{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TKQSIMKBKAVB54ROPBFYZKCNAC","short_pith_number":"pith:TKQSIMKB","schema_version":"1.0","canonical_sha256":"9aa1243141502a1ef22e784b8ca84d0094033980ac58db52cf5af6786759c610","source":{"kind":"arxiv","id":"2207.01206","version":4},"attestation_state":"computed","paper":{"title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Howard Chen, John Yang, Karthik Narasimhan, Shunyu Yao","submitted_at":"2022-07-04T05:30:22Z","abstract_excerpt":"Existing benchmarks for grounding language in interactive environments either lack real-world linguistic elements, or prove difficult to scale up due to substantial human involvement in the collection of data or feedback signals. To bridge this gap, we develop WebShop -- a simulated e-commerce website environment with $1.18$ million real-world products and $12,087$ crowd-sourced text instructions. Given a text instruction specifying a product requirement, an agent needs to navigate multiple types of webpages and issue diverse actions to find, customize, and purchase an item. WebShop provides s"},"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":"2207.01206","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-04T05:30:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a5a735f223f0dcf6ddb1915ba8c2c95b0347b163c6f4e908e3f5649302720845","abstract_canon_sha256":"31a4f2a604add86bfb7b1bf2f5011bbac58a071e412c7d9f1264c89c1893f2f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:52.071897Z","signature_b64":"yavMtV1kI+4+oHmhwZdijfbgQ0vst3R3WUrRIXVq770hmrro235MF/XO30s3UDYVMhr66YfAikXcLCwCYw5oDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9aa1243141502a1ef22e784b8ca84d0094033980ac58db52cf5af6786759c610","last_reissued_at":"2026-07-05T05:39:52.071480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:52.071480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Howard Chen, John Yang, Karthik Narasimhan, Shunyu Yao","submitted_at":"2022-07-04T05:30:22Z","abstract_excerpt":"Existing benchmarks for grounding language in interactive environments either lack real-world linguistic elements, or prove difficult to scale up due to substantial human involvement in the collection of data or feedback signals. To bridge this gap, we develop WebShop -- a simulated e-commerce website environment with $1.18$ million real-world products and $12,087$ crowd-sourced text instructions. Given a text instruction specifying a product requirement, an agent needs to navigate multiple types of webpages and issue diverse actions to find, customize, and purchase an item. WebShop provides s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01206","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/2207.01206/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":"2207.01206","created_at":"2026-07-05T05:39:52.071536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01206v4","created_at":"2026-07-05T05:39:52.071536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01206","created_at":"2026-07-05T05:39:52.071536+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKQSIMKBKAVB","created_at":"2026-07-05T05:39:52.071536+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKQSIMKBKAVB54RO","created_at":"2026-07-05T05:39:52.071536+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKQSIMKB","created_at":"2026-07-05T05:39:52.071536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26918","citing_title":"Diagnosing Task Insensitivity in Language Agents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23049","citing_title":"PhoneBuddy: Training Open Models for Agentic Phone Use","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18671","citing_title":"HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19409","citing_title":"OpenRath: Session-Centered Runtime State for Agent Systems","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20724","citing_title":"When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06223","citing_title":"From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03371","citing_title":"See, Infer, Intervene: Proactive World Modeling for Goal-Oriented Social Intelligence","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01311","citing_title":"SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31308","citing_title":"TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31073","citing_title":"MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14786","citing_title":"Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24756","citing_title":"Proper Scoring Rules for Agentic Uncertainty Quantification","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25160","citing_title":"ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20724","citing_title":"When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29537","citing_title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26329","citing_title":"JobBench: Aligning Agent Work With Human Will","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26807","citing_title":"HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18141","citing_title":"A Brief Overview: On-Policy Self-Distillation In Large Language Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18805","citing_title":"RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19099","citing_title":"DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18141","citing_title":"A Brief Overview: On-Policy Self-Distillation In Large Language Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09033","citing_title":"ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09572","citing_title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09033","citing_title":"ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14558","citing_title":"Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKQSIMKBKAVB54ROPBFYZKCNAC","json":"https://pith.science/pith/TKQSIMKBKAVB54ROPBFYZKCNAC.json","graph_json":"https://pith.science/api/pith-number/TKQSIMKBKAVB54ROPBFYZKCNAC/graph.json","events_json":"https://pith.science/api/pith-number/TKQSIMKBKAVB54ROPBFYZKCNAC/events.json","paper":"https://pith.science/paper/TKQSIMKB"},"agent_actions":{"view_html":"https://pith.science/pith/TKQSIMKBKAVB54ROPBFYZKCNAC","download_json":"https://pith.science/pith/TKQSIMKBKAVB54ROPBFYZKCNAC.json","view_paper":"https://pith.science/paper/TKQSIMKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01206&json=true","fetch_graph":"https://pith.science/api/pith-number/TKQSIMKBKAVB54ROPBFYZKCNAC/graph.json","fetch_events":"https://pith.science/api/pith-number/TKQSIMKBKAVB54ROPBFYZKCNAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKQSIMKBKAVB54ROPBFYZKCNAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKQSIMKBKAVB54ROPBFYZKCNAC/action/storage_attestation","attest_author":"https://pith.science/pith/TKQSIMKBKAVB54ROPBFYZKCNAC/action/author_attestation","sign_citation":"https://pith.science/pith/TKQSIMKBKAVB54ROPBFYZKCNAC/action/citation_signature","submit_replication":"https://pith.science/pith/TKQSIMKBKAVB54ROPBFYZKCNAC/action/replication_record"}},"created_at":"2026-07-05T05:39:52.071536+00:00","updated_at":"2026-07-05T05:39:52.071536+00:00"}