{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:37WHJ2U4XUSJCSG5ZDCOMXI7IJ","short_pith_number":"pith:37WHJ2U4","schema_version":"1.0","canonical_sha256":"dfec74ea9cbd249148ddc8c4e65d1f42504bffb65a1c3e30209f789551206387","source":{"kind":"arxiv","id":"2606.26122","version":1},"attestation_state":"computed","paper":{"title":"DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiamian Wang, Jing Shi, Rajiv Jain, Ruiyi Zhang, Samyadeep Basu, Tong Sun, Tong Yu, Zhiqiang Tao","submitted_at":"2026-05-27T21:21:42Z","abstract_excerpt":"Recent methods train search agents via reinforcement learning from (question, answer, evidence) tuples without requiring expert trajectories. The tuples serve as the training environment, and whose properties directly shape what search strategies and generalization abilities the agent can develop. While prior works have made encouraging progress in improving training data quality, existing environments remain predominantly text-based and existing approaches can struggle to construct training environments that are controllable, scalable, and account for multimodal data. Given this, we propose D"},"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":"2606.26122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T21:21:42Z","cross_cats_sorted":[],"title_canon_sha256":"7a8e89b2ee9978982683e858b944a33f1042696e6e0051587de1e4c43b5c4d81","abstract_canon_sha256":"cda782bbd729213b3fcb622946cb609f8a464a7f2ca08400bd594d3b88494354"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:26.808240Z","signature_b64":"4aeVKgrdD1OFA5GatitX6ui04qliOHehnFmfVzVeZTC3/vMUt8UPn5AIx53cKGAkQiOFb8N1X7tfdv1xDS7XDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfec74ea9cbd249148ddc8c4e65d1f42504bffb65a1c3e30209f789551206387","last_reissued_at":"2026-06-26T00:15:26.807836Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:26.807836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiamian Wang, Jing Shi, Rajiv Jain, Ruiyi Zhang, Samyadeep Basu, Tong Sun, Tong Yu, Zhiqiang Tao","submitted_at":"2026-05-27T21:21:42Z","abstract_excerpt":"Recent methods train search agents via reinforcement learning from (question, answer, evidence) tuples without requiring expert trajectories. The tuples serve as the training environment, and whose properties directly shape what search strategies and generalization abilities the agent can develop. While prior works have made encouraging progress in improving training data quality, existing environments remain predominantly text-based and existing approaches can struggle to construct training environments that are controllable, scalable, and account for multimodal data. Given this, we propose D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26122","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/2606.26122/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":"2606.26122","created_at":"2026-06-26T00:15:26.807898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26122v1","created_at":"2026-06-26T00:15:26.807898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26122","created_at":"2026-06-26T00:15:26.807898+00:00"},{"alias_kind":"pith_short_12","alias_value":"37WHJ2U4XUSJ","created_at":"2026-06-26T00:15:26.807898+00:00"},{"alias_kind":"pith_short_16","alias_value":"37WHJ2U4XUSJCSG5","created_at":"2026-06-26T00:15:26.807898+00:00"},{"alias_kind":"pith_short_8","alias_value":"37WHJ2U4","created_at":"2026-06-26T00:15:26.807898+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/37WHJ2U4XUSJCSG5ZDCOMXI7IJ","json":"https://pith.science/pith/37WHJ2U4XUSJCSG5ZDCOMXI7IJ.json","graph_json":"https://pith.science/api/pith-number/37WHJ2U4XUSJCSG5ZDCOMXI7IJ/graph.json","events_json":"https://pith.science/api/pith-number/37WHJ2U4XUSJCSG5ZDCOMXI7IJ/events.json","paper":"https://pith.science/paper/37WHJ2U4"},"agent_actions":{"view_html":"https://pith.science/pith/37WHJ2U4XUSJCSG5ZDCOMXI7IJ","download_json":"https://pith.science/pith/37WHJ2U4XUSJCSG5ZDCOMXI7IJ.json","view_paper":"https://pith.science/paper/37WHJ2U4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26122&json=true","fetch_graph":"https://pith.science/api/pith-number/37WHJ2U4XUSJCSG5ZDCOMXI7IJ/graph.json","fetch_events":"https://pith.science/api/pith-number/37WHJ2U4XUSJCSG5ZDCOMXI7IJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37WHJ2U4XUSJCSG5ZDCOMXI7IJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37WHJ2U4XUSJCSG5ZDCOMXI7IJ/action/storage_attestation","attest_author":"https://pith.science/pith/37WHJ2U4XUSJCSG5ZDCOMXI7IJ/action/author_attestation","sign_citation":"https://pith.science/pith/37WHJ2U4XUSJCSG5ZDCOMXI7IJ/action/citation_signature","submit_replication":"https://pith.science/pith/37WHJ2U4XUSJCSG5ZDCOMXI7IJ/action/replication_record"}},"created_at":"2026-06-26T00:15:26.807898+00:00","updated_at":"2026-06-26T00:15:26.807898+00:00"}