{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FZYQNGC5OJRDLEPI7GKBYE74A7","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":"2b0cf3509866c3880203f5ae5e422cb06438148879751ee28e92c6fcbd03da69","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-10T15:54:25Z","title_canon_sha256":"043c2554283ddc58b656b06a71a624a299ba4cd44a5262d0cadd64df321ecacf"},"schema_version":"1.0","source":{"id":"2608.09762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09762","created_at":"2026-08-11T02:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09762v1","created_at":"2026-08-11T02:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09762","created_at":"2026-08-11T02:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"FZYQNGC5OJRD","created_at":"2026-08-11T02:24:57Z"},{"alias_kind":"pith_short_16","alias_value":"FZYQNGC5OJRDLEPI","created_at":"2026-08-11T02:24:57Z"},{"alias_kind":"pith_short_8","alias_value":"FZYQNGC5","created_at":"2026-08-11T02:24:57Z"}],"graph_snapshots":[{"event_id":"sha256:208d9acbe3d08b2b4e1a745fd37a838d2bb2b726d46dff59fabea6fa245e0f60","target":"graph","created_at":"2026-08-11T02:24:57Z","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/2608.09762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world online reinforcement learning (RL) provides a promising approach for training robotic manipulation policies directly in the physical world, avoiding the sim-to-real gap and enabling continuous policy refinement through human-in-the-loop interaction. Recent methods have demonstrated sample-efficient learning through human intervention but remain limited to small randomization ranges and encounter challenges with the non-stationarity induced by concurrently training multiple agents. To address these limitations, we introduce a unified framework that combines centralized training with ","authors_text":"Arash Ajoudani, Arturo Laurenzi, Changhao Li, Damiano Gasperini, Davide Torielli, Heng Zhang, Luca Muratore, Nikos Tsagarakis, Yifang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-10T15:54:25Z","title":"Efficient Real-World Online Reinforcement Learning for Robot Manipulation via Centralized Training and Critic Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09762","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:ac8a2740ed5c623fa77d817129b8848a2b41e41e635bc9bd0e9aaaba19a0563a","target":"record","created_at":"2026-08-11T02:24:57Z","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":"2b0cf3509866c3880203f5ae5e422cb06438148879751ee28e92c6fcbd03da69","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-10T15:54:25Z","title_canon_sha256":"043c2554283ddc58b656b06a71a624a299ba4cd44a5262d0cadd64df321ecacf"},"schema_version":"1.0","source":{"id":"2608.09762","kind":"arxiv","version":1}},"canonical_sha256":"2e7106985d72623591e8f9941c13fc07ce982b07b160098442b2bd5f48d0c23f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e7106985d72623591e8f9941c13fc07ce982b07b160098442b2bd5f48d0c23f","first_computed_at":"2026-08-11T02:24:57.752678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:24:57.752678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PdB+Wbs2QKEldTOD0U8pQ2vVYQ+pymb1W7Su4ZW5fdOz/HOdlVBR0Lg3+iC+17mkqKHZ+foaFSMMmE3UG7oHCw==","signature_status":"signed_v1","signed_at":"2026-08-11T02:24:57.754242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac8a2740ed5c623fa77d817129b8848a2b41e41e635bc9bd0e9aaaba19a0563a","sha256:208d9acbe3d08b2b4e1a745fd37a838d2bb2b726d46dff59fabea6fa245e0f60"],"state_sha256":"3933662643485124c0f2a9351c2cf155e31e8f14aa404a5578ff0798ea07995d"}