{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JD26GFBOB5MVHERGI34ZAEAYJL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ce39f24aeb2f2bc8a33c2f74dba39416f422d05027316d341c8009fc39761849","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T18:54:43Z","title_canon_sha256":"c4f6f002a0579b068eb8a2b38140a165e6c7cabba10389882ce1718046f357b1"},"schema_version":"1.0","source":{"id":"2311.07565","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07565","created_at":"2026-06-05T01:14:24Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07565v3","created_at":"2026-06-05T01:14:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07565","created_at":"2026-06-05T01:14:24Z"},{"alias_kind":"pith_short_12","alias_value":"JD26GFBOB5MV","created_at":"2026-06-05T01:14:24Z"},{"alias_kind":"pith_short_16","alias_value":"JD26GFBOB5MVHERG","created_at":"2026-06-05T01:14:24Z"},{"alias_kind":"pith_short_8","alias_value":"JD26GFBO","created_at":"2026-06-05T01:14:24Z"}],"graph_snapshots":[{"event_id":"sha256:a13103ff6fa8af87ce747694a960e26ecd4995fcaf3a8bdb11dddc47b67a66fb","target":"graph","created_at":"2026-06-05T01:14:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.07565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce exploration via linear loss perturbations (EVILL), a randomised exploration method for structured stochastic bandit problems that works by solving for the minimiser of a linearly perturbed regularised negative log-likelihood function. We show that, for the case of generalised linear bandits, EVILL reduces to perturbed history exploration (PHE), a method where exploration is done by training on randomly perturbed rewards. In doing so, we provide a simple and clean explanation of when and why random reward perturbations give rise to good bandit algorithms. We propose data-dependent ","authors_text":"Alex Ayoub, Csaba Szepesv\\'ari, David Janz, Shuai Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T18:54:43Z","title":"Exploration via linearly perturbed loss minimisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07565","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:55455dfc8bed5c5e79245048532ed6beb0fd2a6998c5ceb694287e9f325da69f","target":"record","created_at":"2026-06-05T01:14:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ce39f24aeb2f2bc8a33c2f74dba39416f422d05027316d341c8009fc39761849","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T18:54:43Z","title_canon_sha256":"c4f6f002a0579b068eb8a2b38140a165e6c7cabba10389882ce1718046f357b1"},"schema_version":"1.0","source":{"id":"2311.07565","kind":"arxiv","version":3}},"canonical_sha256":"48f5e3142e0f5953922646f99010184ae6f8325dab5c1a3b3ec4b4c7a925f097","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48f5e3142e0f5953922646f99010184ae6f8325dab5c1a3b3ec4b4c7a925f097","first_computed_at":"2026-06-05T01:14:24.046168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:24.046168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JS7LTtXg9o0TAt1vbeG40Y8vqIWadc00z2uGERNjyrKthIcAUsrFaFOtJihQaWe+0bDcrQGyv/pPBIk8QPpaDw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:24.047008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07565","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55455dfc8bed5c5e79245048532ed6beb0fd2a6998c5ceb694287e9f325da69f","sha256:a13103ff6fa8af87ce747694a960e26ecd4995fcaf3a8bdb11dddc47b67a66fb"],"state_sha256":"bba60976369dc51dfd6180109112730c855ed7af12ee0de0546efcebfb85f4d3"}