{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3TDWXRW7EBR53VQ5OGXPITXY33","short_pith_number":"pith:3TDWXRW7","schema_version":"1.0","canonical_sha256":"dcc76bc6df2063ddd61d71aef44ef8def86430a867a15216c0191d4fd7091f9b","source":{"kind":"arxiv","id":"2608.08621","version":1},"attestation_state":"computed","paper":{"title":"Business Arena: Benchmarking LLM Agents in a Realistic Marketplace","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guannan Zhang, Hongwei Xue, Junbo Li, Kunyu Shi, Sicong Xie, Xiaoying Xing, Yijun Pan, Yukun Lian","submitted_at":"2026-08-09T10:08:21Z","abstract_excerpt":"Running a business is a challenging form of intelligent work. Operators must infer opportunities from partial signals, commit capital under uncertainty, adapt to delayed outcomes in a changing market, and satisfy regulatory obligations before trading legally. Frontier LLM agents can increasingly complete complex workflows, yet business-related capabilities are rarely evaluated in existing agent benchmarks. We introduce \\textbf{Business Arena}, a controlled environment where an AI agent runs a cross-border shop, buying from suppliers and selling to buyers over a long horizon. We ground the aren"},"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":"2608.08621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T10:08:21Z","cross_cats_sorted":[],"title_canon_sha256":"e0d87822122ea1f65b16ae72698eee2b9e217039b14a0fb6396d947b9891a6ee","abstract_canon_sha256":"a5d3fb0e1e381764ad295b7e595132bdf3c1e31e85e76aa09bd839dda7467917"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:23:11.448587Z","signature_b64":"PBcxS4OtrKOA4qeJoVfiI8uY3XnsVbYR/sJE7vwO7ZRAQnFv2jgBcVSqu/zDNXyHcxUNdxRID+3D4hb5wAsGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcc76bc6df2063ddd61d71aef44ef8def86430a867a15216c0191d4fd7091f9b","last_reissued_at":"2026-08-11T01:23:11.446153Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:23:11.446153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Business Arena: Benchmarking LLM Agents in a Realistic Marketplace","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guannan Zhang, Hongwei Xue, Junbo Li, Kunyu Shi, Sicong Xie, Xiaoying Xing, Yijun Pan, Yukun Lian","submitted_at":"2026-08-09T10:08:21Z","abstract_excerpt":"Running a business is a challenging form of intelligent work. Operators must infer opportunities from partial signals, commit capital under uncertainty, adapt to delayed outcomes in a changing market, and satisfy regulatory obligations before trading legally. Frontier LLM agents can increasingly complete complex workflows, yet business-related capabilities are rarely evaluated in existing agent benchmarks. We introduce \\textbf{Business Arena}, a controlled environment where an AI agent runs a cross-border shop, buying from suppliers and selling to buyers over a long horizon. We ground the aren"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08621","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/2608.08621/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":"2608.08621","created_at":"2026-08-11T01:23:11.446966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08621v1","created_at":"2026-08-11T01:23:11.446966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08621","created_at":"2026-08-11T01:23:11.446966+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TDWXRW7EBR5","created_at":"2026-08-11T01:23:11.446966+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TDWXRW7EBR53VQ5","created_at":"2026-08-11T01:23:11.446966+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TDWXRW7","created_at":"2026-08-11T01:23:11.446966+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/3TDWXRW7EBR53VQ5OGXPITXY33","json":"https://pith.science/pith/3TDWXRW7EBR53VQ5OGXPITXY33.json","graph_json":"https://pith.science/api/pith-number/3TDWXRW7EBR53VQ5OGXPITXY33/graph.json","events_json":"https://pith.science/api/pith-number/3TDWXRW7EBR53VQ5OGXPITXY33/events.json","paper":"https://pith.science/paper/3TDWXRW7"},"agent_actions":{"view_html":"https://pith.science/pith/3TDWXRW7EBR53VQ5OGXPITXY33","download_json":"https://pith.science/pith/3TDWXRW7EBR53VQ5OGXPITXY33.json","view_paper":"https://pith.science/paper/3TDWXRW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08621&json=true","fetch_graph":"https://pith.science/api/pith-number/3TDWXRW7EBR53VQ5OGXPITXY33/graph.json","fetch_events":"https://pith.science/api/pith-number/3TDWXRW7EBR53VQ5OGXPITXY33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TDWXRW7EBR53VQ5OGXPITXY33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TDWXRW7EBR53VQ5OGXPITXY33/action/storage_attestation","attest_author":"https://pith.science/pith/3TDWXRW7EBR53VQ5OGXPITXY33/action/author_attestation","sign_citation":"https://pith.science/pith/3TDWXRW7EBR53VQ5OGXPITXY33/action/citation_signature","submit_replication":"https://pith.science/pith/3TDWXRW7EBR53VQ5OGXPITXY33/action/replication_record"}},"created_at":"2026-08-11T01:23:11.446966+00:00","updated_at":"2026-08-11T01:23:11.446966+00:00"}