{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X5DSCMJU4EFU4DQVPLGVLPBIOH","short_pith_number":"pith:X5DSCMJU","canonical_record":{"source":{"id":"2406.01631","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-01T11:56:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"34e5569acf5c5e7a8835ce26e024073060adc443fb6c5646ded40763aef85fec","abstract_canon_sha256":"bec7a7f4e9f95d75fc9b10f1583db57fd459a484798646369e129052ae3157f1"},"schema_version":"1.0"},"canonical_sha256":"bf47213134e10b4e0e157acd55bc2871e43888430316663ba36689069ee2b95a","source":{"kind":"arxiv","id":"2406.01631","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01631","created_at":"2026-07-05T08:57:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01631v2","created_at":"2026-07-05T08:57:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01631","created_at":"2026-07-05T08:57:04Z"},{"alias_kind":"pith_short_12","alias_value":"X5DSCMJU4EFU","created_at":"2026-07-05T08:57:04Z"},{"alias_kind":"pith_short_16","alias_value":"X5DSCMJU4EFU4DQV","created_at":"2026-07-05T08:57:04Z"},{"alias_kind":"pith_short_8","alias_value":"X5DSCMJU","created_at":"2026-07-05T08:57:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X5DSCMJU4EFU4DQVPLGVLPBIOH","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01631","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-01T11:56:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"34e5569acf5c5e7a8835ce26e024073060adc443fb6c5646ded40763aef85fec","abstract_canon_sha256":"bec7a7f4e9f95d75fc9b10f1583db57fd459a484798646369e129052ae3157f1"},"schema_version":"1.0"},"canonical_sha256":"bf47213134e10b4e0e157acd55bc2871e43888430316663ba36689069ee2b95a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:04.588098Z","signature_b64":"J1BjGBe1E7ULhNJ9Mm3ts1B6e0Alm30vC6UMV7o6U9T7srV5dVmpHXmVgMvYiJxLepLnBN1E28ZRgYt3vVIbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf47213134e10b4e0e157acd55bc2871e43888430316663ba36689069ee2b95a","last_reissued_at":"2026-07-05T08:57:04.587628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:04.587628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01631","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2Xg+2PHUQFS/h65R/Pu6ayAQP+GisCN5da3tgBkBCRAa8/zeokwdz4ZFuRun7qmaPz4dvVM6y9klQZ1Y9dJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:15:24.929107Z"},"content_sha256":"bd1f08041672e3a1a65c8bdc523d9ae3de3e0646ef8cd15fdf8e6d47d0bb8a3a","schema_version":"1.0","event_id":"sha256:bd1f08041672e3a1a65c8bdc523d9ae3de3e0646ef8cd15fdf8e6d47d0bb8a3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X5DSCMJU4EFU4DQVPLGVLPBIOH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Flint Xiaofeng Fan, Giorgio Piatti, Luca A. Lanzend\\\"orfer, Nathan Corecco, Roger Wattenhofer","submitted_at":"2024-06-01T11:56:08Z","abstract_excerpt":"Reinforcement learning (RL) has gained popularity in the realm of recommender systems due to its ability to optimize long-term rewards and guide users in discovering relevant content. However, the successful implementation of RL in recommender systems is challenging because of several factors, including the limited availability of online data for training on-policy methods. This scarcity requires expensive human interaction for online model training. Furthermore, the development of effective evaluation frameworks that accurately reflect the quality of models remains a fundamental challenge in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01631","kind":"arxiv","version":2},"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/2406.01631/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":"2026-07-05T08:57:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3kqBsyj7PT9u4DLQDfwcdn/wfBwGOjQqLFKhJ23J7vgeo4t0OetwpoovLj1QsHB3zq+URHBoSG0aYkDq10+2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:15:24.929624Z"},"content_sha256":"056ff0d9f76eead48f4a187a8f4cd071437a0ea41391dac94dc9db71afdfebca","schema_version":"1.0","event_id":"sha256:056ff0d9f76eead48f4a187a8f4cd071437a0ea41391dac94dc9db71afdfebca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X5DSCMJU4EFU4DQVPLGVLPBIOH/bundle.json","state_url":"https://pith.science/pith/X5DSCMJU4EFU4DQVPLGVLPBIOH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X5DSCMJU4EFU4DQVPLGVLPBIOH/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":"2026-08-09T18:15:24Z","links":{"resolver":"https://pith.science/pith/X5DSCMJU4EFU4DQVPLGVLPBIOH","bundle":"https://pith.science/pith/X5DSCMJU4EFU4DQVPLGVLPBIOH/bundle.json","state":"https://pith.science/pith/X5DSCMJU4EFU4DQVPLGVLPBIOH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X5DSCMJU4EFU4DQVPLGVLPBIOH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X5DSCMJU4EFU4DQVPLGVLPBIOH","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":"bec7a7f4e9f95d75fc9b10f1583db57fd459a484798646369e129052ae3157f1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-01T11:56:08Z","title_canon_sha256":"34e5569acf5c5e7a8835ce26e024073060adc443fb6c5646ded40763aef85fec"},"schema_version":"1.0","source":{"id":"2406.01631","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01631","created_at":"2026-07-05T08:57:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01631v2","created_at":"2026-07-05T08:57:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01631","created_at":"2026-07-05T08:57:04Z"},{"alias_kind":"pith_short_12","alias_value":"X5DSCMJU4EFU","created_at":"2026-07-05T08:57:04Z"},{"alias_kind":"pith_short_16","alias_value":"X5DSCMJU4EFU4DQV","created_at":"2026-07-05T08:57:04Z"},{"alias_kind":"pith_short_8","alias_value":"X5DSCMJU","created_at":"2026-07-05T08:57:04Z"}],"graph_snapshots":[{"event_id":"sha256:056ff0d9f76eead48f4a187a8f4cd071437a0ea41391dac94dc9db71afdfebca","target":"graph","created_at":"2026-07-05T08:57:04Z","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/2406.01631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has gained popularity in the realm of recommender systems due to its ability to optimize long-term rewards and guide users in discovering relevant content. However, the successful implementation of RL in recommender systems is challenging because of several factors, including the limited availability of online data for training on-policy methods. This scarcity requires expensive human interaction for online model training. Furthermore, the development of effective evaluation frameworks that accurately reflect the quality of models remains a fundamental challenge in ","authors_text":"Flint Xiaofeng Fan, Giorgio Piatti, Luca A. Lanzend\\\"orfer, Nathan Corecco, Roger Wattenhofer","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-01T11:56:08Z","title":"SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01631","kind":"arxiv","version":2},"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:bd1f08041672e3a1a65c8bdc523d9ae3de3e0646ef8cd15fdf8e6d47d0bb8a3a","target":"record","created_at":"2026-07-05T08:57:04Z","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":"bec7a7f4e9f95d75fc9b10f1583db57fd459a484798646369e129052ae3157f1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-01T11:56:08Z","title_canon_sha256":"34e5569acf5c5e7a8835ce26e024073060adc443fb6c5646ded40763aef85fec"},"schema_version":"1.0","source":{"id":"2406.01631","kind":"arxiv","version":2}},"canonical_sha256":"bf47213134e10b4e0e157acd55bc2871e43888430316663ba36689069ee2b95a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf47213134e10b4e0e157acd55bc2871e43888430316663ba36689069ee2b95a","first_computed_at":"2026-07-05T08:57:04.587628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:04.587628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J1BjGBe1E7ULhNJ9Mm3ts1B6e0Alm30vC6UMV7o6U9T7srV5dVmpHXmVgMvYiJxLepLnBN1E28ZRgYt3vVIbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:04.588098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01631","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd1f08041672e3a1a65c8bdc523d9ae3de3e0646ef8cd15fdf8e6d47d0bb8a3a","sha256:056ff0d9f76eead48f4a187a8f4cd071437a0ea41391dac94dc9db71afdfebca"],"state_sha256":"71185569edd4008db400f2cf64bbe8ae8113eb0da1adde7967d7fc42d0e98ffc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GjQhIHA3mFwUaR6wxLADNsL8M9PzZ00/50kleK+/8MC1vIHGgDqsgzBQIf238MkXuofcuvhdITiDo47iLFe2Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:15:24.934554Z","bundle_sha256":"45c9cb2c3e8a3afcf8deeee100aa43c27319706725c6d3097069e4b9e29bde09"}}