{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BFBVFIO2AW2R4BNJLVCUOYQM4B","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":"82c8e6b68b7b2fc53954cdd060e9e7ccc1b778d0a05f61ecf2bdca1c5706dfcb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-10T16:35:50Z","title_canon_sha256":"52cf3800324c6fdaf82999f3a244c64c2af4a009f8cdc00698307dcc653b48da"},"schema_version":"1.0","source":{"id":"2511.07288","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.07288","created_at":"2026-05-20T00:05:37Z"},{"alias_kind":"arxiv_version","alias_value":"2511.07288v2","created_at":"2026-05-20T00:05:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07288","created_at":"2026-05-20T00:05:37Z"},{"alias_kind":"pith_short_12","alias_value":"BFBVFIO2AW2R","created_at":"2026-05-20T00:05:37Z"},{"alias_kind":"pith_short_16","alias_value":"BFBVFIO2AW2R4BNJ","created_at":"2026-05-20T00:05:37Z"},{"alias_kind":"pith_short_8","alias_value":"BFBVFIO2","created_at":"2026-05-20T00:05:37Z"}],"graph_snapshots":[{"event_id":"sha256:0a958d8a6d1b9d274d12a9d9f99b269ed0b51a1aad0be424ba5b17f40ef4e877","target":"graph","created_at":"2026-05-20T00:05:37Z","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/2511.07288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning complex policies with Reinforcement Learning (RL) is often hindered by instability and slow convergence, a problem exacerbated by the difficulty of reward engineering. Imitation Learning (IL) from expert demonstrations bypasses this reliance on rewards. However, state-of-the-art IL methods, exemplified by Generative Adversarial Imitation Learning (GAIL)Ho et. al, suffer from severe sample inefficiency. This is a direct consequence of their foundational on-policy algorithms, such as TRPO Schulman et.al. In this work, we introduce an adversarial imitation learning algorithm that incorpo","authors_text":"Sayambhu Sen, Shalabh Bhatnagar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-10T16:35:50Z","title":"Enabling Off-Policy Imitation Learning with Deep Actor Critic Stabilization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07288","kind":"arxiv","version":2},"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":"sha256:87c6b2ae1553a164e2304c1b99a2209a80fddad79253b72c72941c51b64b2fce","target":"record","created_at":"2026-05-20T00:05:37Z","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":"82c8e6b68b7b2fc53954cdd060e9e7ccc1b778d0a05f61ecf2bdca1c5706dfcb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-10T16:35:50Z","title_canon_sha256":"52cf3800324c6fdaf82999f3a244c64c2af4a009f8cdc00698307dcc653b48da"},"schema_version":"1.0","source":{"id":"2511.07288","kind":"arxiv","version":2}},"canonical_sha256":"094352a1da05b51e05a95d4547620ce04c4fd3b4634e57cf2cc7594ba6b5d49d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"094352a1da05b51e05a95d4547620ce04c4fd3b4634e57cf2cc7594ba6b5d49d","first_computed_at":"2026-05-20T00:05:37.268440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:37.268440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wMJG62nXVSR+DO4a5sEAAqzh4lqbDeA+8BhVc4SY4WQ+Y8hnRaeJVt2wfhXb+yrw5aNL7gdoREnfb6HvI8xkCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:37.269441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.07288","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87c6b2ae1553a164e2304c1b99a2209a80fddad79253b72c72941c51b64b2fce","sha256:0a958d8a6d1b9d274d12a9d9f99b269ed0b51a1aad0be424ba5b17f40ef4e877"],"state_sha256":"2b307c279d934dffef192647faea597d677dca10e51af65ca4f4d89c55b09e80"}