{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I5VY6ONYE7DPPF5L542CLDHREF","short_pith_number":"pith:I5VY6ONY","schema_version":"1.0","canonical_sha256":"476b8f39b827c6f797abef34258cf12159096078ea2119688b0fddc421756090","source":{"kind":"arxiv","id":"2405.15661","version":2},"attestation_state":"computed","paper":{"title":"Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"David Martens, James Hinns","submitted_at":"2024-05-24T15:58:02Z","abstract_excerpt":"The rise of deep learning in image classification has brought unprecedented accuracy but also highlighted a key issue: the use of 'shortcuts' by models. Such shortcuts are easy-to-learn patterns from the training data that fail to generalise to new data. Examples include the use of a copyright watermark to recognise horses, snowy background to recognise huskies, or ink markings to detect malignant skin lesions. The explainable AI (XAI) community has suggested using instance-level explanations to detect shortcuts without external data, but this requires the examination of many explanations to c"},"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":"2405.15661","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T15:58:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e77def08d6369746ef27ec382133652b8aeecb5a98044664dc8cc7546d2f37c","abstract_canon_sha256":"8fecf5da1a8484b3d610c80d2102b0e3c51df465f0a7de42e4ccc9b72167bcb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:40.868564Z","signature_b64":"J9UNMuBNoPMFTRz40vakRR9IMYcVg61LvlcqCQZM+emYRrpQbdOQAmCTvWOnvKxfRu/ObYXhg6gCImfoI+KhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"476b8f39b827c6f797abef34258cf12159096078ea2119688b0fddc421756090","last_reissued_at":"2026-07-05T10:06:40.868169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:40.868169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"David Martens, James Hinns","submitted_at":"2024-05-24T15:58:02Z","abstract_excerpt":"The rise of deep learning in image classification has brought unprecedented accuracy but also highlighted a key issue: the use of 'shortcuts' by models. Such shortcuts are easy-to-learn patterns from the training data that fail to generalise to new data. Examples include the use of a copyright watermark to recognise horses, snowy background to recognise huskies, or ink markings to detect malignant skin lesions. The explainable AI (XAI) community has suggested using instance-level explanations to detect shortcuts without external data, but this requires the examination of many explanations to c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15661","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/2405.15661/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":"2405.15661","created_at":"2026-07-05T10:06:40.868225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15661v2","created_at":"2026-07-05T10:06:40.868225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15661","created_at":"2026-07-05T10:06:40.868225+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5VY6ONYE7DP","created_at":"2026-07-05T10:06:40.868225+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5VY6ONYE7DPPF5L","created_at":"2026-07-05T10:06:40.868225+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5VY6ONY","created_at":"2026-07-05T10:06:40.868225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23247","citing_title":"Aggregating Local Saliency Maps for Semi-Global Explainable Image Classification","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5VY6ONYE7DPPF5L542CLDHREF","json":"https://pith.science/pith/I5VY6ONYE7DPPF5L542CLDHREF.json","graph_json":"https://pith.science/api/pith-number/I5VY6ONYE7DPPF5L542CLDHREF/graph.json","events_json":"https://pith.science/api/pith-number/I5VY6ONYE7DPPF5L542CLDHREF/events.json","paper":"https://pith.science/paper/I5VY6ONY"},"agent_actions":{"view_html":"https://pith.science/pith/I5VY6ONYE7DPPF5L542CLDHREF","download_json":"https://pith.science/pith/I5VY6ONYE7DPPF5L542CLDHREF.json","view_paper":"https://pith.science/paper/I5VY6ONY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15661&json=true","fetch_graph":"https://pith.science/api/pith-number/I5VY6ONYE7DPPF5L542CLDHREF/graph.json","fetch_events":"https://pith.science/api/pith-number/I5VY6ONYE7DPPF5L542CLDHREF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5VY6ONYE7DPPF5L542CLDHREF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5VY6ONYE7DPPF5L542CLDHREF/action/storage_attestation","attest_author":"https://pith.science/pith/I5VY6ONYE7DPPF5L542CLDHREF/action/author_attestation","sign_citation":"https://pith.science/pith/I5VY6ONYE7DPPF5L542CLDHREF/action/citation_signature","submit_replication":"https://pith.science/pith/I5VY6ONYE7DPPF5L542CLDHREF/action/replication_record"}},"created_at":"2026-07-05T10:06:40.868225+00:00","updated_at":"2026-07-05T10:06:40.868225+00:00"}