{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2JJKI5UQGMKXPVPXS5K573WHRC","short_pith_number":"pith:2JJKI5UQ","canonical_record":{"source":{"id":"2504.21776","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T16:25:25Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"d518db51547776410cc9728128f4fd47506bcf25e3bad8c45c165fe41daa4a18","abstract_canon_sha256":"e99d68991c3e046a23e457994dc6f977a81a18aab14292ab79ad9980dc1b958f"},"schema_version":"1.0"},"canonical_sha256":"d252a47690331577d5f79755dfeec78889b87740c75130c472c25ff2b5a61c87","source":{"kind":"arxiv","id":"2504.21776","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21776","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21776v2","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21776","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"2JJKI5UQGMKX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2JJKI5UQGMKXPVPX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2JJKI5UQ","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2JJKI5UQGMKXPVPXS5K573WHRC","target":"record","payload":{"canonical_record":{"source":{"id":"2504.21776","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T16:25:25Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"d518db51547776410cc9728128f4fd47506bcf25e3bad8c45c165fe41daa4a18","abstract_canon_sha256":"e99d68991c3e046a23e457994dc6f977a81a18aab14292ab79ad9980dc1b958f"},"schema_version":"1.0"},"canonical_sha256":"d252a47690331577d5f79755dfeec78889b87740c75130c472c25ff2b5a61c87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.874411Z","signature_b64":"8zsvoBnKdS7mJ3FJmaxVBc5X2nT1yoorLy5NNWuTaeNIPglWkZQbfB0sQ3mA24sSU+kNJRaqT0CD3CTqpcFuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d252a47690331577d5f79755dfeec78889b87740c75130c472c25ff2b5a61c87","last_reissued_at":"2026-05-17T23:38:46.873797Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.873797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.21776","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AUHotdXyiixGDHSd6RJ8NEfQg80geqZIXmskWG/eM8dKMbSWYmVM9DayZX1O9rXnxIMTg1S3MMK3Yq2t8ahgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:57:01.250048Z"},"content_sha256":"ec0c363f955fd147b72638a17145bc3e8352f6027c5ea0677b4878bbf3a8969a","schema_version":"1.0","event_id":"sha256:ec0c363f955fd147b72638a17145bc3e8352f6027c5ea0677b4878bbf3a8969a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2JJKI5UQGMKXPVPXS5K573WHRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"WebThinker lets large reasoning models search the web and draft reports autonomously during reasoning.","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Guanting Dong, Hongjin Qian, Jiajie Jin, Ji-Rong Wen, Xiaoxi Li, Yongkang Wu, Yutao Zhu, Zhicheng Dou","submitted_at":"2025-04-30T16:25:25Z","abstract_excerpt":"Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities. However, their reliance on static internal knowledge limits their performance on complex, knowledge-intensive tasks and hinders their ability to produce comprehensive research reports requiring synthesis of diverse web information. To address this, we propose WebThinker, a deep research agent that empowers LRMs to autonomously search the web, navigate among web pages, and draft reports during the reasoning process. WebThinker integrates a Deep Web Explorer module, enabl"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments on complex reasoning benchmarks (GPQA, GAIA, WebWalkerQA, HLE) and scientific report generation tasks (Glaive) demonstrate that WebThinker significantly outperforms existing methods and strong proprietary systems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Deep Web Explorer module can reliably locate, navigate, and extract accurate information from arbitrary web pages without introducing navigation errors or factual hallucinations that propagate into the final report.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"WebThinker equips large reasoning models with autonomous web exploration and interleaved reasoning-drafting via a Deep Web Explorer and RL-based DPO training, yielding gains on GPQA, GAIA, and report-generation benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"WebThinker lets large reasoning models search the web and draft reports autonomously during reasoning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3db15b16a255aa86d7c1b8f203a47221f75bfb09cac96dc1478706c5bea109bd"},"source":{"id":"2504.21776","kind":"arxiv","version":2},"verdict":{"id":"bbacda62-c9bb-4c50-932c-6f78389003ec","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T19:09:52.921915Z","strongest_claim":"Extensive experiments on complex reasoning benchmarks (GPQA, GAIA, WebWalkerQA, HLE) and scientific report generation tasks (Glaive) demonstrate that WebThinker significantly outperforms existing methods and strong proprietary systems.","one_line_summary":"WebThinker equips large reasoning models with autonomous web exploration and interleaved reasoning-drafting via a Deep Web Explorer and RL-based DPO training, yielding gains on GPQA, GAIA, and report-generation benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Deep Web Explorer module can reliably locate, navigate, and extract accurate information from arbitrary web pages without introducing navigation errors or factual hallucinations that propagate into the final report.","pith_extraction_headline":"WebThinker lets large reasoning models search the web and draft reports autonomously during reasoning."},"references":{"count":91,"sample":[{"doi":"","year":2024,"title":"Self-rag: Learn- ing to retrieve, generate, and critique through self-reflection","work_id":"195a1a15-2803-42f1-bf5b-3ad204d104dc","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","work_id":"cc9775d9-2fbd-4690-a641-2b50ae4a59dc","ref_index":2,"cited_arxiv_id":"2503.19470","is_internal_anchor":true},{"doi":"","year":2025,"title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","work_id":"0b361fed-cf2a-4b90-b61a-de88de4b8840","ref_index":3,"cited_arxiv_id":"2503.09567","is_internal_anchor":true},{"doi":"","year":2025,"title":"An empirical study on eliciting and improving r1-like reasoning models","work_id":"5d962724-fdfd-471c-b457-0c9fd4d5aa44","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Self-play with execution feedback: Improving instruction-following capabilities of large language models","work_id":"c7b45c2c-cd3d-468a-9501-0e7877cd44f8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":91,"snapshot_sha256":"a461ebf681d1385ac3cba82c9c48b3191ad9face0c8748fc0eba458329c0bc6c","internal_anchors":23},"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":"bbacda62-c9bb-4c50-932c-6f78389003ec"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pBy0MXfkjtSK+2nSxrctPVqzjzX+6HCpG97hglGcWZtNZqmRA8kwgtNO3yvLcH/lvovFELYuiCFiPrDHwFlxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:57:01.251111Z"},"content_sha256":"ffbb236fd847182ea6f95df3c1e0b947ae602baa101d16f33feb36f92ac86277","schema_version":"1.0","event_id":"sha256:ffbb236fd847182ea6f95df3c1e0b947ae602baa101d16f33feb36f92ac86277"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2JJKI5UQGMKXPVPXS5K573WHRC/bundle.json","state_url":"https://pith.science/pith/2JJKI5UQGMKXPVPXS5K573WHRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2JJKI5UQGMKXPVPXS5K573WHRC/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":"2026-05-27T19:57:01Z","links":{"resolver":"https://pith.science/pith/2JJKI5UQGMKXPVPXS5K573WHRC","bundle":"https://pith.science/pith/2JJKI5UQGMKXPVPXS5K573WHRC/bundle.json","state":"https://pith.science/pith/2JJKI5UQGMKXPVPXS5K573WHRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2JJKI5UQGMKXPVPXS5K573WHRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2JJKI5UQGMKXPVPXS5K573WHRC","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":"e99d68991c3e046a23e457994dc6f977a81a18aab14292ab79ad9980dc1b958f","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T16:25:25Z","title_canon_sha256":"d518db51547776410cc9728128f4fd47506bcf25e3bad8c45c165fe41daa4a18"},"schema_version":"1.0","source":{"id":"2504.21776","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21776","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21776v2","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21776","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"2JJKI5UQGMKX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2JJKI5UQGMKXPVPX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2JJKI5UQ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ffbb236fd847182ea6f95df3c1e0b947ae602baa101d16f33feb36f92ac86277","target":"graph","created_at":"2026-05-17T23:38:46Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Extensive experiments on complex reasoning benchmarks (GPQA, GAIA, WebWalkerQA, HLE) and scientific report generation tasks (Glaive) demonstrate that WebThinker significantly outperforms existing methods and strong proprietary systems."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the Deep Web Explorer module can reliably locate, navigate, and extract accurate information from arbitrary web pages without introducing navigation errors or factual hallucinations that propagate into the final report."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"WebThinker equips large reasoning models with autonomous web exploration and interleaved reasoning-drafting via a Deep Web Explorer and RL-based DPO training, yielding gains on GPQA, GAIA, and report-generation benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"WebThinker lets large reasoning models search the web and draft reports autonomously during reasoning."}],"snapshot_sha256":"3db15b16a255aa86d7c1b8f203a47221f75bfb09cac96dc1478706c5bea109bd"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities. However, their reliance on static internal knowledge limits their performance on complex, knowledge-intensive tasks and hinders their ability to produce comprehensive research reports requiring synthesis of diverse web information. To address this, we propose WebThinker, a deep research agent that empowers LRMs to autonomously search the web, navigate among web pages, and draft reports during the reasoning process. WebThinker integrates a Deep Web Explorer module, enabl","authors_text":"Guanting Dong, Hongjin Qian, Jiajie Jin, Ji-Rong Wen, Xiaoxi Li, Yongkang Wu, Yutao Zhu, Zhicheng Dou","cross_cats":["cs.AI","cs.IR"],"headline":"WebThinker lets large reasoning models search the web and draft reports autonomously during reasoning.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T16:25:25Z","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability"},"references":{"count":91,"internal_anchors":23,"resolved_work":91,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Self-rag: Learn- ing to retrieve, generate, and critique through self-reflection","work_id":"195a1a15-2803-42f1-bf5b-3ad204d104dc","year":2024},{"cited_arxiv_id":"2503.19470","doi":"","is_internal_anchor":true,"ref_index":2,"title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","work_id":"cc9775d9-2fbd-4690-a641-2b50ae4a59dc","year":2025},{"cited_arxiv_id":"2503.09567","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","work_id":"0b361fed-cf2a-4b90-b61a-de88de4b8840","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"An empirical study on eliciting and improving r1-like reasoning models","work_id":"5d962724-fdfd-471c-b457-0c9fd4d5aa44","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Self-play with execution feedback: Improving instruction-following capabilities of large language models","work_id":"c7b45c2c-cd3d-468a-9501-0e7877cd44f8","year":2025}],"snapshot_sha256":"a461ebf681d1385ac3cba82c9c48b3191ad9face0c8748fc0eba458329c0bc6c"},"source":{"id":"2504.21776","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T19:09:52.921915Z","id":"bbacda62-c9bb-4c50-932c-6f78389003ec","model_set":{"reader":"grok-4.3"},"one_line_summary":"WebThinker equips large reasoning models with autonomous web exploration and interleaved reasoning-drafting via a Deep Web Explorer and RL-based DPO training, yielding gains on GPQA, GAIA, and report-generation benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"WebThinker lets large reasoning models search the web and draft reports autonomously during reasoning.","strongest_claim":"Extensive experiments on complex reasoning benchmarks (GPQA, GAIA, WebWalkerQA, HLE) and scientific report generation tasks (Glaive) demonstrate that WebThinker significantly outperforms existing methods and strong proprietary systems.","weakest_assumption":"That the Deep Web Explorer module can reliably locate, navigate, and extract accurate information from arbitrary web pages without introducing navigation errors or factual hallucinations that propagate into the final report."}},"verdict_id":"bbacda62-c9bb-4c50-932c-6f78389003ec"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ec0c363f955fd147b72638a17145bc3e8352f6027c5ea0677b4878bbf3a8969a","target":"record","created_at":"2026-05-17T23:38:46Z","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":"e99d68991c3e046a23e457994dc6f977a81a18aab14292ab79ad9980dc1b958f","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T16:25:25Z","title_canon_sha256":"d518db51547776410cc9728128f4fd47506bcf25e3bad8c45c165fe41daa4a18"},"schema_version":"1.0","source":{"id":"2504.21776","kind":"arxiv","version":2}},"canonical_sha256":"d252a47690331577d5f79755dfeec78889b87740c75130c472c25ff2b5a61c87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d252a47690331577d5f79755dfeec78889b87740c75130c472c25ff2b5a61c87","first_computed_at":"2026-05-17T23:38:46.873797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.873797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8zsvoBnKdS7mJ3FJmaxVBc5X2nT1yoorLy5NNWuTaeNIPglWkZQbfB0sQ3mA24sSU+kNJRaqT0CD3CTqpcFuAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.874411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.21776","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec0c363f955fd147b72638a17145bc3e8352f6027c5ea0677b4878bbf3a8969a","sha256:ffbb236fd847182ea6f95df3c1e0b947ae602baa101d16f33feb36f92ac86277"],"state_sha256":"1afdb24c414fecd3cf339832d42de90c98da780c27e0b9c11b46783f19f1b476"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FRa/Li0rSom8y8RJMRugtPQZAUwWyopOw03hIC5Y/8CMfQq0eo5AAtc+x3xuligrRuIQ2j53wYFtG/V/dlFYCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T19:57:01.258154Z","bundle_sha256":"2bf03f093a6f6d121e7aa797f48a40120234cac0407247f4ea8636b7e6340e2f"}}