{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BFBVFIO2AW2R4BNJLVCUOYQM4B","short_pith_number":"pith:BFBVFIO2","canonical_record":{"source":{"id":"2511.07288","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-10T16:35:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52cf3800324c6fdaf82999f3a244c64c2af4a009f8cdc00698307dcc653b48da","abstract_canon_sha256":"82c8e6b68b7b2fc53954cdd060e9e7ccc1b778d0a05f61ecf2bdca1c5706dfcb"},"schema_version":"1.0"},"canonical_sha256":"094352a1da05b51e05a95d4547620ce04c4fd3b4634e57cf2cc7594ba6b5d49d","source":{"kind":"arxiv","id":"2511.07288","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BFBVFIO2AW2R4BNJLVCUOYQM4B","target":"record","payload":{"canonical_record":{"source":{"id":"2511.07288","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-10T16:35:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52cf3800324c6fdaf82999f3a244c64c2af4a009f8cdc00698307dcc653b48da","abstract_canon_sha256":"82c8e6b68b7b2fc53954cdd060e9e7ccc1b778d0a05f61ecf2bdca1c5706dfcb"},"schema_version":"1.0"},"canonical_sha256":"094352a1da05b51e05a95d4547620ce04c4fd3b4634e57cf2cc7594ba6b5d49d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:37.269441Z","signature_b64":"wMJG62nXVSR+DO4a5sEAAqzh4lqbDeA+8BhVc4SY4WQ+Y8hnRaeJVt2wfhXb+yrw5aNL7gdoREnfb6HvI8xkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"094352a1da05b51e05a95d4547620ce04c4fd3b4634e57cf2cc7594ba6b5d49d","last_reissued_at":"2026-05-20T00:05:37.268440Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:37.268440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.07288","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VfcFVEVODCeBGiFnjsEzWmEmHmuwZWTY2dFk6zegdkhhWTKfQBjoC6R9qzGeEIkmFb/KXehRKtbh+jhgyUlhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T17:11:19.599517Z"},"content_sha256":"87c6b2ae1553a164e2304c1b99a2209a80fddad79253b72c72941c51b64b2fce","schema_version":"1.0","event_id":"sha256:87c6b2ae1553a164e2304c1b99a2209a80fddad79253b72c72941c51b64b2fce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BFBVFIO2AW2R4BNJLVCUOYQM4B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enabling Off-Policy Imitation Learning with Deep Actor Critic Stabilization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sayambhu Sen, Shalabh Bhatnagar","submitted_at":"2025-11-10T16:35:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07288","kind":"arxiv","version":2},"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/2511.07288/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":"2026-05-20T00:05:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p0AaSO5Ah3ZZ/RJj4nWAq8AET+shsPPdxO4H8easMl4LLCapl8X9+PPeHAdzAgJS8MPitbECmSoYrRua7yh7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T17:11:19.600347Z"},"content_sha256":"0a958d8a6d1b9d274d12a9d9f99b269ed0b51a1aad0be424ba5b17f40ef4e877","schema_version":"1.0","event_id":"sha256:0a958d8a6d1b9d274d12a9d9f99b269ed0b51a1aad0be424ba5b17f40ef4e877"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BFBVFIO2AW2R4BNJLVCUOYQM4B/bundle.json","state_url":"https://pith.science/pith/BFBVFIO2AW2R4BNJLVCUOYQM4B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BFBVFIO2AW2R4BNJLVCUOYQM4B/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":"2026-06-06T17:11:19Z","links":{"resolver":"https://pith.science/pith/BFBVFIO2AW2R4BNJLVCUOYQM4B","bundle":"https://pith.science/pith/BFBVFIO2AW2R4BNJLVCUOYQM4B/bundle.json","state":"https://pith.science/pith/BFBVFIO2AW2R4BNJLVCUOYQM4B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BFBVFIO2AW2R4BNJLVCUOYQM4B/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sH99QBGruKezIgw4cdUku+AOApPhggLAjPVD6n1TUfoAR8oF0giT3o/wJuv1HRDeM+rCtcDTMfilCE5TxtunAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T17:11:19.605882Z","bundle_sha256":"5f0c19ab33ca67f0a808ac3795d6f9772c0d26026241eacc29b44886ec6fc9d3"}}