{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XPDYHPWSDUVU4UVQ7KMDA7EGAT","short_pith_number":"pith:XPDYHPWS","schema_version":"1.0","canonical_sha256":"bbc783bed21d2b4e52b0fa98307c8604e1182b29d14ff06ffad526053fc12333","source":{"kind":"arxiv","id":"2605.10165","version":2},"attestation_state":"computed","paper":{"title":"Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Aggregating standardized cross-validation losses produces reliable sample-level scores for detecting noisy labels.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Doohyun Park, Inhyuk Park","submitted_at":"2026-05-11T08:16:09Z","abstract_excerpt":"Noisy labels are common in large-scale medical imaging datasets due to inter-observer variability and ambiguous cases. We propose a statistically grounded and task-agnostic framework, Standardized Loss Aggregation (SLA), for detecting noisy labels at the sample level. SLA quantifies label reliability by aggregating standardized fold-level validation losses across repeated cross-validation runs. This formulation generalizes discrete hard-counting schemes into a continuous estimator that captures both the frequency and magnitude of performance deviations, yielding interpretable and statistically"},"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":"2605.10165","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:16:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff854aac1e5ed25536cacecaf436bb702a531e6a27ab0d4e58b4b1410b49903a","abstract_canon_sha256":"0fa739daa4a46bdafb0385bd4918802aa35318bbdb3d086df2cdafa6d6e54ded"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:20.894768Z","signature_b64":"fLiDaHLHwT4Vm4el5eLmrSOjkg/OnODdsyk2v4otRFEeOSrllUk6mX5Zqy65485r2mrxnxQuPCjz4g3enoKQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbc783bed21d2b4e52b0fa98307c8604e1182b29d14ff06ffad526053fc12333","last_reissued_at":"2026-05-21T01:05:20.893991Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:20.893991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Aggregating standardized cross-validation losses produces reliable sample-level scores for detecting noisy labels.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Doohyun Park, Inhyuk Park","submitted_at":"2026-05-11T08:16:09Z","abstract_excerpt":"Noisy labels are common in large-scale medical imaging datasets due to inter-observer variability and ambiguous cases. We propose a statistically grounded and task-agnostic framework, Standardized Loss Aggregation (SLA), for detecting noisy labels at the sample level. SLA quantifies label reliability by aggregating standardized fold-level validation losses across repeated cross-validation runs. This formulation generalizes discrete hard-counting schemes into a continuous estimator that captures both the frequency and magnitude of performance deviations, yielding interpretable and statistically"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SLA generalizes discrete hard-counting schemes into a continuous estimator that captures both the frequency and magnitude of performance deviations, yielding interpretable and statistically stable noisiness scores.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That deviations in fold-level validation losses across cross-validation runs are caused primarily by label noise rather than by model randomness, data split effects, or other unmodeled factors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SLA converts hard-counting of high-loss samples into a continuous noisiness score by standardizing fold-level validation losses and aggregating them over multiple cross-validation runs, showing better performance than baselines on fundus data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Aggregating standardized cross-validation losses produces reliable sample-level scores for detecting noisy labels.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6039bdddbc4af920c394f01f6b74388cdf76580b00ad62685e648e6137a3cb3c"},"source":{"id":"2605.10165","kind":"arxiv","version":2},"verdict":{"id":"7e2fe95e-f73b-4411-bd62-4e6390068d5b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T03:03:25.559556Z","strongest_claim":"SLA generalizes discrete hard-counting schemes into a continuous estimator that captures both the frequency and magnitude of performance deviations, yielding interpretable and statistically stable noisiness scores.","one_line_summary":"SLA converts hard-counting of high-loss samples into a continuous noisiness score by standardizing fold-level validation losses and aggregating them over multiple cross-validation runs, showing better performance than baselines on fundus data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That deviations in fold-level validation losses across cross-validation runs are caused primarily by label noise rather than by model randomness, data split effects, or other unmodeled factors.","pith_extraction_headline":"Aggregating standardized cross-validation losses produces reliable sample-level scores for detecting noisy labels."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10165/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T06:22:00.948767Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T15:39:14.066848Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T12:01:17.495592Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:38:21.616054Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"df4f8794a11a834459c471225f4ca0ef5c4cdf7635385944d1e034d2639775d5"},"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":"2605.10165","created_at":"2026-05-21T01:05:20.894092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.10165v2","created_at":"2026-05-21T01:05:20.894092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10165","created_at":"2026-05-21T01:05:20.894092+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPDYHPWSDUVU","created_at":"2026-05-21T01:05:20.894092+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPDYHPWSDUVU4UVQ","created_at":"2026-05-21T01:05:20.894092+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPDYHPWS","created_at":"2026-05-21T01:05:20.894092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.10165","citing_title":"Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10165","citing_title":"Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPDYHPWSDUVU4UVQ7KMDA7EGAT","json":"https://pith.science/pith/XPDYHPWSDUVU4UVQ7KMDA7EGAT.json","graph_json":"https://pith.science/api/pith-number/XPDYHPWSDUVU4UVQ7KMDA7EGAT/graph.json","events_json":"https://pith.science/api/pith-number/XPDYHPWSDUVU4UVQ7KMDA7EGAT/events.json","paper":"https://pith.science/paper/XPDYHPWS"},"agent_actions":{"view_html":"https://pith.science/pith/XPDYHPWSDUVU4UVQ7KMDA7EGAT","download_json":"https://pith.science/pith/XPDYHPWSDUVU4UVQ7KMDA7EGAT.json","view_paper":"https://pith.science/paper/XPDYHPWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.10165&json=true","fetch_graph":"https://pith.science/api/pith-number/XPDYHPWSDUVU4UVQ7KMDA7EGAT/graph.json","fetch_events":"https://pith.science/api/pith-number/XPDYHPWSDUVU4UVQ7KMDA7EGAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPDYHPWSDUVU4UVQ7KMDA7EGAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPDYHPWSDUVU4UVQ7KMDA7EGAT/action/storage_attestation","attest_author":"https://pith.science/pith/XPDYHPWSDUVU4UVQ7KMDA7EGAT/action/author_attestation","sign_citation":"https://pith.science/pith/XPDYHPWSDUVU4UVQ7KMDA7EGAT/action/citation_signature","submit_replication":"https://pith.science/pith/XPDYHPWSDUVU4UVQ7KMDA7EGAT/action/replication_record"}},"created_at":"2026-05-21T01:05:20.894092+00:00","updated_at":"2026-05-21T01:05:20.894092+00:00"}