{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IX3GR6IVTQCTK4WJVVNMIKYMBI","short_pith_number":"pith:IX3GR6IV","schema_version":"1.0","canonical_sha256":"45f668f9159c053572c9ad5ac42b0c0a2830927040794a33c49450e75a83fa74","source":{"kind":"arxiv","id":"2607.19399","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aleksandr I. Panov, Aleksei Staroverov, Dmitriy Poyarkov","submitted_at":"2026-07-06T05:24:25Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.19399","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T05:24:25Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"1741620ab91731bbfb181243fea2ff446ec06b58a75da20fe37fbb4a344a6be9","abstract_canon_sha256":"23c114a90d310592ebcd30fdc6207899d5185e4a3747a7142ce019ecb03e178f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T00:23:48.043428Z","signature_b64":"/0jxTxi9Eu0H5nnGiv+EKlbaPPQ8QNdAevw3LYAyFKkx6OmTtyc1SEdVXGfSJ6YEbOD8Se/EUmbWJf38LNZgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45f668f9159c053572c9ad5ac42b0c0a2830927040794a33c49450e75a83fa74","last_reissued_at":"2026-07-23T00:23:48.042591Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T00:23:48.042591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aleksandr I. Panov, Aleksei Staroverov, Dmitriy Poyarkov","submitted_at":"2026-07-06T05:24:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19399","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/2607.19399/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.19399","created_at":"2026-07-23T00:23:48.043022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19399v1","created_at":"2026-07-23T00:23:48.043022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19399","created_at":"2026-07-23T00:23:48.043022+00:00"},{"alias_kind":"pith_short_12","alias_value":"IX3GR6IVTQCT","created_at":"2026-07-23T00:23:48.043022+00:00"},{"alias_kind":"pith_short_16","alias_value":"IX3GR6IVTQCTK4WJ","created_at":"2026-07-23T00:23:48.043022+00:00"},{"alias_kind":"pith_short_8","alias_value":"IX3GR6IV","created_at":"2026-07-23T00:23:48.043022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IX3GR6IVTQCTK4WJVVNMIKYMBI","json":"https://pith.science/pith/IX3GR6IVTQCTK4WJVVNMIKYMBI.json","graph_json":"https://pith.science/api/pith-number/IX3GR6IVTQCTK4WJVVNMIKYMBI/graph.json","events_json":"https://pith.science/api/pith-number/IX3GR6IVTQCTK4WJVVNMIKYMBI/events.json","paper":"https://pith.science/paper/IX3GR6IV"},"agent_actions":{"view_html":"https://pith.science/pith/IX3GR6IVTQCTK4WJVVNMIKYMBI","download_json":"https://pith.science/pith/IX3GR6IVTQCTK4WJVVNMIKYMBI.json","view_paper":"https://pith.science/paper/IX3GR6IV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19399&json=true","fetch_graph":"https://pith.science/api/pith-number/IX3GR6IVTQCTK4WJVVNMIKYMBI/graph.json","fetch_events":"https://pith.science/api/pith-number/IX3GR6IVTQCTK4WJVVNMIKYMBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IX3GR6IVTQCTK4WJVVNMIKYMBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IX3GR6IVTQCTK4WJVVNMIKYMBI/action/storage_attestation","attest_author":"https://pith.science/pith/IX3GR6IVTQCTK4WJVVNMIKYMBI/action/author_attestation","sign_citation":"https://pith.science/pith/IX3GR6IVTQCTK4WJVVNMIKYMBI/action/citation_signature","submit_replication":"https://pith.science/pith/IX3GR6IVTQCTK4WJVVNMIKYMBI/action/replication_record"}},"created_at":"2026-07-23T00:23:48.043022+00:00","updated_at":"2026-07-23T00:23:48.043022+00:00"}