40d68","abstract_canon_sha256":"c5746f24406fc0c09c42b4d975f0443064d0bf255926648a97d7a76073494187"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:16.164237Z","signature_b64":"XF9hHMrg8GqSnZnE5igpcKWx+XCEaw0qQCiIPPtFUiRyGc2dfUD6ca7hjwcuXLHGx9/JLpeUwmZmgrm1bT2pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99bd532647f683cc5c8acc10b7fd6f71d0c72defc10f2a5c038d455b53fa5dd0","last_reissued_at":"2026-07-05T03:55:16.163871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:16.163871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying Uncertainty in Deep Learning Approaches to Radio Galaxy Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.GA","cs.LG"],"primary_cat":"astro-ph.CO","authors_text":"Anna M. M. Scaife, Devina Mohan, Fiona Porter, Micah Bowles, Mike Walmsley","submitted_at":"2022-01-04T15:31:18Z","abstract_excerpt":"In this work we use variational inference to quantify the degree of uncertainty in deep learning model predictions of radio galaxy classification. We show that the level of model posterior variance for individual test samples is correlated with human uncertainty when labelling radio galaxies. We explore the model performance and uncertainty calibration for different weight priors and suggest that a sparse prior produces more well-calibrated uncertainty estimates. Using the posterior distributions for individual weights, we demonstrate that we can prune 30% of the fully-connected layer weights "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01203","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/2201.01203/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":"2201.01203","created_at":"2026-07-05T03:55:16.163925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.01203v2","created_at":"2026-07-05T03:55:16.163925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01203","created_at":"2026-07-05T03:55:16.163925+00:00"},{"alias_kind":"pith_short_12","alias_value":"TG6VGJSH62B4","created_at":"2026-07-05T03:55:16.163925+00:00"},{"alias_kind":"pith_short_16","alias_value":"TG6VGJSH62B4YXEK","created_at":"2026-07-05T03:55:16.163925+00:00"},{"alias_kind":"pith_short_8","alias_value":"TG6VGJSH","created_at":"2026-07-05T03:55:16.163925+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/TG6VGJSH62B4YXEKZQILP7LPOH","json":"https://pith.science/pith/TG6VGJSH62B4YXEKZQILP7LPOH.json","graph_json":"https://pith.science/api/pith-number/TG6VGJSH62B4YXEKZQILP7LPOH/graph.json","events_json":"https://pith.science/api/pith-number/TG6VGJSH62B4YXEKZQILP7LPOH/events.json","paper":"https://pith.science/paper/TG6VGJSH"},"agent_actions":{"view_html":"https://pith.science/pith/TG6VGJSH62B4YXEKZQILP7LPOH","download_json":"https://pith.science/pith/TG6VGJSH62B4YXEKZQILP7LPOH.json","view_paper":"https://pith.science/paper/TG6VGJSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.01203&json=true","fetch_graph":"https://pith.science/api/pith-number/TG6VGJSH62B4YXEKZQILP7LPOH/graph.json","fetch_events":"https://pith.science/api/pith-number/TG6VGJSH62B4YXEKZQILP7LPOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TG6VGJSH62B4YXEKZQILP7LPOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TG6VGJSH62B4YXEKZQILP7LPOH/action/storage_attestation","attest_author":"https://pith.science/pith/TG6VGJSH62B4YXEKZQILP7LPOH/action/author_attestation","sign_citation":"https://pith.science/pith/TG6VGJSH62B4YXEKZQILP7LPOH/action/citation_signature","submit_replication":"https://pith.science/pith/TG6VGJSH62B4YXEKZQILP7LPOH/action/replication_record"}},"created_at":"2026-07-05T03:55:16.163925+00:00","updated_at":"2026-07-05T03:55:16.163925+00:00"}