{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HDDNTKDNVFZNYNS6I6SWWZ3FRD","short_pith_number":"pith:HDDNTKDN","schema_version":"1.0","canonical_sha256":"38c6d9a86da972dc365e47a56b676588ed707d4e29602a47adf683f791101da3","source":{"kind":"arxiv","id":"2606.02031","version":1},"attestation_state":"computed","paper":{"title":"OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Baolin Peng, Hao Bai, Hao Cheng, Huan Zhang, Jianfeng Gao, Qianhui Wu, Rui Yang, Tong Zhang, Wenlin Yao, Yuxi Chen","submitted_at":"2026-06-01T10:20:10Z","abstract_excerpt":"Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, while open agents still depend heavily on supervised post-training over large collections of curated web trajectories. This dependence creates a major scalability bottleneck: high-quality demonstrations are expensive to collect, and static datasets offer limited coverage of the diverse, ever-changing open web. Although online RL has shown promise for text-based agents, its potent"},"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":"2606.02031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T10:20:10Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"caf074a9c7be3fd0b4f3e97ef3ec14843bd0550137a82acd6679c50f5c20ec2f","abstract_canon_sha256":"e363926fc3de7a28ca456d9ee969ef6ab8680df84b372cc5683f856b48093cc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:04.041743Z","signature_b64":"T/Hz5iUGnmFvrGzHxjgwcKzlqsDAZM/YhmJLnLwI/L+CmrGgvytp7PhPpPEhiosO7r1l9X9XWBunKe2UF0RiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38c6d9a86da972dc365e47a56b676588ed707d4e29602a47adf683f791101da3","last_reissued_at":"2026-06-02T02:05:04.041343Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:04.041343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Baolin Peng, Hao Bai, Hao Cheng, Huan Zhang, Jianfeng Gao, Qianhui Wu, Rui Yang, Tong Zhang, Wenlin Yao, Yuxi Chen","submitted_at":"2026-06-01T10:20:10Z","abstract_excerpt":"Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, while open agents still depend heavily on supervised post-training over large collections of curated web trajectories. This dependence creates a major scalability bottleneck: high-quality demonstrations are expensive to collect, and static datasets offer limited coverage of the diverse, ever-changing open web. Although online RL has shown promise for text-based agents, its potent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02031","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/2606.02031/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":"2606.02031","created_at":"2026-06-02T02:05:04.041402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02031v1","created_at":"2026-06-02T02:05:04.041402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02031","created_at":"2026-06-02T02:05:04.041402+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDDNTKDNVFZN","created_at":"2026-06-02T02:05:04.041402+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDDNTKDNVFZNYNS6","created_at":"2026-06-02T02:05:04.041402+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDDNTKDN","created_at":"2026-06-02T02:05:04.041402+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/HDDNTKDNVFZNYNS6I6SWWZ3FRD","json":"https://pith.science/pith/HDDNTKDNVFZNYNS6I6SWWZ3FRD.json","graph_json":"https://pith.science/api/pith-number/HDDNTKDNVFZNYNS6I6SWWZ3FRD/graph.json","events_json":"https://pith.science/api/pith-number/HDDNTKDNVFZNYNS6I6SWWZ3FRD/events.json","paper":"https://pith.science/paper/HDDNTKDN"},"agent_actions":{"view_html":"https://pith.science/pith/HDDNTKDNVFZNYNS6I6SWWZ3FRD","download_json":"https://pith.science/pith/HDDNTKDNVFZNYNS6I6SWWZ3FRD.json","view_paper":"https://pith.science/paper/HDDNTKDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02031&json=true","fetch_graph":"https://pith.science/api/pith-number/HDDNTKDNVFZNYNS6I6SWWZ3FRD/graph.json","fetch_events":"https://pith.science/api/pith-number/HDDNTKDNVFZNYNS6I6SWWZ3FRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDDNTKDNVFZNYNS6I6SWWZ3FRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDDNTKDNVFZNYNS6I6SWWZ3FRD/action/storage_attestation","attest_author":"https://pith.science/pith/HDDNTKDNVFZNYNS6I6SWWZ3FRD/action/author_attestation","sign_citation":"https://pith.science/pith/HDDNTKDNVFZNYNS6I6SWWZ3FRD/action/citation_signature","submit_replication":"https://pith.science/pith/HDDNTKDNVFZNYNS6I6SWWZ3FRD/action/replication_record"}},"created_at":"2026-06-02T02:05:04.041402+00:00","updated_at":"2026-06-02T02:05:04.041402+00:00"}