{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SJMMFR5RAAKXFQXZNWA3TSOHOY","short_pith_number":"pith:SJMMFR5R","canonical_record":{"source":{"id":"2501.13816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-01-23T16:37:44Z","cross_cats_sorted":[],"title_canon_sha256":"c928e8c87ad692780e93c06d3f9c512bdef6b5f9644ae98b5820f93f1b144482","abstract_canon_sha256":"8873067852e8bd78570e328861564cbbf1bca4691a1a5c2aca2c3f8a232474cf"},"schema_version":"1.0"},"canonical_sha256":"9258c2c7b1001572c2f96d81b9c9c77614229c986fa4a0cbcc18bc2102fb93b7","source":{"kind":"arxiv","id":"2501.13816","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13816","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13816v1","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13816","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"SJMMFR5RAAKX","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"SJMMFR5RAAKXFQXZ","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"SJMMFR5R","created_at":"2026-07-05T10:04:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SJMMFR5RAAKXFQXZNWA3TSOHOY","target":"record","payload":{"canonical_record":{"source":{"id":"2501.13816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-01-23T16:37:44Z","cross_cats_sorted":[],"title_canon_sha256":"c928e8c87ad692780e93c06d3f9c512bdef6b5f9644ae98b5820f93f1b144482","abstract_canon_sha256":"8873067852e8bd78570e328861564cbbf1bca4691a1a5c2aca2c3f8a232474cf"},"schema_version":"1.0"},"canonical_sha256":"9258c2c7b1001572c2f96d81b9c9c77614229c986fa4a0cbcc18bc2102fb93b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:34.301528Z","signature_b64":"JDTe5OQT7wHxQyRaJOuEYRFG8fU+fTt/Rm0A9ifGWfYlKift0lByLfrPD1DdDvFm/n+DO/4j7waO/nl3b4bTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9258c2c7b1001572c2f96d81b9c9c77614229c986fa4a0cbcc18bc2102fb93b7","last_reissued_at":"2026-07-05T10:04:34.301027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:34.301027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.13816","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":"2026-07-05T10:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iGHeWGWiJ/OjQHkcfbskB3G5QgkDpCTAE+ZvBX98NA/mNKgnwd33x5Yj2C19oqSuc6l8MzgEvh8P4EmHv8E+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:33:27.214029Z"},"content_sha256":"32180c1626c2b2a88e4fda9a84333cc54a7af904463c704382af9337dbc2f357","schema_version":"1.0","event_id":"sha256:32180c1626c2b2a88e4fda9a84333cc54a7af904463c704382af9337dbc2f357"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SJMMFR5RAAKXFQXZNWA3TSOHOY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Model driven Policy Exploration for Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Alexandros Karatzoglou, Ioannis Arapakis, Jie Wang, Joemon M. Jose","submitted_at":"2025-01-23T16:37:44Z","abstract_excerpt":"Recent advancements in Recommender Systems (RS) have incorporated Reinforcement Learning (RL), framing the recommendation as a Markov Decision Process (MDP). However, offline RL policies trained on static user data are vulnerable to distribution shift when deployed in dynamic online environments. Additionally, excessive focus on exploiting short-term relevant items can hinder exploration, leading to suboptimal recommendations and negatively impacting long-term user gains. Online RL-based RS also face challenges in production deployment, due to the risks of exposing users to untrained or unstab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13816","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/2501.13816/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":"2026-07-05T10:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jfT5ukD8fhLmRybMgafeSVYnZfT7qgbQ2smkl8fAlrX/lb/RUgdqJtX4ajfJ9vShZQpMUhpIXZUuzmvwj0yPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:33:27.214849Z"},"content_sha256":"305095781ed9709df3353308f432defe83cdc60caf5a3e98e57ac5a062b4a9fb","schema_version":"1.0","event_id":"sha256:305095781ed9709df3353308f432defe83cdc60caf5a3e98e57ac5a062b4a9fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJMMFR5RAAKXFQXZNWA3TSOHOY/bundle.json","state_url":"https://pith.science/pith/SJMMFR5RAAKXFQXZNWA3TSOHOY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJMMFR5RAAKXFQXZNWA3TSOHOY/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":"2026-08-11T06:33:27Z","links":{"resolver":"https://pith.science/pith/SJMMFR5RAAKXFQXZNWA3TSOHOY","bundle":"https://pith.science/pith/SJMMFR5RAAKXFQXZNWA3TSOHOY/bundle.json","state":"https://pith.science/pith/SJMMFR5RAAKXFQXZNWA3TSOHOY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJMMFR5RAAKXFQXZNWA3TSOHOY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SJMMFR5RAAKXFQXZNWA3TSOHOY","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":"8873067852e8bd78570e328861564cbbf1bca4691a1a5c2aca2c3f8a232474cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-01-23T16:37:44Z","title_canon_sha256":"c928e8c87ad692780e93c06d3f9c512bdef6b5f9644ae98b5820f93f1b144482"},"schema_version":"1.0","source":{"id":"2501.13816","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13816","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13816v1","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13816","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"SJMMFR5RAAKX","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"SJMMFR5RAAKXFQXZ","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"SJMMFR5R","created_at":"2026-07-05T10:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:305095781ed9709df3353308f432defe83cdc60caf5a3e98e57ac5a062b4a9fb","target":"graph","created_at":"2026-07-05T10:04:34Z","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/2501.13816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Recommender Systems (RS) have incorporated Reinforcement Learning (RL), framing the recommendation as a Markov Decision Process (MDP). However, offline RL policies trained on static user data are vulnerable to distribution shift when deployed in dynamic online environments. Additionally, excessive focus on exploiting short-term relevant items can hinder exploration, leading to suboptimal recommendations and negatively impacting long-term user gains. Online RL-based RS also face challenges in production deployment, due to the risks of exposing users to untrained or unstab","authors_text":"Alexandros Karatzoglou, Ioannis Arapakis, Jie Wang, Joemon M. Jose","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-01-23T16:37:44Z","title":"Large Language Model driven Policy Exploration for Recommender Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13816","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":"sha256:32180c1626c2b2a88e4fda9a84333cc54a7af904463c704382af9337dbc2f357","target":"record","created_at":"2026-07-05T10:04:34Z","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":"8873067852e8bd78570e328861564cbbf1bca4691a1a5c2aca2c3f8a232474cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-01-23T16:37:44Z","title_canon_sha256":"c928e8c87ad692780e93c06d3f9c512bdef6b5f9644ae98b5820f93f1b144482"},"schema_version":"1.0","source":{"id":"2501.13816","kind":"arxiv","version":1}},"canonical_sha256":"9258c2c7b1001572c2f96d81b9c9c77614229c986fa4a0cbcc18bc2102fb93b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9258c2c7b1001572c2f96d81b9c9c77614229c986fa4a0cbcc18bc2102fb93b7","first_computed_at":"2026-07-05T10:04:34.301027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:34.301027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JDTe5OQT7wHxQyRaJOuEYRFG8fU+fTt/Rm0A9ifGWfYlKift0lByLfrPD1DdDvFm/n+DO/4j7waO/nl3b4bTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:34.301528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13816","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32180c1626c2b2a88e4fda9a84333cc54a7af904463c704382af9337dbc2f357","sha256:305095781ed9709df3353308f432defe83cdc60caf5a3e98e57ac5a062b4a9fb"],"state_sha256":"37a17628ba8c7c2031582ce2fa2b5bf20bd561d8bd8aab89d29a8830de2d04f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/qXgdEYmkhSYLU0Q1nz+BWgrPxv/qjiGYSOP3lgLd5taE0IlNhKU+iq8wxg2cy57s0uuei+9K7LPjDHfZQLzBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T06:33:27.219324Z","bundle_sha256":"b76ea85d1b9707b1de28e460851258fe0122b70be35c54e5f044ad896962cebb"}}