{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZTGKR6AF6FDXUQX4SL2NPW47PX","short_pith_number":"pith:ZTGKR6AF","canonical_record":{"source":{"id":"2509.26000","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T09:32:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e3f1bec8c6d81a6af47e0f83585e8296b12a26ac204ad4f2b7c476063ae857ef","abstract_canon_sha256":"6aa522745401ee2210dbc3891b4623d1e7130a11c3a73987311e5acdf5150ada"},"schema_version":"1.0"},"canonical_sha256":"cccca8f805f1477a42fc92f4d7db9f7df0ac1dad424d61b25ff167d5e00b329e","source":{"kind":"arxiv","id":"2509.26000","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZTGKR6AF6FDXUQX4SL2NPW47PX","target":"record","payload":{"canonical_record":{"source":{"id":"2509.26000","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T09:32:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e3f1bec8c6d81a6af47e0f83585e8296b12a26ac204ad4f2b7c476063ae857ef","abstract_canon_sha256":"6aa522745401ee2210dbc3891b4623d1e7130a11c3a73987311e5acdf5150ada"},"schema_version":"1.0"},"canonical_sha256":"cccca8f805f1477a42fc92f4d7db9f7df0ac1dad424d61b25ff167d5e00b329e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:44.363762Z","signature_b64":"KuGJZ9jaON4zukxU2d8ivlIsBdJdgFs6qDaQBfVsOoUX+sjg8CIAxKhi503GAYZfxc56fGua4GXQszYoMJTZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cccca8f805f1477a42fc92f4d7db9f7df0ac1dad424d61b25ff167d5e00b329e","last_reissued_at":"2026-06-10T01:09:44.363191Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:44.363191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.26000","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pXP/AkyeOFElREWsHFLc55ZXNd08xJGXPAl2t56PdBdymMsNiARCresuME3iMXZnOebW+4WOP2c2A9UeLhxXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:15.014259Z"},"content_sha256":"67b74c1d0da60154cb7c99a38b2b9e4d2bd9452280c8c9ecec3b7f5e654caca2","schema_version":"1.0","event_id":"sha256:67b74c1d0da60154cb7c99a38b2b9e4d2bd9452280c8c9ecec3b7f5e654caca2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZTGKR6AF6FDXUQX4SL2NPW47PX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Damien Ernst, Daniel Ebi, Gaspard Lambrechts, Klemens B\\\"ohm","submitted_at":"2025-09-30T09:32:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.26000","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/2509.26000/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q7ZAhDnqi35ooZSUH4JqGah7N7c/DFsbOSimDy5ARz8i2sapP3rRDdwtYz03sAGGBZLdCH/UdV8RIHdFMCRKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:15.015137Z"},"content_sha256":"73065105ff6c7a1147283bd6ec5d07ca725793df336b5e90008c5c33b083d4d6","schema_version":"1.0","event_id":"sha256:73065105ff6c7a1147283bd6ec5d07ca725793df336b5e90008c5c33b083d4d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZTGKR6AF6FDXUQX4SL2NPW47PX/bundle.json","state_url":"https://pith.science/pith/ZTGKR6AF6FDXUQX4SL2NPW47PX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZTGKR6AF6FDXUQX4SL2NPW47PX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T19:52:15Z","links":{"resolver":"https://pith.science/pith/ZTGKR6AF6FDXUQX4SL2NPW47PX","bundle":"https://pith.science/pith/ZTGKR6AF6FDXUQX4SL2NPW47PX/bundle.json","state":"https://pith.science/pith/ZTGKR6AF6FDXUQX4SL2NPW47PX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZTGKR6AF6FDXUQX4SL2NPW47PX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y7i9KmT3h9scEiyvlEJOztxIYd3GHbroXmAiJfqlWLN7rqN6W8kwty7wD8kycjS3011Ztv6kzt1bGOWiB5TSCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:52:15.021071Z","bundle_sha256":"7cdce3e174345181b74727520983e0ac78ca4f571454ebccd5664ea1268e3a7d"}}