{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AL5DHXQZMRTXDGM57YJFTCPWRE","short_pith_number":"pith:AL5DHXQZ","canonical_record":{"source":{"id":"2606.22056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T14:14:24Z","cross_cats_sorted":[],"title_canon_sha256":"e3deed61340fe2b899a3382eff689bac955b9d06c3be4828b667748d024b3205","abstract_canon_sha256":"4e54d8e8bfd5bdaf65a8880cdf0cafdc42dc480805f83f22b2a55442f0a247ae"},"schema_version":"1.0"},"canonical_sha256":"02fa33de19646771999dfe125989f6892abee710a68b531f4edaae15b5e1fec7","source":{"kind":"arxiv","id":"2606.22056","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22056","created_at":"2026-06-23T02:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22056v1","created_at":"2026-06-23T02:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22056","created_at":"2026-06-23T02:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"AL5DHXQZMRTX","created_at":"2026-06-23T02:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"AL5DHXQZMRTXDGM5","created_at":"2026-06-23T02:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"AL5DHXQZ","created_at":"2026-06-23T02:13:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AL5DHXQZMRTXDGM57YJFTCPWRE","target":"record","payload":{"canonical_record":{"source":{"id":"2606.22056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T14:14:24Z","cross_cats_sorted":[],"title_canon_sha256":"e3deed61340fe2b899a3382eff689bac955b9d06c3be4828b667748d024b3205","abstract_canon_sha256":"4e54d8e8bfd5bdaf65a8880cdf0cafdc42dc480805f83f22b2a55442f0a247ae"},"schema_version":"1.0"},"canonical_sha256":"02fa33de19646771999dfe125989f6892abee710a68b531f4edaae15b5e1fec7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:06.625469Z","signature_b64":"YF6ptvGRi0nQPnFc+RTxb5M2A5E7yVSsLSv7uMz42LFIbfUPryAs2j784/aFKYTZuIzW9tACI+Is3UYZopUuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02fa33de19646771999dfe125989f6892abee710a68b531f4edaae15b5e1fec7","last_reissued_at":"2026-06-23T02:13:06.625073Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:06.625073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.22056","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g8IG2vTnnsQLzYXbI1MlPAND5K7Ro5t5CZj4JTIkfDQCmSzTm/WsOknlaMBA1Q3bOkEmCRkYgmCrAJ9T7Xp5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T14:05:56.770298Z"},"content_sha256":"fc6337fcea195b85d9ea5f19ba4e6e7b96efedf53e655b53465bb1bbdc711c78","schema_version":"1.0","event_id":"sha256:fc6337fcea195b85d9ea5f19ba4e6e7b96efedf53e655b53465bb1bbdc711c78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AL5DHXQZMRTXDGM57YJFTCPWRE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenyang Wang, Lei Yuan, Tian Xu, Yang Yu, Yi-Chen Li, Zexuan Chen, Zhilong Zhang","submitted_at":"2026-06-20T14:14:24Z","abstract_excerpt":"Adversarial imitation learning (AIL) achieves high-quality imitation compared to behavioral cloning (BC), but demands substantial online environment interaction. Recent empirical work has explored initializing AIL algorithms with BC pretrained policies to address this limitation, yet a rigorous theoretical understanding of pretraining's role in AIL remains elusive. This paper provides a systematic theoretical analysis and introduces principled pretraining algorithms for accelerating AIL. We begin by analyzing AIL with policy pretraining alone, identifying reward error as the dominant source of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22056","kind":"arxiv","version":1},"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/2606.22056/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":"2026-06-23T02:13:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hnnhm2Q9i0zClBvBVAJu1HWFxNi5CM1BHq7MA+wZgbWtpp9un6e7Hr0ZKXj3ooUIltQSlPpm/pzjxnl7sC+DAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T14:05:56.770706Z"},"content_sha256":"9fb83ca7c59c55957b9ca90cab5108dbbf011ae10f623bdb2a439794472f35f1","schema_version":"1.0","event_id":"sha256:9fb83ca7c59c55957b9ca90cab5108dbbf011ae10f623bdb2a439794472f35f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AL5DHXQZMRTXDGM57YJFTCPWRE/bundle.json","state_url":"https://pith.science/pith/AL5DHXQZMRTXDGM57YJFTCPWRE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AL5DHXQZMRTXDGM57YJFTCPWRE/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":"2026-07-01T14:05:56Z","links":{"resolver":"https://pith.science/pith/AL5DHXQZMRTXDGM57YJFTCPWRE","bundle":"https://pith.science/pith/AL5DHXQZMRTXDGM57YJFTCPWRE/bundle.json","state":"https://pith.science/pith/AL5DHXQZMRTXDGM57YJFTCPWRE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AL5DHXQZMRTXDGM57YJFTCPWRE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AL5DHXQZMRTXDGM57YJFTCPWRE","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":"4e54d8e8bfd5bdaf65a8880cdf0cafdc42dc480805f83f22b2a55442f0a247ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T14:14:24Z","title_canon_sha256":"e3deed61340fe2b899a3382eff689bac955b9d06c3be4828b667748d024b3205"},"schema_version":"1.0","source":{"id":"2606.22056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22056","created_at":"2026-06-23T02:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22056v1","created_at":"2026-06-23T02:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22056","created_at":"2026-06-23T02:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"AL5DHXQZMRTX","created_at":"2026-06-23T02:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"AL5DHXQZMRTXDGM5","created_at":"2026-06-23T02:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"AL5DHXQZ","created_at":"2026-06-23T02:13:06Z"}],"graph_snapshots":[{"event_id":"sha256:9fb83ca7c59c55957b9ca90cab5108dbbf011ae10f623bdb2a439794472f35f1","target":"graph","created_at":"2026-06-23T02:13:06Z","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/2606.22056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial imitation learning (AIL) achieves high-quality imitation compared to behavioral cloning (BC), but demands substantial online environment interaction. Recent empirical work has explored initializing AIL algorithms with BC pretrained policies to address this limitation, yet a rigorous theoretical understanding of pretraining's role in AIL remains elusive. This paper provides a systematic theoretical analysis and introduces principled pretraining algorithms for accelerating AIL. We begin by analyzing AIL with policy pretraining alone, identifying reward error as the dominant source of","authors_text":"Chenyang Wang, Lei Yuan, Tian Xu, Yang Yu, Yi-Chen Li, Zexuan Chen, Zhilong Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T14:14:24Z","title":"Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22056","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:fc6337fcea195b85d9ea5f19ba4e6e7b96efedf53e655b53465bb1bbdc711c78","target":"record","created_at":"2026-06-23T02:13:06Z","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":"4e54d8e8bfd5bdaf65a8880cdf0cafdc42dc480805f83f22b2a55442f0a247ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T14:14:24Z","title_canon_sha256":"e3deed61340fe2b899a3382eff689bac955b9d06c3be4828b667748d024b3205"},"schema_version":"1.0","source":{"id":"2606.22056","kind":"arxiv","version":1}},"canonical_sha256":"02fa33de19646771999dfe125989f6892abee710a68b531f4edaae15b5e1fec7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02fa33de19646771999dfe125989f6892abee710a68b531f4edaae15b5e1fec7","first_computed_at":"2026-06-23T02:13:06.625073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:06.625073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YF6ptvGRi0nQPnFc+RTxb5M2A5E7yVSsLSv7uMz42LFIbfUPryAs2j784/aFKYTZuIzW9tACI+Is3UYZopUuBg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:06.625469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc6337fcea195b85d9ea5f19ba4e6e7b96efedf53e655b53465bb1bbdc711c78","sha256:9fb83ca7c59c55957b9ca90cab5108dbbf011ae10f623bdb2a439794472f35f1"],"state_sha256":"7f32fd585eb633876f80bb6b01432cc52182aebc648f262a91cc6d597d271b75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OtS369r7uTCfa0RKIwhuvyUur/WsRMozbE0YPfoyW1xq5c4LBzCZb84ccaPFKCBTNoJ3Af4VoTE1KPBj2ihnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T14:05:56.772711Z","bundle_sha256":"bd958262d953c05d01f5e31eba174b11eff70454f51be6c36eee0b23dcbe5270"}}