{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:742HC3TB5QT36QPMQ5M3BJ5RKU","short_pith_number":"pith:742HC3TB","schema_version":"1.0","canonical_sha256":"ff34716e61ec27bf41ec8759b0a7b1550e6e989afc67898911165d8732084a93","source":{"kind":"arxiv","id":"2502.10097","version":1},"attestation_state":"computed","paper":{"title":"Causal Information Prioritization for Efficient Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fan Feng, Hongye Cao, Jing Huo, Tianpei Yang, Yang Gao","submitted_at":"2025-02-14T11:44:17Z","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"},"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":"2502.10097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-14T11:44:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab76545eb6ef5d294672e1f74b2e5d58a01abd54635a3441612389516301a182","abstract_canon_sha256":"e0f98c3e0583cf2eedccb8ba0bc55d6bf04bc3dbdecb042372c612365afd0f4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:28.078643Z","signature_b64":"0zQY9f72VwIRt1rpiYwhBUS+annPTWOfeTROw4fwgS3DR9sD+6kq7g8bLv9C23r/S0dZaD/7LSNyTYB5fqYFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff34716e61ec27bf41ec8759b0a7b1550e6e989afc67898911165d8732084a93","last_reissued_at":"2026-07-05T10:14:28.078127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:28.078127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Information Prioritization for Efficient Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fan Feng, Hongye Cao, Jing Huo, Tianpei Yang, Yang Gao","submitted_at":"2025-02-14T11:44:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10097","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/2502.10097/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":"2502.10097","created_at":"2026-07-05T10:14:28.078193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10097v1","created_at":"2026-07-05T10:14:28.078193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10097","created_at":"2026-07-05T10:14:28.078193+00:00"},{"alias_kind":"pith_short_12","alias_value":"742HC3TB5QT3","created_at":"2026-07-05T10:14:28.078193+00:00"},{"alias_kind":"pith_short_16","alias_value":"742HC3TB5QT36QPM","created_at":"2026-07-05T10:14:28.078193+00:00"},{"alias_kind":"pith_short_8","alias_value":"742HC3TB","created_at":"2026-07-05T10:14:28.078193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09742","citing_title":"Causality-informed Anomaly Detection in Partially Observable Sensor Networks: Moving beyond Correlations","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/742HC3TB5QT36QPMQ5M3BJ5RKU","json":"https://pith.science/pith/742HC3TB5QT36QPMQ5M3BJ5RKU.json","graph_json":"https://pith.science/api/pith-number/742HC3TB5QT36QPMQ5M3BJ5RKU/graph.json","events_json":"https://pith.science/api/pith-number/742HC3TB5QT36QPMQ5M3BJ5RKU/events.json","paper":"https://pith.science/paper/742HC3TB"},"agent_actions":{"view_html":"https://pith.science/pith/742HC3TB5QT36QPMQ5M3BJ5RKU","download_json":"https://pith.science/pith/742HC3TB5QT36QPMQ5M3BJ5RKU.json","view_paper":"https://pith.science/paper/742HC3TB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10097&json=true","fetch_graph":"https://pith.science/api/pith-number/742HC3TB5QT36QPMQ5M3BJ5RKU/graph.json","fetch_events":"https://pith.science/api/pith-number/742HC3TB5QT36QPMQ5M3BJ5RKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/742HC3TB5QT36QPMQ5M3BJ5RKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/742HC3TB5QT36QPMQ5M3BJ5RKU/action/storage_attestation","attest_author":"https://pith.science/pith/742HC3TB5QT36QPMQ5M3BJ5RKU/action/author_attestation","sign_citation":"https://pith.science/pith/742HC3TB5QT36QPMQ5M3BJ5RKU/action/citation_signature","submit_replication":"https://pith.science/pith/742HC3TB5QT36QPMQ5M3BJ5RKU/action/replication_record"}},"created_at":"2026-07-05T10:14:28.078193+00:00","updated_at":"2026-07-05T10:14:28.078193+00:00"}