{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IX3GR6IVTQCTK4WJVVNMIKYMBI","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":"23c114a90d310592ebcd30fdc6207899d5185e4a3747a7142ce019ecb03e178f","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T05:24:25Z","title_canon_sha256":"1741620ab91731bbfb181243fea2ff446ec06b58a75da20fe37fbb4a344a6be9"},"schema_version":"1.0","source":{"id":"2607.19399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19399","created_at":"2026-07-23T00:23:48Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19399v1","created_at":"2026-07-23T00:23:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19399","created_at":"2026-07-23T00:23:48Z"},{"alias_kind":"pith_short_12","alias_value":"IX3GR6IVTQCT","created_at":"2026-07-23T00:23:48Z"},{"alias_kind":"pith_short_16","alias_value":"IX3GR6IVTQCTK4WJ","created_at":"2026-07-23T00:23:48Z"},{"alias_kind":"pith_short_8","alias_value":"IX3GR6IV","created_at":"2026-07-23T00:23:48Z"}],"graph_snapshots":[{"event_id":"sha256:ba641f2ecad152b2b58d46b35629ed06feee9f3c051292f748bdbdf77709dff1","target":"graph","created_at":"2026-07-23T00:23:48Z","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/2607.19399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is commonly observed that online reinforcement learning (RL) produces better-performing strategies than offline methods across a broad range of performance measures. In particular, RL-trained policies exhibit stronger out-of-distribution (OOD) behavior, where models trained only with imitation learning approaches often struggle. A recent study introduced an OOD-focused benchmark and reported that RL-trained vision-language-action (VLA) policies achieve noticeably better OOD performance and slightly better in-distribution (IND) performance than their counterparts trained with supervised fine","authors_text":"Aleksandr I. Panov, Aleksei Staroverov, Dmitriy Poyarkov","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T05:24:25Z","title":"Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19399","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:c59f249566b157797b6fc7425a3798589c36cc706038ebb24a12bd34ad670954","target":"record","created_at":"2026-07-23T00:23:48Z","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":"23c114a90d310592ebcd30fdc6207899d5185e4a3747a7142ce019ecb03e178f","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T05:24:25Z","title_canon_sha256":"1741620ab91731bbfb181243fea2ff446ec06b58a75da20fe37fbb4a344a6be9"},"schema_version":"1.0","source":{"id":"2607.19399","kind":"arxiv","version":1}},"canonical_sha256":"45f668f9159c053572c9ad5ac42b0c0a2830927040794a33c49450e75a83fa74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45f668f9159c053572c9ad5ac42b0c0a2830927040794a33c49450e75a83fa74","first_computed_at":"2026-07-23T00:23:48.042591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T00:23:48.042591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/0jxTxi9Eu0H5nnGiv+EKlbaPPQ8QNdAevw3LYAyFKkx6OmTtyc1SEdVXGfSJ6YEbOD8Se/EUmbWJf38LNZgBg==","signature_status":"signed_v1","signed_at":"2026-07-23T00:23:48.043428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c59f249566b157797b6fc7425a3798589c36cc706038ebb24a12bd34ad670954","sha256:ba641f2ecad152b2b58d46b35629ed06feee9f3c051292f748bdbdf77709dff1"],"state_sha256":"eb308fd76307c8cd6be68aa11ebe9007f91a86c0cec6c2e2b315b2eb6c2a8454"}