{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:INIMD5NVLBVNFMQL2OGLDC5QN7","short_pith_number":"pith:INIMD5NV","schema_version":"1.0","canonical_sha256":"4350c1f5b5586ad2b20bd38cb18bb06fd5cbcf2d2fe9aec9781354fe7749c189","source":{"kind":"arxiv","id":"2510.19244","version":3},"attestation_state":"computed","paper":{"title":"Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Chen, Liyuan Zhao, Qinyue Zhou, Su Nguyen, Yiyu Qian","submitted_at":"2025-10-22T05:04:43Z","abstract_excerpt":"Deep reinforcement learning (RL) achieves remarkable performance but lacks interpretability, limiting trust in policy behavior. The existing SILVER framework (Li, Siddique, and Cao 2025) explains RL policy via Shapley-based regression but remains restricted to low-dimensional, binary-action domains. We propose SILVER with RL-guided labeling, an enhanced variant that extends SILVER to multi-action and high-dimensional environments by incorporating the RL policy's own action outputs into the boundary points identification. Our method first extracts compact feature representations from image obse"},"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":"2510.19244","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-22T05:04:43Z","cross_cats_sorted":[],"title_canon_sha256":"8dfcf49f46ddf87426e3ea9348b78fc8c33db9f3140365fec7c7b379fe8fc7d4","abstract_canon_sha256":"a164a1991a699290ddc26500933d77f430c7aec418d54f1bd7cedb5a0686edb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:38.554719Z","signature_b64":"eic+slRkU4Ke2H1rMJsan6K0Jh6e4TnPw1YqwzDTBJtSJ+FOq0kaygyYPo3OO50Wc0gqZuZmrjK3m4JxhWVjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4350c1f5b5586ad2b20bd38cb18bb06fd5cbcf2d2fe9aec9781354fe7749c189","last_reissued_at":"2026-07-21T01:20:38.553729Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:38.553729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Chen, Liyuan Zhao, Qinyue Zhou, Su Nguyen, Yiyu Qian","submitted_at":"2025-10-22T05:04:43Z","abstract_excerpt":"Deep reinforcement learning (RL) achieves remarkable performance but lacks interpretability, limiting trust in policy behavior. The existing SILVER framework (Li, Siddique, and Cao 2025) explains RL policy via Shapley-based regression but remains restricted to low-dimensional, binary-action domains. We propose SILVER with RL-guided labeling, an enhanced variant that extends SILVER to multi-action and high-dimensional environments by incorporating the RL policy's own action outputs into the boundary points identification. Our method first extracts compact feature representations from image obse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.19244","kind":"arxiv","version":3},"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/2510.19244/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":"2510.19244","created_at":"2026-07-21T01:20:38.554178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.19244v3","created_at":"2026-07-21T01:20:38.554178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.19244","created_at":"2026-07-21T01:20:38.554178+00:00"},{"alias_kind":"pith_short_12","alias_value":"INIMD5NVLBVN","created_at":"2026-07-21T01:20:38.554178+00:00"},{"alias_kind":"pith_short_16","alias_value":"INIMD5NVLBVNFMQL","created_at":"2026-07-21T01:20:38.554178+00:00"},{"alias_kind":"pith_short_8","alias_value":"INIMD5NV","created_at":"2026-07-21T01:20:38.554178+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/INIMD5NVLBVNFMQL2OGLDC5QN7","json":"https://pith.science/pith/INIMD5NVLBVNFMQL2OGLDC5QN7.json","graph_json":"https://pith.science/api/pith-number/INIMD5NVLBVNFMQL2OGLDC5QN7/graph.json","events_json":"https://pith.science/api/pith-number/INIMD5NVLBVNFMQL2OGLDC5QN7/events.json","paper":"https://pith.science/paper/INIMD5NV"},"agent_actions":{"view_html":"https://pith.science/pith/INIMD5NVLBVNFMQL2OGLDC5QN7","download_json":"https://pith.science/pith/INIMD5NVLBVNFMQL2OGLDC5QN7.json","view_paper":"https://pith.science/paper/INIMD5NV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.19244&json=true","fetch_graph":"https://pith.science/api/pith-number/INIMD5NVLBVNFMQL2OGLDC5QN7/graph.json","fetch_events":"https://pith.science/api/pith-number/INIMD5NVLBVNFMQL2OGLDC5QN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INIMD5NVLBVNFMQL2OGLDC5QN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INIMD5NVLBVNFMQL2OGLDC5QN7/action/storage_attestation","attest_author":"https://pith.science/pith/INIMD5NVLBVNFMQL2OGLDC5QN7/action/author_attestation","sign_citation":"https://pith.science/pith/INIMD5NVLBVNFMQL2OGLDC5QN7/action/citation_signature","submit_replication":"https://pith.science/pith/INIMD5NVLBVNFMQL2OGLDC5QN7/action/replication_record"}},"created_at":"2026-07-21T01:20:38.554178+00:00","updated_at":"2026-07-21T01:20:38.554178+00:00"}