{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QQHROJGIH5MZ6KHSLRVZWLWHVA","short_pith_number":"pith:QQHROJGI","canonical_record":{"source":{"id":"2411.02337","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"539d87cfb0bcd8350aae34f5c33d8880a6d8efbbeaca92cd76c67d9019f133a8","abstract_canon_sha256":"672dd39bb3610e12acdd6294efbeb33f1eca6ed763d78e47a5eb0e222789ded3"},"schema_version":"1.0"},"canonical_sha256":"840f1724c83f599f28f25c6b9b2ec7a8123675ca24a32fbfb9eef22068af1664","source":{"kind":"arxiv","id":"2411.02337","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02337","created_at":"2026-07-05T10:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02337v3","created_at":"2026-07-05T10:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02337","created_at":"2026-07-05T10:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"QQHROJGIH5MZ","created_at":"2026-07-05T10:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"QQHROJGIH5MZ6KHS","created_at":"2026-07-05T10:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"QQHROJGI","created_at":"2026-07-05T10:05:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QQHROJGIH5MZ6KHSLRVZWLWHVA","target":"record","payload":{"canonical_record":{"source":{"id":"2411.02337","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"539d87cfb0bcd8350aae34f5c33d8880a6d8efbbeaca92cd76c67d9019f133a8","abstract_canon_sha256":"672dd39bb3610e12acdd6294efbeb33f1eca6ed763d78e47a5eb0e222789ded3"},"schema_version":"1.0"},"canonical_sha256":"840f1724c83f599f28f25c6b9b2ec7a8123675ca24a32fbfb9eef22068af1664","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:46.457917Z","signature_b64":"tHT8UUPTgMvaWYlUXSD8Ul4a1osXJUZ9c9wQTE2JHBEnnLKKC2lK/RC+lheJOP5uFiz2YwEPUkrWguJHpzgpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"840f1724c83f599f28f25c6b9b2ec7a8123675ca24a32fbfb9eef22068af1664","last_reissued_at":"2026-07-05T10:05:46.457412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:46.457412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.02337","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o40idXwMy/h8LZ4UndMm3JL8Hgt+HC0Qi6sRaH4ELLeS/GhwFUtlK4uEzRcDgtpikhgrVJ4R1GdxggD3wv4wAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:40:27.921577Z"},"content_sha256":"a7f7e8c079c2f901b2d0f9a0ac73e85adecb1178918c4ff04bfabb5173c8f5c8","schema_version":"1.0","event_id":"sha256:a7f7e8c079c2f901b2d0f9a0ac73e85adecb1178918c4ff04bfabb5173c8f5c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QQHROJGIH5MZ6KHSLRVZWLWHVA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanyu Lai, Iat Long Iong, Jiadai Sun, Jie Tang, Shuntian Yao, Tianjie Zhang, Wei Xu, Wenyi Zhao, Xiao Liu, Xinyue Yang, Xueqiao Sun, Yuxiao Dong, Yu Yang, Zehan Qi","submitted_at":"2024-11-04T17:59:58Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable potential as autonomous agents, particularly in web-based tasks. However, existing LLM web agents heavily rely on expensive proprietary LLM APIs, while open LLMs lack the necessary decision-making capabilities. This paper introduces WebRL, a self-evolving online curriculum reinforcement learning framework designed to train high-performance web agents using open LLMs. WebRL addresses three key challenges in building LLM web agents, including the scarcity of training tasks, sparse feedback signals, and policy distribution drift in online learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02337","kind":"arxiv","version":3},"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/2411.02337/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lX9hUK8MHqh8BvCVHfmXJ63Xy9/n/WrjKZqhDui3xph08kvtX3z5iazFHd79zDXcpdzpVLAzlRiEipFqxaOvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:40:27.922159Z"},"content_sha256":"963e774d29b60b5e9c62d37c389e6ea64721036ca572524953de2fc1af58dcf5","schema_version":"1.0","event_id":"sha256:963e774d29b60b5e9c62d37c389e6ea64721036ca572524953de2fc1af58dcf5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQHROJGIH5MZ6KHSLRVZWLWHVA/bundle.json","state_url":"https://pith.science/pith/QQHROJGIH5MZ6KHSLRVZWLWHVA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQHROJGIH5MZ6KHSLRVZWLWHVA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-31T17:40:27Z","links":{"resolver":"https://pith.science/pith/QQHROJGIH5MZ6KHSLRVZWLWHVA","bundle":"https://pith.science/pith/QQHROJGIH5MZ6KHSLRVZWLWHVA/bundle.json","state":"https://pith.science/pith/QQHROJGIH5MZ6KHSLRVZWLWHVA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQHROJGIH5MZ6KHSLRVZWLWHVA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QQHROJGIH5MZ6KHSLRVZWLWHVA","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":"672dd39bb3610e12acdd6294efbeb33f1eca6ed763d78e47a5eb0e222789ded3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T17:59:58Z","title_canon_sha256":"539d87cfb0bcd8350aae34f5c33d8880a6d8efbbeaca92cd76c67d9019f133a8"},"schema_version":"1.0","source":{"id":"2411.02337","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02337","created_at":"2026-07-05T10:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02337v3","created_at":"2026-07-05T10:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02337","created_at":"2026-07-05T10:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"QQHROJGIH5MZ","created_at":"2026-07-05T10:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"QQHROJGIH5MZ6KHS","created_at":"2026-07-05T10:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"QQHROJGI","created_at":"2026-07-05T10:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:963e774d29b60b5e9c62d37c389e6ea64721036ca572524953de2fc1af58dcf5","target":"graph","created_at":"2026-07-05T10:05:46Z","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/2411.02337/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown remarkable potential as autonomous agents, particularly in web-based tasks. However, existing LLM web agents heavily rely on expensive proprietary LLM APIs, while open LLMs lack the necessary decision-making capabilities. This paper introduces WebRL, a self-evolving online curriculum reinforcement learning framework designed to train high-performance web agents using open LLMs. WebRL addresses three key challenges in building LLM web agents, including the scarcity of training tasks, sparse feedback signals, and policy distribution drift in online learnin","authors_text":"Hanyu Lai, Iat Long Iong, Jiadai Sun, Jie Tang, Shuntian Yao, Tianjie Zhang, Wei Xu, Wenyi Zhao, Xiao Liu, Xinyue Yang, Xueqiao Sun, Yuxiao Dong, Yu Yang, Zehan Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T17:59:58Z","title":"WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02337","kind":"arxiv","version":3},"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:a7f7e8c079c2f901b2d0f9a0ac73e85adecb1178918c4ff04bfabb5173c8f5c8","target":"record","created_at":"2026-07-05T10:05:46Z","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":"672dd39bb3610e12acdd6294efbeb33f1eca6ed763d78e47a5eb0e222789ded3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T17:59:58Z","title_canon_sha256":"539d87cfb0bcd8350aae34f5c33d8880a6d8efbbeaca92cd76c67d9019f133a8"},"schema_version":"1.0","source":{"id":"2411.02337","kind":"arxiv","version":3}},"canonical_sha256":"840f1724c83f599f28f25c6b9b2ec7a8123675ca24a32fbfb9eef22068af1664","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"840f1724c83f599f28f25c6b9b2ec7a8123675ca24a32fbfb9eef22068af1664","first_computed_at":"2026-07-05T10:05:46.457412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:46.457412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tHT8UUPTgMvaWYlUXSD8Ul4a1osXJUZ9c9wQTE2JHBEnnLKKC2lK/RC+lheJOP5uFiz2YwEPUkrWguJHpzgpBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:46.457917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02337","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7f7e8c079c2f901b2d0f9a0ac73e85adecb1178918c4ff04bfabb5173c8f5c8","sha256:963e774d29b60b5e9c62d37c389e6ea64721036ca572524953de2fc1af58dcf5"],"state_sha256":"8b09157ba2e565abeeb08ee2f2b7e367e3c08fcfeba3c297447d9c89a2ea3fb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HuIjzx7rTTrfm6cEtYeL/IIVuTiVTRcR1azol208GuTrlxinxKm+WSjhSMF61iIjGaaDISxoLyoydujXfhJjBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T17:40:27.926663Z","bundle_sha256":"54f4504ce8e8d34112e2d8c071d7427ebd942caf2d79cf5b43736e2d056e64f7"}}