{"paper":{"title":"Temporal Task Diversity: Inductive Biases Under Non-Stationarity in Synthetic Sequence Modelling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Afiq Abdillah Effiezal Aswadi, Matthew Farrugia-Roberts, Oliver Britton, Ross Baker","submitted_at":"2026-05-18T12:12:16Z","abstract_excerpt":"Modern deep learning science often assumes that neural networks learn from a fixed data distribution. However, many practically important learning problems involve data distributions that change throughout training. How does such non-stationarity impact the inductive biases of deep learning towards models with different structural, generalisation, and safety properties? A fruitful testbed for studying inductive bias is in-context linear regression sequence modelling, where small transformers display strikingly different generalisation patterns depending on the diversity of the (fixed) training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18281","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/2605.18281/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.234148Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.936267Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6916c32dceb04f9fe353efcc73b12db01a1cf9f7ec16198b0aa021f940ecdfb4"},"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"}