{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DX3BNS5IHQMWUSRZ6J4CCRS5TE","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":"4be6adf8cdc9a519c4708792d5a2189e9150b6249b7d66ec42e18bad28d010a5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T11:10:44Z","title_canon_sha256":"2fc1b838bdcf9ce3db8424f3bfb3fd8e50005863e22ef286ae61b6e9dd0e2b60"},"schema_version":"1.0","source":{"id":"2605.18899","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18899","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18899v1","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18899","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"DX3BNS5IHQMW","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"DX3BNS5IHQMWUSRZ","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"DX3BNS5I","created_at":"2026-05-20T00:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:fe5ef573d87e03fe6336ba0348acff8cdf7d0f285feeacd5388f2c994b780a73","target":"graph","created_at":"2026-05-20T00:06:31Z","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/2605.18899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative LLM-based recommenders (LLM-Rec) require continual post-deployment updates, yet deployment logs provide only policy-shaped contextual bandit feedback: outcomes are observed solely for items exposed by a prior serving policy, inducing exposure bias and yielding partial, asymmetric signals consisting of relatively reliable positive responses and ambiguous no-responses. We propose an Anchored Bandit Policy Optimization (ABPO) framework for continual LLM-Rec updates that combines group-relative policy optimization (GRPO) with explicit treatment of exposure bias and feedback ambiguity. S","authors_text":"Chung Park, Hyeongjun Yun, Jaegul Choo, Taesan Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T11:10:44Z","title":"Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18899","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:bd3be29fac9a5bd761c31ae19ac85160324de6e5924f7248a7903657d36cea90","target":"record","created_at":"2026-05-20T00:06:31Z","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":"4be6adf8cdc9a519c4708792d5a2189e9150b6249b7d66ec42e18bad28d010a5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T11:10:44Z","title_canon_sha256":"2fc1b838bdcf9ce3db8424f3bfb3fd8e50005863e22ef286ae61b6e9dd0e2b60"},"schema_version":"1.0","source":{"id":"2605.18899","kind":"arxiv","version":1}},"canonical_sha256":"1df616cba83c196a4a39f27821465d993f1c5784d49fb70e29590437162152fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1df616cba83c196a4a39f27821465d993f1c5784d49fb70e29590437162152fe","first_computed_at":"2026-05-20T00:06:31.128071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:31.128071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yrNur30hD/DmMXCwmZVI8uuFA12GqTptIoTi8D2ORireDlMc2nM8bmffAK5W0MvGQ1m1MmUHZkkEP50BfpvVBQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:31.128856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18899","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd3be29fac9a5bd761c31ae19ac85160324de6e5924f7248a7903657d36cea90","sha256:fe5ef573d87e03fe6336ba0348acff8cdf7d0f285feeacd5388f2c994b780a73"],"state_sha256":"ed308036a6bfcc8d51f8148b94f8e459f8af4f4e85073b6590af2aca8cf759e6"}