{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:USLONIBFBKNHJZFHPPVXGZG7BR","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":"b1104f07489ac1d85e257638c4c9019be45fbfebae7680b65baedb06c1025d5d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T10:40:28Z","title_canon_sha256":"9f260fa9c28358becc92f6ee1ef36bd4ec09d93e8e7d6f0185963469cf47bb42"},"schema_version":"1.0","source":{"id":"2606.01151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01151","created_at":"2026-06-02T02:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01151v1","created_at":"2026-06-02T02:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01151","created_at":"2026-06-02T02:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"USLONIBFBKNH","created_at":"2026-06-02T02:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"USLONIBFBKNHJZFH","created_at":"2026-06-02T02:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"USLONIBF","created_at":"2026-06-02T02:04:25Z"}],"graph_snapshots":[{"event_id":"sha256:5bff3de1840a8b3f40a91da1ee49b5f9b3270ef3371d01514210ee9eee95ac25","target":"graph","created_at":"2026-06-02T02:04:25Z","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/2606.01151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Behavior cloning with high-capacity generative policies achieves strong imitation performance, but is often limited by demonstration coverage and distribution shift. Direct reinforcement learning fine-tuning can improve performance, but updating large action decoders is frequently unstable and sample inefficient. We propose Lagrangian Perturbation Diffusion Steering (LP-DS), a lightweight adaptation method that improves a frozen generative policy by learning a compact noise-space perturbation before decoding. LP-DS optimizes this perturbation with a Lagrangian trust-region objective, improving","authors_text":"Hikmet Simsir, Ozgur S. Oguz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T10:40:28Z","title":"Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01151","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":"sha256:6e4aa05e9929df304109603faeb3fe93da66e2d7365d03e4781bcfdb2c8a4cfe","target":"record","created_at":"2026-06-02T02:04:25Z","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":"b1104f07489ac1d85e257638c4c9019be45fbfebae7680b65baedb06c1025d5d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T10:40:28Z","title_canon_sha256":"9f260fa9c28358becc92f6ee1ef36bd4ec09d93e8e7d6f0185963469cf47bb42"},"schema_version":"1.0","source":{"id":"2606.01151","kind":"arxiv","version":1}},"canonical_sha256":"a496e6a0250a9a74e4a77beb7364df0c7a382205975917d4fe1ef7291e50b9f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a496e6a0250a9a74e4a77beb7364df0c7a382205975917d4fe1ef7291e50b9f8","first_computed_at":"2026-06-02T02:04:25.152885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:25.152885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CW39NssjqJQxnRmok0gbX5tij8ohik6zk5V2Gr0AcM+gqsLIU6LpTsBLsgz+L/greYsy5TGMWgqBWokRAg4FDg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:25.153301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e4aa05e9929df304109603faeb3fe93da66e2d7365d03e4781bcfdb2c8a4cfe","sha256:5bff3de1840a8b3f40a91da1ee49b5f9b3270ef3371d01514210ee9eee95ac25"],"state_sha256":"285d88ca7e11f5a4da05f9179fa8393fdd17977e9659cef14c2d88e96913632a"}