{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QT5DR5OKMEMICKLWONIDV2HB7P","short_pith_number":"pith:QT5DR5OK","schema_version":"1.0","canonical_sha256":"84fa38f5ca611881297673503ae8e1fbeb1490be7eeb26564807e3bb181e1fc3","source":{"kind":"arxiv","id":"2605.29218","version":1},"attestation_state":"computed","paper":{"title":"GTA: Generating Long-Horizon Tasks for Web Agents at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chien-Sheng Wu, Jonathan May, Kung-Hsiang Huang, Muhao Chen, Prafulla Kumar Choubey, Tenghao Huang, Yilun Zhou","submitted_at":"2026-05-28T01:05:50Z","abstract_excerpt":"Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely manually constructed, providing only coarse start-goal annotations without intermediate trajectories, while recent automatic generation efforts remain expensive, biased, and shallow. These limitations prevent reliable training and evaluation of agents that must generalize to realistic, multi-hop, cross-page tasks. We introduce a scalable framework, GTA, that"},"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":"2605.29218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T01:05:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fca32e49c2c4d85e0b5cc195b24618bd24e85c84f65538a39a9af69b15e0e1ad","abstract_canon_sha256":"16cc078697a1e728e2f2495acf96b1f279926877b13a59e3b24133eaef1efa1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:25.158377Z","signature_b64":"30pcnZjlLCOsd7ipdt8EaaDvN4Er8AlCBmvjXpVyEiBO3TVesEoUrCsVYZ3/VmDtJJU7pU2Whe5qiOFKy7maDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84fa38f5ca611881297673503ae8e1fbeb1490be7eeb26564807e3bb181e1fc3","last_reissued_at":"2026-05-29T01:05:25.157504Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:25.157504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GTA: Generating Long-Horizon Tasks for Web Agents at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chien-Sheng Wu, Jonathan May, Kung-Hsiang Huang, Muhao Chen, Prafulla Kumar Choubey, Tenghao Huang, Yilun Zhou","submitted_at":"2026-05-28T01:05:50Z","abstract_excerpt":"Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely manually constructed, providing only coarse start-goal annotations without intermediate trajectories, while recent automatic generation efforts remain expensive, biased, and shallow. These limitations prevent reliable training and evaluation of agents that must generalize to realistic, multi-hop, cross-page tasks. We introduce a scalable framework, GTA, that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29218","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/2605.29218/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":"2605.29218","created_at":"2026-05-29T01:05:25.157655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29218v1","created_at":"2026-05-29T01:05:25.157655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29218","created_at":"2026-05-29T01:05:25.157655+00:00"},{"alias_kind":"pith_short_12","alias_value":"QT5DR5OKMEMI","created_at":"2026-05-29T01:05:25.157655+00:00"},{"alias_kind":"pith_short_16","alias_value":"QT5DR5OKMEMICKLW","created_at":"2026-05-29T01:05:25.157655+00:00"},{"alias_kind":"pith_short_8","alias_value":"QT5DR5OK","created_at":"2026-05-29T01:05:25.157655+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/QT5DR5OKMEMICKLWONIDV2HB7P","json":"https://pith.science/pith/QT5DR5OKMEMICKLWONIDV2HB7P.json","graph_json":"https://pith.science/api/pith-number/QT5DR5OKMEMICKLWONIDV2HB7P/graph.json","events_json":"https://pith.science/api/pith-number/QT5DR5OKMEMICKLWONIDV2HB7P/events.json","paper":"https://pith.science/paper/QT5DR5OK"},"agent_actions":{"view_html":"https://pith.science/pith/QT5DR5OKMEMICKLWONIDV2HB7P","download_json":"https://pith.science/pith/QT5DR5OKMEMICKLWONIDV2HB7P.json","view_paper":"https://pith.science/paper/QT5DR5OK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29218&json=true","fetch_graph":"https://pith.science/api/pith-number/QT5DR5OKMEMICKLWONIDV2HB7P/graph.json","fetch_events":"https://pith.science/api/pith-number/QT5DR5OKMEMICKLWONIDV2HB7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QT5DR5OKMEMICKLWONIDV2HB7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QT5DR5OKMEMICKLWONIDV2HB7P/action/storage_attestation","attest_author":"https://pith.science/pith/QT5DR5OKMEMICKLWONIDV2HB7P/action/author_attestation","sign_citation":"https://pith.science/pith/QT5DR5OKMEMICKLWONIDV2HB7P/action/citation_signature","submit_replication":"https://pith.science/pith/QT5DR5OKMEMICKLWONIDV2HB7P/action/replication_record"}},"created_at":"2026-05-29T01:05:25.157655+00:00","updated_at":"2026-05-29T01:05:25.157655+00:00"}