{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RCVWN2C6DIXAWN4DAKJOWVCXTH","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":"a0d6debeb403c8282110486e65d8cb549cd1e0911d4f09c7aad19272952c83cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T10:21:19Z","title_canon_sha256":"641bc8ce5da1cb84aaa3661a1e673821dede860f63447edb3e923c0a1380b6fd"},"schema_version":"1.0","source":{"id":"2501.06258","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06258","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06258v1","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06258","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"RCVWN2C6DIXA","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"RCVWN2C6DIXAWN4D","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"RCVWN2C6","created_at":"2026-07-05T10:00:00Z"}],"graph_snapshots":[{"event_id":"sha256:0f959010dca820309cdeed23a7275872779b01bc7e66f8a7ffdd204bc519a95a","target":"graph","created_at":"2026-07-05T10:00:00Z","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/2501.06258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bandit optimization is a difficult problem, especially if the reward model is high-dimensional. When rewards are modeled by neural networks, sublinear regret has only been shown under strong assumptions, usually when the network is extremely wide. In this thesis, we investigate how pre-training can help us in the regime of smaller models. We consider a stochastic contextual bandit with the rewards modeled by a multi-layer neural network. The last layer is a linear predictor, and the layers before it are a black box neural architecture, which we call a representation network. We model pre-train","authors_text":"Mikhail Terekhov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06258","kind":"arxiv","version":1},"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":"sha256:2f36cd40dcce352f903fdb5729e842329560865627f25bd4bbbbb291d4252654","target":"record","created_at":"2026-07-05T10:00:00Z","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":"a0d6debeb403c8282110486e65d8cb549cd1e0911d4f09c7aad19272952c83cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T10:21:19Z","title_canon_sha256":"641bc8ce5da1cb84aaa3661a1e673821dede860f63447edb3e923c0a1380b6fd"},"schema_version":"1.0","source":{"id":"2501.06258","kind":"arxiv","version":1}},"canonical_sha256":"88ab66e85e1a2e0b37830292eb545799c47c06f3930ee61bc244d49624415672","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88ab66e85e1a2e0b37830292eb545799c47c06f3930ee61bc244d49624415672","first_computed_at":"2026-07-05T10:00:00.008716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:00.008716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lOaeVP7uYE+fbux58exGwdIQXHA4SQe5UP+9et0XDXA7BZvCnYA4lzTiAJzS14P4ic3suee6hQ9wh6cti/aiBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:00.009147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06258","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f36cd40dcce352f903fdb5729e842329560865627f25bd4bbbbb291d4252654","sha256:0f959010dca820309cdeed23a7275872779b01bc7e66f8a7ffdd204bc519a95a"],"state_sha256":"f8faf89d08f9eaabb5380f82264c85a24e5975ff7bad36d5ffbc24cd6a279f35"}