{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PPMJXP4L72FBYIFVVOP67FHZJ3","short_pith_number":"pith:PPMJXP4L","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"},"canonical_sha256":"7bd89bbf8bfe8a1c20b5ab9fef94f94ec4fc97aeda46611a9a4bec0d34b2e370","source":{"kind":"arxiv","id":"2502.02327","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02327","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02327v1","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02327","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"PPMJXP4L72FB","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"PPMJXP4L72FBYIFV","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"PPMJXP4L","created_at":"2026-07-05T10:09:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PPMJXP4L72FBYIFVVOP67FHZJ3","target":"record","payload":{"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"},"canonical_sha256":"7bd89bbf8bfe8a1c20b5ab9fef94f94ec4fc97aeda46611a9a4bec0d34b2e370","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"},"source_kind":"arxiv","source_id":"2502.02327","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":"2026-07-05T10:09:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3wDPtdCOKtQfbutgj7PooF6QuNlJxagyp7Rm7/weKdD9q80JKLRu1y4ziPZDy+IKXjRiTP0pP4Fk8gs9wt4/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:22:57.565060Z"},"content_sha256":"d24d5a300597b9d929126ab34ce6781a3bdb4ad123f3b6a1acee47277a7b47e4","schema_version":"1.0","event_id":"sha256:d24d5a300597b9d929126ab34ce6781a3bdb4ad123f3b6a1acee47277a7b47e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PPMJXP4L72FBYIFVVOP67FHZJ3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2J98jLCSzJczN9nPCtJdX0cLuB4rMb3CAmwMyIAPNQ6FoK8uvqjzDftmbJ0U7AdYKq2ABxSLZmkfiKL4Z0mrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:22:57.565444Z"},"content_sha256":"c31c4e2247f452698baa4b5c7be1e43b581f681ef198412ee45cbfc88b4d0696","schema_version":"1.0","event_id":"sha256:c31c4e2247f452698baa4b5c7be1e43b581f681ef198412ee45cbfc88b4d0696"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/bundle.json","state_url":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/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":"2026-07-07T10:22:57Z","links":{"resolver":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3","bundle":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/bundle.json","state":"https://pith.science/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPMJXP4L72FBYIFVVOP67FHZJ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PPMJXP4L72FBYIFVVOP67FHZJ3","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":"f67b4dae934c0e0c1addae3cb02521db417235ae34f95afe51d417b1934dc52e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-02-04T13:58:20Z","title_canon_sha256":"671115ff17689e8cbcd3053f4291bded929aae09912ab5eb081d58d7d11930bb"},"schema_version":"1.0","source":{"id":"2502.02327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02327","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02327v1","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02327","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"PPMJXP4L72FB","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"PPMJXP4L72FBYIFV","created_at":"2026-07-05T10:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"PPMJXP4L","created_at":"2026-07-05T10:09:26Z"}],"graph_snapshots":[{"event_id":"sha256:c31c4e2247f452698baa4b5c7be1e43b581f681ef198412ee45cbfc88b4d0696","target":"graph","created_at":"2026-07-05T10:09:26Z","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/2502.02327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Lina Yao, Siyu Wang, Xiaocong Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-02-04T13:58:20Z","title":"Policy-Guided Causal State Representation for Offline Reinforcement Learning Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02327","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:d24d5a300597b9d929126ab34ce6781a3bdb4ad123f3b6a1acee47277a7b47e4","target":"record","created_at":"2026-07-05T10:09:26Z","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":"f67b4dae934c0e0c1addae3cb02521db417235ae34f95afe51d417b1934dc52e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-02-04T13:58:20Z","title_canon_sha256":"671115ff17689e8cbcd3053f4291bded929aae09912ab5eb081d58d7d11930bb"},"schema_version":"1.0","source":{"id":"2502.02327","kind":"arxiv","version":1}},"canonical_sha256":"7bd89bbf8bfe8a1c20b5ab9fef94f94ec4fc97aeda46611a9a4bec0d34b2e370","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bd89bbf8bfe8a1c20b5ab9fef94f94ec4fc97aeda46611a9a4bec0d34b2e370","first_computed_at":"2026-07-05T10:09:26.937079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:26.937079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pRV0XI4GkpqGMtcllGgSzEXycG0TocGX6Xm6Naj2AtQpnKwtJp/KiajBNiisbVNVKdimqe0yVWQbpoCGQHClBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:26.937554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d24d5a300597b9d929126ab34ce6781a3bdb4ad123f3b6a1acee47277a7b47e4","sha256:c31c4e2247f452698baa4b5c7be1e43b581f681ef198412ee45cbfc88b4d0696"],"state_sha256":"5eb862338345d4586c5a389859a1145c9b741c27ab4e953a1e06a03a3a224129"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HFU68nTISU7eB/tFMRMC7SsJ1o/FtEICOnuGINGqJZ/+EuOYXh6dJZKNCL7v4vKh/ogvVq7+dhfZyiQUJqlACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:22:57.568391Z","bundle_sha256":"55698600aab5d14de4fb1967f0453a7c4b84372a88a512d04360dd53d8e2ff51"}}