{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RZSJLPYWP5ORANHY6BFQSNPULY","short_pith_number":"pith:RZSJLPYW","schema_version":"1.0","canonical_sha256":"8e6495bf167f5d1034f8f04b0935f45e2bbf1b89fb3f1747d08b9f21c76cf87e","source":{"kind":"arxiv","id":"2502.11357","version":4},"attestation_state":"computed","paper":{"title":"Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Ahmed Awadallah, Arindam Mitra, Boyu Gou, Corby Rosset, Spencer Whitehead, Vardaan Pahuja, Yadong Lu, Yu Su","submitted_at":"2025-02-17T02:13:48Z","abstract_excerpt":"Recent success in large multimodal models (LMMs) has sparked promising applications of agents capable of autonomously completing complex web tasks. While open-source LMM agents have made significant advances in offline evaluation benchmarks, their performance still falls substantially short of human-level capabilities in more realistic online settings. A key bottleneck is the lack of diverse and large-scale trajectory-level datasets across various domains, which are expensive to collect. In this paper, we address this challenge by developing a scalable recipe to synthesize the largest and most"},"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":"2502.11357","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T02:13:48Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"a453889a670af51da37314e6f0bef3831b0c37ff56a654db228c1b8bb0d33894","abstract_canon_sha256":"91020f190b2f7617bf72c441216ab7ea0bdf658ce209f2ba937ab0a121446370"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:26.823706Z","signature_b64":"34L2jucJ77LvGm2uBcTNYV3J90/6LeAvcGSC6NC9KcOd3SlLg7M4nZtGSaVhry1dVtLzwBKiwqzEBUPSB8mQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e6495bf167f5d1034f8f04b0935f45e2bbf1b89fb3f1747d08b9f21c76cf87e","last_reissued_at":"2026-07-05T11:12:26.823181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:26.823181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Ahmed Awadallah, Arindam Mitra, Boyu Gou, Corby Rosset, Spencer Whitehead, Vardaan Pahuja, Yadong Lu, Yu Su","submitted_at":"2025-02-17T02:13:48Z","abstract_excerpt":"Recent success in large multimodal models (LMMs) has sparked promising applications of agents capable of autonomously completing complex web tasks. While open-source LMM agents have made significant advances in offline evaluation benchmarks, their performance still falls substantially short of human-level capabilities in more realistic online settings. A key bottleneck is the lack of diverse and large-scale trajectory-level datasets across various domains, which are expensive to collect. In this paper, we address this challenge by developing a scalable recipe to synthesize the largest and most"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11357","kind":"arxiv","version":4},"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/2502.11357/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":"2502.11357","created_at":"2026-07-05T11:12:26.823250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11357v4","created_at":"2026-07-05T11:12:26.823250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11357","created_at":"2026-07-05T11:12:26.823250+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZSJLPYWP5OR","created_at":"2026-07-05T11:12:26.823250+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZSJLPYWP5ORANHY","created_at":"2026-07-05T11:12:26.823250+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZSJLPYW","created_at":"2026-07-05T11:12:26.823250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21654","citing_title":"ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17321","citing_title":"ProCUA-SFT Technical Report","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27483","citing_title":"Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26807","citing_title":"HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22149","citing_title":"DynaWeb: Model-Based Reinforcement Learning of Web Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09718","citing_title":"Agentic Compilation: Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":126,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZSJLPYWP5ORANHY6BFQSNPULY","json":"https://pith.science/pith/RZSJLPYWP5ORANHY6BFQSNPULY.json","graph_json":"https://pith.science/api/pith-number/RZSJLPYWP5ORANHY6BFQSNPULY/graph.json","events_json":"https://pith.science/api/pith-number/RZSJLPYWP5ORANHY6BFQSNPULY/events.json","paper":"https://pith.science/paper/RZSJLPYW"},"agent_actions":{"view_html":"https://pith.science/pith/RZSJLPYWP5ORANHY6BFQSNPULY","download_json":"https://pith.science/pith/RZSJLPYWP5ORANHY6BFQSNPULY.json","view_paper":"https://pith.science/paper/RZSJLPYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11357&json=true","fetch_graph":"https://pith.science/api/pith-number/RZSJLPYWP5ORANHY6BFQSNPULY/graph.json","fetch_events":"https://pith.science/api/pith-number/RZSJLPYWP5ORANHY6BFQSNPULY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZSJLPYWP5ORANHY6BFQSNPULY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZSJLPYWP5ORANHY6BFQSNPULY/action/storage_attestation","attest_author":"https://pith.science/pith/RZSJLPYWP5ORANHY6BFQSNPULY/action/author_attestation","sign_citation":"https://pith.science/pith/RZSJLPYWP5ORANHY6BFQSNPULY/action/citation_signature","submit_replication":"https://pith.science/pith/RZSJLPYWP5ORANHY6BFQSNPULY/action/replication_record"}},"created_at":"2026-07-05T11:12:26.823250+00:00","updated_at":"2026-07-05T11:12:26.823250+00:00"}