{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5XBO2DTG53YTFMHPAKQLN4CIUR","short_pith_number":"pith:5XBO2DTG","canonical_record":{"source":{"id":"2606.02194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T12:49:14Z","cross_cats_sorted":[],"title_canon_sha256":"dfd0bc624a49b2d299bc1684fdf4ef92e6be93d8385c6ba0052d41240ca587e0","abstract_canon_sha256":"9ceceb6d99bbc57b97c680a4f437887a19e1b5261eccb35fabf71b24ffa821e6"},"schema_version":"1.0"},"canonical_sha256":"edc2ed0e66eef132b0ef02a0b6f048a474b086a4a0938ddcf362ebba98394d97","source":{"kind":"arxiv","id":"2606.02194","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02194","created_at":"2026-06-02T03:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02194v1","created_at":"2026-06-02T03:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02194","created_at":"2026-06-02T03:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"5XBO2DTG53YT","created_at":"2026-06-02T03:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"5XBO2DTG53YTFMHP","created_at":"2026-06-02T03:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"5XBO2DTG","created_at":"2026-06-02T03:04:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5XBO2DTG53YTFMHPAKQLN4CIUR","target":"record","payload":{"canonical_record":{"source":{"id":"2606.02194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T12:49:14Z","cross_cats_sorted":[],"title_canon_sha256":"dfd0bc624a49b2d299bc1684fdf4ef92e6be93d8385c6ba0052d41240ca587e0","abstract_canon_sha256":"9ceceb6d99bbc57b97c680a4f437887a19e1b5261eccb35fabf71b24ffa821e6"},"schema_version":"1.0"},"canonical_sha256":"edc2ed0e66eef132b0ef02a0b6f048a474b086a4a0938ddcf362ebba98394d97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:52.855120Z","signature_b64":"sIQ4f5b2ZFg3+fzDzO/Eeh8ZtJ9vtkMm/n5z5VN2r9ii0cQ5XL7clYQAb+TokY9m+PwXt9PMImRKxQCn2YRUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edc2ed0e66eef132b0ef02a0b6f048a474b086a4a0938ddcf362ebba98394d97","last_reissued_at":"2026-06-02T03:04:52.854655Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:52.854655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.02194","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":"2026-06-02T03:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8hUbHBilFPHQjvK/BzsQuct5fIE5j0g7q7enf8a9pP9V27KbRmtlRRk5vsMzqB+nkxLXibc8vZgV2Qz+FxVKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T06:18:46.173674Z"},"content_sha256":"ff25e50f0217c0f32c5c885fba4d54469a59051fa1bdb46521ba464c04435c5b","schema_version":"1.0","event_id":"sha256:ff25e50f0217c0f32c5c885fba4d54469a59051fa1bdb46521ba464c04435c5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5XBO2DTG53YTFMHPAKQLN4CIUR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christian Scherer, Daniel Palenicek, Ingmar Posner, Jan Peters, Joe Watson, Theo Gruner","submitted_at":"2026-06-01T12:49:14Z","abstract_excerpt":"Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation. Reinforcement learning (RL) can be used as a means to finetune these policies further using additional experience. An open question is whether RL is more sample-efficient than collecting more human demonstrations. Prior work has finetuned large pretrained policies in a scalable fashion by applying RL to a smaller residual policy that corrects the pretrained model. However, for the typical spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02194","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/2606.02194/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":"2026-06-02T03:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kFKUNr+DcK4bMTODz98ichg2upFK43ChU63waUiMr/r9+fFn8iYtei0VkN6oqRD6po8RE7O/5YyNHwJCaM88AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T06:18:46.174070Z"},"content_sha256":"5fd70d1d3056d6d1c1a51dd026480b3ec0f3aa2cc21a1c3383b724be4f732540","schema_version":"1.0","event_id":"sha256:5fd70d1d3056d6d1c1a51dd026480b3ec0f3aa2cc21a1c3383b724be4f732540"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XBO2DTG53YTFMHPAKQLN4CIUR/bundle.json","state_url":"https://pith.science/pith/5XBO2DTG53YTFMHPAKQLN4CIUR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XBO2DTG53YTFMHPAKQLN4CIUR/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":"2026-06-03T06:18:46Z","links":{"resolver":"https://pith.science/pith/5XBO2DTG53YTFMHPAKQLN4CIUR","bundle":"https://pith.science/pith/5XBO2DTG53YTFMHPAKQLN4CIUR/bundle.json","state":"https://pith.science/pith/5XBO2DTG53YTFMHPAKQLN4CIUR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XBO2DTG53YTFMHPAKQLN4CIUR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5XBO2DTG53YTFMHPAKQLN4CIUR","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":"9ceceb6d99bbc57b97c680a4f437887a19e1b5261eccb35fabf71b24ffa821e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T12:49:14Z","title_canon_sha256":"dfd0bc624a49b2d299bc1684fdf4ef92e6be93d8385c6ba0052d41240ca587e0"},"schema_version":"1.0","source":{"id":"2606.02194","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02194","created_at":"2026-06-02T03:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02194v1","created_at":"2026-06-02T03:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02194","created_at":"2026-06-02T03:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"5XBO2DTG53YT","created_at":"2026-06-02T03:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"5XBO2DTG53YTFMHP","created_at":"2026-06-02T03:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"5XBO2DTG","created_at":"2026-06-02T03:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:5fd70d1d3056d6d1c1a51dd026480b3ec0f3aa2cc21a1c3383b724be4f732540","target":"graph","created_at":"2026-06-02T03:04:52Z","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/2606.02194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation. Reinforcement learning (RL) can be used as a means to finetune these policies further using additional experience. An open question is whether RL is more sample-efficient than collecting more human demonstrations. Prior work has finetuned large pretrained policies in a scalable fashion by applying RL to a smaller residual policy that corrects the pretrained model. However, for the typical spa","authors_text":"Christian Scherer, Daniel Palenicek, Ingmar Posner, Jan Peters, Joe Watson, Theo Gruner","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T12:49:14Z","title":"Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02194","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:ff25e50f0217c0f32c5c885fba4d54469a59051fa1bdb46521ba464c04435c5b","target":"record","created_at":"2026-06-02T03:04:52Z","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":"9ceceb6d99bbc57b97c680a4f437887a19e1b5261eccb35fabf71b24ffa821e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T12:49:14Z","title_canon_sha256":"dfd0bc624a49b2d299bc1684fdf4ef92e6be93d8385c6ba0052d41240ca587e0"},"schema_version":"1.0","source":{"id":"2606.02194","kind":"arxiv","version":1}},"canonical_sha256":"edc2ed0e66eef132b0ef02a0b6f048a474b086a4a0938ddcf362ebba98394d97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edc2ed0e66eef132b0ef02a0b6f048a474b086a4a0938ddcf362ebba98394d97","first_computed_at":"2026-06-02T03:04:52.854655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:04:52.854655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sIQ4f5b2ZFg3+fzDzO/Eeh8ZtJ9vtkMm/n5z5VN2r9ii0cQ5XL7clYQAb+TokY9m+PwXt9PMImRKxQCn2YRUCQ==","signature_status":"signed_v1","signed_at":"2026-06-02T03:04:52.855120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02194","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff25e50f0217c0f32c5c885fba4d54469a59051fa1bdb46521ba464c04435c5b","sha256:5fd70d1d3056d6d1c1a51dd026480b3ec0f3aa2cc21a1c3383b724be4f732540"],"state_sha256":"18afcc8b074a48a52331e0118555bf148feefcc7e9196abebf1f71d2ccbfd21e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9ARifyQ0A6SFjPy28Hn5hCbwsygwbOsV2UAnv1SjKeg4ue4ySkUpiZWcIzJFI5EGgTvZpVzphI+NjsFJQU0BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T06:18:46.176254Z","bundle_sha256":"2e193e10ab1e5cf8e87741a90739ac2de584ba5df5d734319cf5ca15f4e645c8"}}