{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:INIMD5NVLBVNFMQL2OGLDC5QN7","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":"a164a1991a699290ddc26500933d77f430c7aec418d54f1bd7cedb5a0686edb2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-22T05:04:43Z","title_canon_sha256":"8dfcf49f46ddf87426e3ea9348b78fc8c33db9f3140365fec7c7b379fe8fc7d4"},"schema_version":"1.0","source":{"id":"2510.19244","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.19244","created_at":"2026-07-21T01:20:38Z"},{"alias_kind":"arxiv_version","alias_value":"2510.19244v3","created_at":"2026-07-21T01:20:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.19244","created_at":"2026-07-21T01:20:38Z"},{"alias_kind":"pith_short_12","alias_value":"INIMD5NVLBVN","created_at":"2026-07-21T01:20:38Z"},{"alias_kind":"pith_short_16","alias_value":"INIMD5NVLBVNFMQL","created_at":"2026-07-21T01:20:38Z"},{"alias_kind":"pith_short_8","alias_value":"INIMD5NV","created_at":"2026-07-21T01:20:38Z"}],"graph_snapshots":[{"event_id":"sha256:84218821e86318d185d78b3a367cf20bb3e4ed5a2e862453a77c110d6401a975","target":"graph","created_at":"2026-07-21T01:20:38Z","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/2510.19244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao Chen, Liyuan Zhao, Qinyue Zhou, Su Nguyen, Yiyu Qian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-22T05:04:43Z","title":"Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.19244","kind":"arxiv","version":3},"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:ba644ad065544aa6894d919206967b627170c23b68e218e7c720f512d330046d","target":"record","created_at":"2026-07-21T01:20:38Z","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":"a164a1991a699290ddc26500933d77f430c7aec418d54f1bd7cedb5a0686edb2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-22T05:04:43Z","title_canon_sha256":"8dfcf49f46ddf87426e3ea9348b78fc8c33db9f3140365fec7c7b379fe8fc7d4"},"schema_version":"1.0","source":{"id":"2510.19244","kind":"arxiv","version":3}},"canonical_sha256":"4350c1f5b5586ad2b20bd38cb18bb06fd5cbcf2d2fe9aec9781354fe7749c189","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4350c1f5b5586ad2b20bd38cb18bb06fd5cbcf2d2fe9aec9781354fe7749c189","first_computed_at":"2026-07-21T01:20:38.553729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:20:38.553729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eic+slRkU4Ke2H1rMJsan6K0Jh6e4TnPw1YqwzDTBJtSJ+FOq0kaygyYPo3OO50Wc0gqZuZmrjK3m4JxhWVjDg==","signature_status":"signed_v1","signed_at":"2026-07-21T01:20:38.554719Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.19244","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba644ad065544aa6894d919206967b627170c23b68e218e7c720f512d330046d","sha256:84218821e86318d185d78b3a367cf20bb3e4ed5a2e862453a77c110d6401a975"],"state_sha256":"0872f1979ba27579023e0dfd44b94b0aaf5b7ea6d4ddc4c9ef14f4e08c82f178"}