{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZO3TO2T6MWNCEK2QKZBJVE34QJ","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":"b185847398d8a5b1323169be882bf9528cc2ec549493b4061c4ca8aca9b96f3c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-10T22:49:46Z","title_canon_sha256":"58a54e9944d049fee997e9cd07e806fa100292f562d0cf399f6e38ecc17e4a27"},"schema_version":"1.0","source":{"id":"2603.10263","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10263","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10263v2","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10263","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"pith_short_12","alias_value":"ZO3TO2T6MWNC","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"pith_short_16","alias_value":"ZO3TO2T6MWNCEK2Q","created_at":"2026-07-02T01:17:29Z"},{"alias_kind":"pith_short_8","alias_value":"ZO3TO2T6","created_at":"2026-07-02T01:17:29Z"}],"graph_snapshots":[{"event_id":"sha256:a3e13cf1c297e2234eb15d030cef8fc5d8fa9926478cc153a88397c2ec2a4949","target":"graph","created_at":"2026-07-02T01:17:29Z","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/2603.10263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a \"distribution contraction\" operator to refine pretrained generative robot policies. DICE-RL turns a pretrained behavior prior into a high-performing \"pro\" policy by amplifying high-success behaviors from online feedback. We pretrain a diffusion- or flow-based policy for broad behavioral coverage, then finetune it with a stable, sample-efficient residual off-policy RL framework that combines selective behavior regularization with value-guided action selection. Extensive","authors_text":"Shuran Song, Zhanyi Sun","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-10T22:49:46Z","title":"From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10263","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":"sha256:36e61658e382b560f369624b9f98d3b13b3991ae1ea26f668436e8837690d302","target":"record","created_at":"2026-07-02T01:17:29Z","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":"b185847398d8a5b1323169be882bf9528cc2ec549493b4061c4ca8aca9b96f3c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-10T22:49:46Z","title_canon_sha256":"58a54e9944d049fee997e9cd07e806fa100292f562d0cf399f6e38ecc17e4a27"},"schema_version":"1.0","source":{"id":"2603.10263","kind":"arxiv","version":2}},"canonical_sha256":"cbb7376a7e659a222b5056429a937c826a2227b3a80b979ee937cf1e74f49439","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbb7376a7e659a222b5056429a937c826a2227b3a80b979ee937cf1e74f49439","first_computed_at":"2026-07-02T01:17:29.308942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:29.308942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AUwmITRUuw2Nw2o5r0MOfSzNMjWaBfRHFwGZGh7kxOAdmOt7h4yLHaPJqNHUmz6i3Feu7KbeNF9q8zy1jzgDBw==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:29.309462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.10263","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36e61658e382b560f369624b9f98d3b13b3991ae1ea26f668436e8837690d302","sha256:a3e13cf1c297e2234eb15d030cef8fc5d8fa9926478cc153a88397c2ec2a4949"],"state_sha256":"16dfbc75cb9ebaf9e2090a8ccb44cf1e66b04bf031cef0d1be05c00fe7cf6f43"}