{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F4NPK6HUBQIHAW6CN4NXNNC4IW","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":"2735bee2a343b35ed3d83fa063959870c20c69cbd16a5425021f5d3c3003edf6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-03-05T15:38:08Z","title_canon_sha256":"83ac31ee6b5c32276f5058f624ae32399273029f7942bb1be8fb893dd9aba3f4"},"schema_version":"1.0","source":{"id":"2603.05296","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.05296","created_at":"2026-07-09T01:19:52Z"},{"alias_kind":"arxiv_version","alias_value":"2603.05296v2","created_at":"2026-07-09T01:19:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.05296","created_at":"2026-07-09T01:19:52Z"},{"alias_kind":"pith_short_12","alias_value":"F4NPK6HUBQIH","created_at":"2026-07-09T01:19:52Z"},{"alias_kind":"pith_short_16","alias_value":"F4NPK6HUBQIHAW6C","created_at":"2026-07-09T01:19:52Z"},{"alias_kind":"pith_short_8","alias_value":"F4NPK6HU","created_at":"2026-07-09T01:19:52Z"}],"graph_snapshots":[{"event_id":"sha256:20c77e5e6929a3567a6d02e0faa2127bb2ce1f1baa737e1bfcf42d5ccafd8852","target":"graph","created_at":"2026-07-09T01:19:52Z","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/2603.05296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration. Yet, offline RL's performance often hinges on a brittle trade-off between (1) return maximization, which can push policies outside the dataset support, and (2) behavioral constraints, which typically require sensitive hyperparameter tuning. Latent steering offers a structural way to stay within the dataset support during RL, but existing offline adaptations commonly approximate action values using latent-space critics learned via indirect distillation, which can lose information and hind","authors_text":"Andrey Kolobov, Hokyun Im, Jianlong Fu, Youngwoon Lee","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-03-05T15:38:08Z","title":"Latent Policy Steering through One-Step Flow Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.05296","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:ada5f6eb03618dc6ebaac8c61a811190d81d0fc2dae53afd22709ad69819c110","target":"record","created_at":"2026-07-09T01:19:52Z","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":"2735bee2a343b35ed3d83fa063959870c20c69cbd16a5425021f5d3c3003edf6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-03-05T15:38:08Z","title_canon_sha256":"83ac31ee6b5c32276f5058f624ae32399273029f7942bb1be8fb893dd9aba3f4"},"schema_version":"1.0","source":{"id":"2603.05296","kind":"arxiv","version":2}},"canonical_sha256":"2f1af578f40c10705bc26f1b76b45c458b362973455ccb5e6fb38961eee61c77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f1af578f40c10705bc26f1b76b45c458b362973455ccb5e6fb38961eee61c77","first_computed_at":"2026-07-09T01:19:52.366263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:19:52.366263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"32vf64T8KqaLXIhgcE11giSB/yOveZdNu1XfpHZr4m5iq1YdxWOmCf2kI9AGJ3x4lMBozteYmtOHtts4gywnBA==","signature_status":"signed_v1","signed_at":"2026-07-09T01:19:52.366788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.05296","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ada5f6eb03618dc6ebaac8c61a811190d81d0fc2dae53afd22709ad69819c110","sha256:20c77e5e6929a3567a6d02e0faa2127bb2ce1f1baa737e1bfcf42d5ccafd8852"],"state_sha256":"67b7e9c34a217e1d38c0adb423cf206db49230730c0c7fae4c045e75ab6c310b"}