{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZTGKR6AF6FDXUQX4SL2NPW47PX","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":"6aa522745401ee2210dbc3891b4623d1e7130a11c3a73987311e5acdf5150ada","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T09:32:20Z","title_canon_sha256":"e3f1bec8c6d81a6af47e0f83585e8296b12a26ac204ad4f2b7c476063ae857ef"},"schema_version":"1.0","source":{"id":"2509.26000","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.26000","created_at":"2026-06-10T01:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2509.26000v3","created_at":"2026-06-10T01:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.26000","created_at":"2026-06-10T01:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZTGKR6AF6FDX","created_at":"2026-06-10T01:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZTGKR6AF6FDXUQX4","created_at":"2026-06-10T01:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZTGKR6AF","created_at":"2026-06-10T01:09:44Z"}],"graph_snapshots":[{"event_id":"sha256:73065105ff6c7a1147283bd6ec5d07ca725793df336b5e90008c5c33b083d4d6","target":"graph","created_at":"2026-06-10T01:09:44Z","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/2509.26000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Asymmetric reinforcement learning leverages privileged information available during training to improve learning under partial observability. Existing asymmetric actor-critic methods typically assume access to the full environment state to condition the critic during training, which is often unrealistic in practice. We introduce the informed asymmetric actor-critic framework that allows the critic to be conditioned on arbitrary state-dependent privileged signals, and show that any such signal yields unbiased policy gradient estimates. This substantially expands the set of admissible privileged","authors_text":"Damien Ernst, Daniel Ebi, Gaspard Lambrechts, Klemens B\\\"ohm","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T09:32:20Z","title":"Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.26000","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":"sha256:67b74c1d0da60154cb7c99a38b2b9e4d2bd9452280c8c9ecec3b7f5e654caca2","target":"record","created_at":"2026-06-10T01:09:44Z","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":"6aa522745401ee2210dbc3891b4623d1e7130a11c3a73987311e5acdf5150ada","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T09:32:20Z","title_canon_sha256":"e3f1bec8c6d81a6af47e0f83585e8296b12a26ac204ad4f2b7c476063ae857ef"},"schema_version":"1.0","source":{"id":"2509.26000","kind":"arxiv","version":3}},"canonical_sha256":"cccca8f805f1477a42fc92f4d7db9f7df0ac1dad424d61b25ff167d5e00b329e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cccca8f805f1477a42fc92f4d7db9f7df0ac1dad424d61b25ff167d5e00b329e","first_computed_at":"2026-06-10T01:09:44.363191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:44.363191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KuGJZ9jaON4zukxU2d8ivlIsBdJdgFs6qDaQBfVsOoUX+sjg8CIAxKhi503GAYZfxc56fGua4GXQszYoMJTZCA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:44.363762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.26000","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67b74c1d0da60154cb7c99a38b2b9e4d2bd9452280c8c9ecec3b7f5e654caca2","sha256:73065105ff6c7a1147283bd6ec5d07ca725793df336b5e90008c5c33b083d4d6"],"state_sha256":"5d6d7b66c58256dfa262388c77640f49066a03652b3c545f57be767c0bbf2d80"}