{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:742HC3TB5QT36QPMQ5M3BJ5RKU","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":"e0f98c3e0583cf2eedccb8ba0bc55d6bf04bc3dbdecb042372c612365afd0f4f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-14T11:44:17Z","title_canon_sha256":"ab76545eb6ef5d294672e1f74b2e5d58a01abd54635a3441612389516301a182"},"schema_version":"1.0","source":{"id":"2502.10097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10097","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10097v1","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10097","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"742HC3TB5QT3","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"742HC3TB5QT36QPM","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"742HC3TB","created_at":"2026-07-05T10:14:28Z"}],"graph_snapshots":[{"event_id":"sha256:3e48770e8613ba1f2d20f7dc94e262c6385a7bd959fddfc28e413f6af2bd1d14","target":"graph","created_at":"2026-07-05T10:14:28Z","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/2502.10097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current Reinforcement Learning (RL) methods often suffer from sample-inefficiency, resulting from blind exploration strategies that neglect causal relationships among states, actions, and rewards. Although recent causal approaches aim to address this problem, they lack grounded modeling of reward-guided causal understanding of states and actions for goal-orientation, thus impairing learning efficiency. To tackle this issue, we propose a novel method named Causal Information Prioritization (CIP) that improves sample efficiency by leveraging factored MDPs to infer causal relationships between di","authors_text":"Fan Feng, Hongye Cao, Jing Huo, Tianpei Yang, Yang Gao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-14T11:44:17Z","title":"Causal Information Prioritization for Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10097","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:d2972cb6a68f748f66f8f74ec02212a2474af28d11eb6b3c80a72618efe4cc36","target":"record","created_at":"2026-07-05T10:14:28Z","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":"e0f98c3e0583cf2eedccb8ba0bc55d6bf04bc3dbdecb042372c612365afd0f4f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-14T11:44:17Z","title_canon_sha256":"ab76545eb6ef5d294672e1f74b2e5d58a01abd54635a3441612389516301a182"},"schema_version":"1.0","source":{"id":"2502.10097","kind":"arxiv","version":1}},"canonical_sha256":"ff34716e61ec27bf41ec8759b0a7b1550e6e989afc67898911165d8732084a93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff34716e61ec27bf41ec8759b0a7b1550e6e989afc67898911165d8732084a93","first_computed_at":"2026-07-05T10:14:28.078127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:28.078127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0zQY9f72VwIRt1rpiYwhBUS+annPTWOfeTROw4fwgS3DR9sD+6kq7g8bLv9C23r/S0dZaD/7LSNyTYB5fqYFBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:28.078643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2972cb6a68f748f66f8f74ec02212a2474af28d11eb6b3c80a72618efe4cc36","sha256:3e48770e8613ba1f2d20f7dc94e262c6385a7bd959fddfc28e413f6af2bd1d14"],"state_sha256":"1cde1693203ac15648733cf15bac96fcfe2627b0caf98b5ca8acbcd3e975ad4a"}