{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DX3BNS5IHQMWUSRZ6J4CCRS5TE","short_pith_number":"pith:DX3BNS5I","canonical_record":{"source":{"id":"2605.18899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T11:10:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2fc1b838bdcf9ce3db8424f3bfb3fd8e50005863e22ef286ae61b6e9dd0e2b60","abstract_canon_sha256":"4be6adf8cdc9a519c4708792d5a2189e9150b6249b7d66ec42e18bad28d010a5"},"schema_version":"1.0"},"canonical_sha256":"1df616cba83c196a4a39f27821465d993f1c5784d49fb70e29590437162152fe","source":{"kind":"arxiv","id":"2605.18899","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DX3BNS5IHQMWUSRZ6J4CCRS5TE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T11:10:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2fc1b838bdcf9ce3db8424f3bfb3fd8e50005863e22ef286ae61b6e9dd0e2b60","abstract_canon_sha256":"4be6adf8cdc9a519c4708792d5a2189e9150b6249b7d66ec42e18bad28d010a5"},"schema_version":"1.0"},"canonical_sha256":"1df616cba83c196a4a39f27821465d993f1c5784d49fb70e29590437162152fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:31.128856Z","signature_b64":"yrNur30hD/DmMXCwmZVI8uuFA12GqTptIoTi8D2ORireDlMc2nM8bmffAK5W0MvGQ1m1MmUHZkkEP50BfpvVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1df616cba83c196a4a39f27821465d993f1c5784d49fb70e29590437162152fe","last_reissued_at":"2026-05-20T00:06:31.128071Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:31.128071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18899","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+9UAwdpY37HblCAakRKcn4yI+NrUGQt3v5Pq5xCPejI4d3qoybZofyyejD+CsZ8AACiZWwNggApDdvO2nCXJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:27:56.040276Z"},"content_sha256":"bd3be29fac9a5bd761c31ae19ac85160324de6e5924f7248a7903657d36cea90","schema_version":"1.0","event_id":"sha256:bd3be29fac9a5bd761c31ae19ac85160324de6e5924f7248a7903657d36cea90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DX3BNS5IHQMWUSRZ6J4CCRS5TE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chung Park, Hyeongjun Yun, Jaegul Choo, Taesan Kim","submitted_at":"2026-05-17T11:10:44Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18899","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/2605.18899/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2z9NM0QFeB1bshrphFybHPNEyWLwM9tytAz6IeGCVF598+5F3Sb0izCbXDMJ6Boj7XuaySNq2Jsxsgq6yYw7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:27:56.040687Z"},"content_sha256":"fe5ef573d87e03fe6336ba0348acff8cdf7d0f285feeacd5388f2c994b780a73","schema_version":"1.0","event_id":"sha256:fe5ef573d87e03fe6336ba0348acff8cdf7d0f285feeacd5388f2c994b780a73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DX3BNS5IHQMWUSRZ6J4CCRS5TE/bundle.json","state_url":"https://pith.science/pith/DX3BNS5IHQMWUSRZ6J4CCRS5TE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DX3BNS5IHQMWUSRZ6J4CCRS5TE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T09:27:56Z","links":{"resolver":"https://pith.science/pith/DX3BNS5IHQMWUSRZ6J4CCRS5TE","bundle":"https://pith.science/pith/DX3BNS5IHQMWUSRZ6J4CCRS5TE/bundle.json","state":"https://pith.science/pith/DX3BNS5IHQMWUSRZ6J4CCRS5TE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DX3BNS5IHQMWUSRZ6J4CCRS5TE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8q+4qpopmtDynkqaWXfG9v4Rxj5Ur/rF7ZCBLTJ8npxzx8czIOuTUBUfKxxkPNbvlXvCVcwC1uCzFcvEYyfAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T09:27:56.042806Z","bundle_sha256":"90537686c366e4b98951a2995146caed9a87fa6214e19c7419277b17b039d30a"}}