{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P56VHMEMJZCPAGTTJEC2VJN5R4","short_pith_number":"pith:P56VHMEM","schema_version":"1.0","canonical_sha256":"7f7d53b08c4e44f01a734905aaa5bd8f07a8d58d3ac4aa6c971ad08e14e07afa","source":{"kind":"arxiv","id":"2606.03493","version":1},"attestation_state":"computed","paper":{"title":"Low-Frequency Shortcuts in Texture-Driven Visual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cathy Hou, David Alvarez-Melis, Stratos Idreos, Utku \\c{S}irin","submitted_at":"2026-06-02T11:11:20Z","abstract_excerpt":"Neural networks suffer from shortcut learning, where learned features generalize well to the training set but not to in-distribution (ID) or out-of-distribution (OOD) test sets. Existing studies are all based on a few standard benchmarks, which are shape-driven. Numerous application domains, however, are texture-driven. In this work, we present shortcut learning analysis for texture-driven domains, and compare it with that of a standard benchmark. We show that texture-driven domains suffer from low-frequency shortcuts. They make the majority of their decisions based on a few low-frequency comp"},"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":"2606.03493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T11:11:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"37a8ecf4cad20ea4d45b9af6ca9c4f5f4eb31246f695bdbf90fa2918cb123426","abstract_canon_sha256":"810b9c0342eb0d95263ad0e06465277588edf66b27cb8dc55ac3a809449cf9b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:59.204011Z","signature_b64":"im7WzK02ee2dyLsgXZOiTUXItX9QBS++RfY8xoutYarHkIAS2mANZENjwEw1B9EU1tMfAPMSuaxy85XA7SogBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f7d53b08c4e44f01a734905aaa5bd8f07a8d58d3ac4aa6c971ad08e14e07afa","last_reissued_at":"2026-06-03T01:05:59.203630Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:59.203630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Frequency Shortcuts in Texture-Driven Visual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cathy Hou, David Alvarez-Melis, Stratos Idreos, Utku \\c{S}irin","submitted_at":"2026-06-02T11:11:20Z","abstract_excerpt":"Neural networks suffer from shortcut learning, where learned features generalize well to the training set but not to in-distribution (ID) or out-of-distribution (OOD) test sets. Existing studies are all based on a few standard benchmarks, which are shape-driven. Numerous application domains, however, are texture-driven. In this work, we present shortcut learning analysis for texture-driven domains, and compare it with that of a standard benchmark. We show that texture-driven domains suffer from low-frequency shortcuts. They make the majority of their decisions based on a few low-frequency comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03493","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/2606.03493/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":"2606.03493","created_at":"2026-06-03T01:05:59.203688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03493v1","created_at":"2026-06-03T01:05:59.203688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03493","created_at":"2026-06-03T01:05:59.203688+00:00"},{"alias_kind":"pith_short_12","alias_value":"P56VHMEMJZCP","created_at":"2026-06-03T01:05:59.203688+00:00"},{"alias_kind":"pith_short_16","alias_value":"P56VHMEMJZCPAGTT","created_at":"2026-06-03T01:05:59.203688+00:00"},{"alias_kind":"pith_short_8","alias_value":"P56VHMEM","created_at":"2026-06-03T01:05:59.203688+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/P56VHMEMJZCPAGTTJEC2VJN5R4","json":"https://pith.science/pith/P56VHMEMJZCPAGTTJEC2VJN5R4.json","graph_json":"https://pith.science/api/pith-number/P56VHMEMJZCPAGTTJEC2VJN5R4/graph.json","events_json":"https://pith.science/api/pith-number/P56VHMEMJZCPAGTTJEC2VJN5R4/events.json","paper":"https://pith.science/paper/P56VHMEM"},"agent_actions":{"view_html":"https://pith.science/pith/P56VHMEMJZCPAGTTJEC2VJN5R4","download_json":"https://pith.science/pith/P56VHMEMJZCPAGTTJEC2VJN5R4.json","view_paper":"https://pith.science/paper/P56VHMEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03493&json=true","fetch_graph":"https://pith.science/api/pith-number/P56VHMEMJZCPAGTTJEC2VJN5R4/graph.json","fetch_events":"https://pith.science/api/pith-number/P56VHMEMJZCPAGTTJEC2VJN5R4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P56VHMEMJZCPAGTTJEC2VJN5R4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P56VHMEMJZCPAGTTJEC2VJN5R4/action/storage_attestation","attest_author":"https://pith.science/pith/P56VHMEMJZCPAGTTJEC2VJN5R4/action/author_attestation","sign_citation":"https://pith.science/pith/P56VHMEMJZCPAGTTJEC2VJN5R4/action/citation_signature","submit_replication":"https://pith.science/pith/P56VHMEMJZCPAGTTJEC2VJN5R4/action/replication_record"}},"created_at":"2026-06-03T01:05:59.203688+00:00","updated_at":"2026-06-03T01:05:59.203688+00:00"}