{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UQBBR3MVAF5G7MDW3IRXYOWWN7","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":"92c8e14c67c11c9a3f858f810f1c06fe6d844d10f1831ab3c661c414df261c88","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T10:43:37Z","title_canon_sha256":"52f222827534008a5bdaeb95a89d9dee61e9453a1b50d9cd6e0504ce506cd50d"},"schema_version":"1.0","source":{"id":"2605.28293","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28293","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28293v1","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28293","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"UQBBR3MVAF5G","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"UQBBR3MVAF5G7MDW","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"UQBBR3MV","created_at":"2026-05-28T01:05:05Z"}],"graph_snapshots":[{"event_id":"sha256:b2589e87245a7fc8a7e12994b33e83ca1aa58803a2bc23457869c22790a55b32","target":"graph","created_at":"2026-05-28T01:05:05Z","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/2605.28293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proactive Recommender Systems (PRSs) aim to guide user preference shift toward target items by generating paths of intermediate recommendations. Reinforcement learning (RL) provides a principled framework for optimizing such sequential decision tasks, as path rewards can naturally capture both short-term acceptance and long-term guidance effectiveness. However, naively applying policy gradients to PRS results in deficient gradient estimation. We identify two deficiencies: (1) path-level rewards decompose into step-level rewards with positive mean, creating a length-dependent bias that causes g","authors_text":"Ao Xu, Denghui Geng, Deqing Yang, Hengrui Chen, Hongru Hou, Jiaqing Liang, Jinhui Huang, Tiehua Mei","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T10:43:37Z","title":"ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28293","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:c94099067a521bb1741217282a8d55b0c75e03f4e18eb09b4316deb0fbde42be","target":"record","created_at":"2026-05-28T01:05:05Z","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":"92c8e14c67c11c9a3f858f810f1c06fe6d844d10f1831ab3c661c414df261c88","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T10:43:37Z","title_canon_sha256":"52f222827534008a5bdaeb95a89d9dee61e9453a1b50d9cd6e0504ce506cd50d"},"schema_version":"1.0","source":{"id":"2605.28293","kind":"arxiv","version":1}},"canonical_sha256":"a40218ed95017a6fb076da237c3ad66fefa9d6448efb7cce631dfd11dda018ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a40218ed95017a6fb076da237c3ad66fefa9d6448efb7cce631dfd11dda018ac","first_computed_at":"2026-05-28T01:05:05.453826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:05.453826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t/1d8IFA2/eVfbGHShnXbuWU1JSXq51rISX24mADTl4eX1W7OAiMpoyz/HJFeGSBNFDepWMWjbNiD+MUEaVWAg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:05.454250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28293","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c94099067a521bb1741217282a8d55b0c75e03f4e18eb09b4316deb0fbde42be","sha256:b2589e87245a7fc8a7e12994b33e83ca1aa58803a2bc23457869c22790a55b32"],"state_sha256":"3c47d91e7842282dad2fae62f7c1c54fc6e16637b56b451b386ea232ca242b69"}