{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PPMJXP4L72FBYIFVVOP67FHZJ3","short_pith_number":"pith:PPMJXP4L","schema_version":"1.0","canonical_sha256":"7bd89bbf8bfe8a1c20b5ab9fef94f94ec4fc97aeda46611a9a4bec0d34b2e370","source":{"kind":"arxiv","id":"2502.02327","version":1},"attestation_state":"computed","paper":{"title":"Policy-Guided Causal State Representation for Offline Reinforcement Learning Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Lina Yao, Siyu Wang, Xiaocong Chen","submitted_at":"2025-02-04T13:58:20Z","abstract_excerpt":"In offline reinforcement learning-based recommender systems (RLRS), learning effective state representations is crucial for capturing user preferences that directly impact long-term rewards. However, raw state representations often contain high-dimensional, noisy information and components that are not causally relevant to the reward. Additionally, missing transitions in offline data make it challenging to accurately identify features that are most relevant to user satisfaction. To address these challenges, we propose Policy-Guided Causal Representation (PGCR), a novel two-stage framework for "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.02327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-02-04T13:58:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"671115ff17689e8cbcd3053f4291bded929aae09912ab5eb081d58d7d11930bb","abstract_canon_sha256":"f67b4dae934c0e0c1addae3cb02521db417235ae34f95afe51d417b1934dc52e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:26.937554Z","signature_b64":"pRV0XI4GkpqGMtcllGgSzEXycG0TocGX6Xm6Naj2AtQpnKwtJp/KiajBNiisbVNVKdimqe0yVWQbpoCGQHClBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bd89bbf8bfe8a1c20b5ab9fef94f94ec4fc97aeda46611a9a4bec0d34b2e370","last_reissued_at":"2026-07-05T10:09:26.937079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:26.937079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy-Guided Causal State Representation for Offline Reinforcement Learning Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Lina Yao, Siyu Wang, Xiaocong Chen","submitted_at":"2025-02-04T13:58:20Z","abstract_excerpt":"In offline reinforcement learning-based recommender systems (RLRS), learning effective state representations is crucial for capturing user preferences that directly impact long-term rewards. However, raw state representations often contain high-dimensional, noisy information and components that are not causally relevant to the reward. Additionally, missing transitions in offline data make it challenging to accurately identify features that are most relevant to user satisfaction. To address these challenges, we propose Policy-Guided Causal Representation (PGCR), a novel two-stage framework for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02327","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/2502.02327/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.02327","created_at":"2026-07-05T10:09:26.937133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02327v1","created_at":"2026-07-05T10:09:26.937133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02327","created_at":"2026-07-05T10:09:26.937133+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPMJXP4L72FB","created_at":"2026-07-05T10:09:26.937133+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPMJXP4L72FBYIFV","created_at":"2026-07-05T10:09:26.937133+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPMJXP4L","created_at":"2026-07-05T10:09:26.937133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3","json":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3.json","graph_json":"https://pith.science/api/pith-number/PPMJXP4L72FBYIFVVOP67FHZJ3/graph.json","events_json":"https://pith.science/api/pith-number/PPMJXP4L72FBYIFVVOP67FHZJ3/events.json","paper":"https://pith.science/paper/PPMJXP4L"},"agent_actions":{"view_html":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3","download_json":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3.json","view_paper":"https://pith.science/paper/PPMJXP4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02327&json=true","fetch_graph":"https://pith.science/api/pith-number/PPMJXP4L72FBYIFVVOP67FHZJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/PPMJXP4L72FBYIFVVOP67FHZJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/action/storage_attestation","attest_author":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/action/author_attestation","sign_citation":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/action/citation_signature","submit_replication":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/action/replication_record"}},"created_at":"2026-07-05T10:09:26.937133+00:00","updated_at":"2026-07-05T10:09:26.937133+00:00"}