{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IUCZFJFH5K4XJVTLCD2WHQ3LCA","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":"6565a29cc3131569fe4bcb58e6fdc965191db790855686f40eb1bf7bc35ffa1e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-20T10:25:24Z","title_canon_sha256":"58780974594671a77a8397c4c2dd7b8e2edc5585440c04fb3984aaa9799cafc5"},"schema_version":"1.0","source":{"id":"2507.14901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14901","created_at":"2026-07-05T11:40:15Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14901v1","created_at":"2026-07-05T11:40:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14901","created_at":"2026-07-05T11:40:15Z"},{"alias_kind":"pith_short_12","alias_value":"IUCZFJFH5K4X","created_at":"2026-07-05T11:40:15Z"},{"alias_kind":"pith_short_16","alias_value":"IUCZFJFH5K4XJVTL","created_at":"2026-07-05T11:40:15Z"},{"alias_kind":"pith_short_8","alias_value":"IUCZFJFH","created_at":"2026-07-05T11:40:15Z"}],"graph_snapshots":[{"event_id":"sha256:9b7c8ebbb8a510327d65b05e71ec1a72246589deb79a38284067865a918b513b","target":"graph","created_at":"2026-07-05T11:40:15Z","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/2507.14901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Why do reinforcement learning (RL) policies fail or succeed? This is a challenging question due to the complex, high-dimensional nature of agent-environment interactions. In this work, we take a causal perspective on explaining the behavior of RL policies by viewing the states, actions, and rewards as variables in a low-level causal model. We introduce random perturbations to policy actions during execution and observe their effects on the cumulative reward, learning a simplified high-level causal model that explains these relationships. To this end, we develop a nonlinear Causal Model Reducti","authors_text":"Armin Keki\\'c, Bernhard Sch\\\"olkopf, Dieter B\\\"uchler, Jan Schneider, Michel Besserve","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-20T10:25:24Z","title":"Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14901","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":"sha256:5d7715d1c18c0f2f9a1b6dc5732bcd7c481a8ce6965886cb52a2ab481112993c","target":"record","created_at":"2026-07-05T11:40:15Z","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":"6565a29cc3131569fe4bcb58e6fdc965191db790855686f40eb1bf7bc35ffa1e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-20T10:25:24Z","title_canon_sha256":"58780974594671a77a8397c4c2dd7b8e2edc5585440c04fb3984aaa9799cafc5"},"schema_version":"1.0","source":{"id":"2507.14901","kind":"arxiv","version":1}},"canonical_sha256":"450592a4a7eab974d66b10f563c36b102445a31d34a504e527b7ad746e07e150","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"450592a4a7eab974d66b10f563c36b102445a31d34a504e527b7ad746e07e150","first_computed_at":"2026-07-05T11:40:15.307243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:15.307243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/AbPWaIFL1gN22LPovcFT6UFWM3YFcSmCu/EGZ6MebUwWSGpTesNlZXA3gE2SMWidAXbq163oLdbO5QXQxgbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:15.307715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d7715d1c18c0f2f9a1b6dc5732bcd7c481a8ce6965886cb52a2ab481112993c","sha256:9b7c8ebbb8a510327d65b05e71ec1a72246589deb79a38284067865a918b513b"],"state_sha256":"0ffc9fbba95b423b5c0dc512584e77a8acf12397e939e0cca3f2759207e6171c"}