{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZRAH5ISAIQOXC56YGK5PVGUVN4","short_pith_number":"pith:ZRAH5ISA","schema_version":"1.0","canonical_sha256":"cc407ea240441d7177d832bafa9a956f23999423c6b7d4a15af66948ffec0aed","source":{"kind":"arxiv","id":"2509.03176","version":1},"attestation_state":"computed","paper":{"title":"Systematic Evaluation of Attribution Methods: Eliminating Threshold Bias and Revealing Method-Dependent Performance Patterns","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Serra Aksoy","submitted_at":"2025-09-03T09:50:31Z","abstract_excerpt":"Attribution methods explain neural network predictions by identifying influential input features, but their evaluation suffers from threshold selection bias that can reverse method rankings and undermine conclusions. Current protocols binarize attribution maps at single thresholds, where threshold choice alone can alter rankings by over 200 percentage points. We address this flaw with a threshold-free framework that computes Area Under the Curve for Intersection over Union (AUC-IoU), capturing attribution quality across the full threshold spectrum. Evaluating seven attribution methods on derma"},"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":"2509.03176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T09:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"22bb481e3e4381451d214bbc08debc8b714371b29c6ebf2f292946073eefbd50","abstract_canon_sha256":"60c1ffd862c785915dc2c1b5a48954043651903862a98b3810342840d945e98f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:05.639697Z","signature_b64":"IdtPWvlsgxcCukYnv9F6AnHNBR+43uHrAU4MUwUKsqoL6dmFk/nUOJW2kOCeCMZCsVeznsmlbT/5aAgT6druCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc407ea240441d7177d832bafa9a956f23999423c6b7d4a15af66948ffec0aed","last_reissued_at":"2026-07-05T12:04:05.639205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:05.639205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Systematic Evaluation of Attribution Methods: Eliminating Threshold Bias and Revealing Method-Dependent Performance Patterns","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Serra Aksoy","submitted_at":"2025-09-03T09:50:31Z","abstract_excerpt":"Attribution methods explain neural network predictions by identifying influential input features, but their evaluation suffers from threshold selection bias that can reverse method rankings and undermine conclusions. Current protocols binarize attribution maps at single thresholds, where threshold choice alone can alter rankings by over 200 percentage points. We address this flaw with a threshold-free framework that computes Area Under the Curve for Intersection over Union (AUC-IoU), capturing attribution quality across the full threshold spectrum. Evaluating seven attribution methods on derma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03176","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/2509.03176/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":"2509.03176","created_at":"2026-07-05T12:04:05.639262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03176v1","created_at":"2026-07-05T12:04:05.639262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03176","created_at":"2026-07-05T12:04:05.639262+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRAH5ISAIQOX","created_at":"2026-07-05T12:04:05.639262+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRAH5ISAIQOXC56Y","created_at":"2026-07-05T12:04:05.639262+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRAH5ISA","created_at":"2026-07-05T12:04:05.639262+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/ZRAH5ISAIQOXC56YGK5PVGUVN4","json":"https://pith.science/pith/ZRAH5ISAIQOXC56YGK5PVGUVN4.json","graph_json":"https://pith.science/api/pith-number/ZRAH5ISAIQOXC56YGK5PVGUVN4/graph.json","events_json":"https://pith.science/api/pith-number/ZRAH5ISAIQOXC56YGK5PVGUVN4/events.json","paper":"https://pith.science/paper/ZRAH5ISA"},"agent_actions":{"view_html":"https://pith.science/pith/ZRAH5ISAIQOXC56YGK5PVGUVN4","download_json":"https://pith.science/pith/ZRAH5ISAIQOXC56YGK5PVGUVN4.json","view_paper":"https://pith.science/paper/ZRAH5ISA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03176&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRAH5ISAIQOXC56YGK5PVGUVN4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRAH5ISAIQOXC56YGK5PVGUVN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRAH5ISAIQOXC56YGK5PVGUVN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRAH5ISAIQOXC56YGK5PVGUVN4/action/storage_attestation","attest_author":"https://pith.science/pith/ZRAH5ISAIQOXC56YGK5PVGUVN4/action/author_attestation","sign_citation":"https://pith.science/pith/ZRAH5ISAIQOXC56YGK5PVGUVN4/action/citation_signature","submit_replication":"https://pith.science/pith/ZRAH5ISAIQOXC56YGK5PVGUVN4/action/replication_record"}},"created_at":"2026-07-05T12:04:05.639262+00:00","updated_at":"2026-07-05T12:04:05.639262+00:00"}