{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2JDHXKAYJWQLMV6FJSH2M5ZAKT","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":"a76a6ed15663fd9eb988b996d144c570cd05051e98f49335d6d8b3ae698d1228","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T01:58:48Z","title_canon_sha256":"935f4f67589a8b5afdac16c0e2762295ed0c7f3cc925a66e226d536209e36e6c"},"schema_version":"1.0","source":{"id":"2506.01250","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01250","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01250v3","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01250","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_12","alias_value":"2JDHXKAYJWQL","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_16","alias_value":"2JDHXKAYJWQLMV6F","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_8","alias_value":"2JDHXKAY","created_at":"2026-06-04T01:08:29Z"}],"graph_snapshots":[{"event_id":"sha256:e73a666616c183dc804019bf6405cf6e8a8c4d111d8a507d8e85e38cdce42bf4","target":"graph","created_at":"2026-06-04T01:08:29Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Under standard assumptions, our algorithms achieve sublinear cumulative average regret of order O(d sqrt(sum_{t=1}^T sigma_t^2) + sqrt(d T)) for sufficiently wide neural networks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The neural networks must be sufficiently wide to approximate the unknown nonlinear utility functions, and the variance-aware exploration strategy must be effective when computed solely from last-layer gradients without requiring deeper network information."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Variance-aware neural dueling bandit algorithms achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(d T)) for wide networks on nonlinear utilities."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Variance-aware neural algorithms for contextual dueling bandits achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(dT))."}],"snapshot_sha256":"c104f98bf241e905f2687818ee7de2e43023026b31b600f38ec46d3306a09bdb"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.01250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the first variance-aware algorithms for contextual dueling bandits that leverage shallow exploration strategies with neural networks for nonlinear utility approximation. A key theoretical challenge is the absence of a closed-form estimator, which led prior work to require an extremely large network width $m$ (i.e., $m = \\widetilde{\\Omega}(T^{14})$). We address this constraint with a novel analytical approach that combines iterative self-improvement with spectral analysis. Our analysis significantly reduces the network width requirement to $m = \\widetilde{\\Omega}(T^{6})$, and shows","authors_text":"Jaemin Park, Jinje Park, Taejin Paik, Youngmin Oh","cross_cats":["stat.ML"],"headline":"Variance-aware neural algorithms for contextual dueling bandits achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(dT)).","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T01:58:48Z","title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01250","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-19T11:26:03.213117Z","id":"5d7dd0d9-1dd4-48f6-9834-7aab0d65d1c9","model_set":{"reader":"grok-4.3"},"one_line_summary":"Variance-aware neural dueling bandit algorithms achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(d T)) for wide networks on nonlinear utilities.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Variance-aware neural algorithms for contextual dueling bandits achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(dT)).","strongest_claim":"Under standard assumptions, our algorithms achieve sublinear cumulative average regret of order O(d sqrt(sum_{t=1}^T sigma_t^2) + sqrt(d T)) for sufficiently wide neural networks.","weakest_assumption":"The neural networks must be sufficiently wide to approximate the unknown nonlinear utility functions, and the variance-aware exploration strategy must be effective when computed solely from last-layer gradients without requiring deeper network information."}},"verdict_id":"5d7dd0d9-1dd4-48f6-9834-7aab0d65d1c9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dfbc33b07e88b0242a8604fe2a6374aee6b640ddcc590863cbb8cd7b0f9751ba","target":"record","created_at":"2026-06-04T01:08:29Z","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":"a76a6ed15663fd9eb988b996d144c570cd05051e98f49335d6d8b3ae698d1228","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T01:58:48Z","title_canon_sha256":"935f4f67589a8b5afdac16c0e2762295ed0c7f3cc925a66e226d536209e36e6c"},"schema_version":"1.0","source":{"id":"2506.01250","kind":"arxiv","version":3}},"canonical_sha256":"d2467ba8184da0b657c54c8fa6772054fcb519793c13ac6467754da944458d2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2467ba8184da0b657c54c8fa6772054fcb519793c13ac6467754da944458d2e","first_computed_at":"2026-06-04T01:08:29.442894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:29.442894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JE8kJRdnwPE1LHiisUb2gRwbrYkHw7UYOjo3Kc14iBsj+7OhHHlgTSpRdrl1eWNS5UCB+lEjh8TYtQALfIgWBQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:29.443460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01250","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfbc33b07e88b0242a8604fe2a6374aee6b640ddcc590863cbb8cd7b0f9751ba","sha256:e73a666616c183dc804019bf6405cf6e8a8c4d111d8a507d8e85e38cdce42bf4"],"state_sha256":"acc9bfb4fae2f084b1ba4adba4ec1424d1d610bebbef9e4301f1cb577e06c278"}