{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EPZPTRJDT7TRZ7JNQSAGFWW7V7","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":"11599428f77d93953f44f63b0c1c0990257b12537c0aeb783ae8979442cec3da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T02:18:44Z","title_canon_sha256":"4c4fe299d5cef0c9e49ac68351556d2716e26d16fd5f85f491074a2fedff94d5"},"schema_version":"1.0","source":{"id":"2606.05597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05597","created_at":"2026-06-05T01:14:55Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05597v1","created_at":"2026-06-05T01:14:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05597","created_at":"2026-06-05T01:14:55Z"},{"alias_kind":"pith_short_12","alias_value":"EPZPTRJDT7TR","created_at":"2026-06-05T01:14:55Z"},{"alias_kind":"pith_short_16","alias_value":"EPZPTRJDT7TRZ7JN","created_at":"2026-06-05T01:14:55Z"},{"alias_kind":"pith_short_8","alias_value":"EPZPTRJD","created_at":"2026-06-05T01:14:55Z"}],"graph_snapshots":[{"event_id":"sha256:c5017f86e917f2f543cd983720f73adc0b1ed422e128a654270265335795b1f8","target":"graph","created_at":"2026-06-05T01:14:55Z","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/2606.05597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training vision-language web agents with multi-step RL is compute-intensive, with two dominant forms of inefficiency: idle GPUs in synchronous RL, and trajectories that use more steps and tokens than necessary. We present AsyncWebRL, which addresses both. On the system side, an asynchronous design overlaps rollout, gradient update, and policy refresh across iterations, paired with two web-agent-specific adaptations, namely an everlasting rollout pool and lightweight screenshot handling, that together deliver up to a $2.9\\times$ end-to-end training-throughput speedup over the previously fastest","authors_text":"Aviral Kumar, Chenlu Ye, Hao Bai, Rui Yang, Spencer Whitehead, Tong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T02:18:44Z","title":"AsyncWebRL: Efficient Multi-Step RL for Visual Web Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05597","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:a4d3bd7d5eeca82133e29eabc62484ee640eae68461102885d7381e49f1104be","target":"record","created_at":"2026-06-05T01:14:55Z","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":"11599428f77d93953f44f63b0c1c0990257b12537c0aeb783ae8979442cec3da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T02:18:44Z","title_canon_sha256":"4c4fe299d5cef0c9e49ac68351556d2716e26d16fd5f85f491074a2fedff94d5"},"schema_version":"1.0","source":{"id":"2606.05597","kind":"arxiv","version":1}},"canonical_sha256":"23f2f9c5239fe71cfd2d848062dadfafcb93bcdf37083bfe9dcc8210f04716b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23f2f9c5239fe71cfd2d848062dadfafcb93bcdf37083bfe9dcc8210f04716b7","first_computed_at":"2026-06-05T01:14:55.939554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:55.939554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jzFU7MEBJ26LwB79YPiXPQQwH7da3am4BEcon1PBr3dQ8sRBIeVYOHMLbiFFeRs6g3cjNpwNSdzKU1XazLoyCg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:55.940046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4d3bd7d5eeca82133e29eabc62484ee640eae68461102885d7381e49f1104be","sha256:c5017f86e917f2f543cd983720f73adc0b1ed422e128a654270265335795b1f8"],"state_sha256":"4d031ecfbac196e07cd32f9b0708f3337c9207616c69a75e4faded9f7a3a43fe"}