{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2JSAFHMER6MYA2G6CLMQVGV2ZS","short_pith_number":"pith:2JSAFHME","schema_version":"1.0","canonical_sha256":"d264029d848f998068de12d90a9abaccb437c9e4e1e53e278d8c3142f79d0390","source":{"kind":"arxiv","id":"2602.14257","version":2},"attestation_state":"computed","paper":{"title":"AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jie Jiang, Lan Xu, Lingxiang Hu, Ming Xu, Siying Wang, Tianle Xia, Wei Xu, Wenwei Li, Yiding Sun","submitted_at":"2026-02-15T17:59:47Z","abstract_excerpt":"While Large Language Model (LLM) agents have made remarkable progress on complex reasoning, evaluating them in real-world environments remains an open problem. Existing benchmarks are largely confined to idealized simulations and fail to capture specialized domains such as advertising and marketing analytics, where tasks require multi-round interaction with professional tools and where ground-truth answers quickly become obsolete as data and platform rules evolve. To address this, we propose AD-Bench, a benchmark built from real user marketing-analysis requests on a production advertising plat"},"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":"2602.14257","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-15T17:59:47Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"e4b8bb84a4574cf07f92daf692af5cdd92defb88cadb61d9f93664fd752871e0","abstract_canon_sha256":"76795125bff0e4fb789d0120ea0e3e04a82440efb3b953f7bf3f508a5278fc1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:54.456445Z","signature_b64":"6avjNIX0QY27379vbs5V0Jq8/EYX1VDcgRkfgyDqgLg/YPUsMcnx54ntB40/ExBZdJVRUGS8IL8eZNJ3uESdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d264029d848f998068de12d90a9abaccb437c9e4e1e53e278d8c3142f79d0390","last_reissued_at":"2026-06-23T03:13:54.455952Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:54.455952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jie Jiang, Lan Xu, Lingxiang Hu, Ming Xu, Siying Wang, Tianle Xia, Wei Xu, Wenwei Li, Yiding Sun","submitted_at":"2026-02-15T17:59:47Z","abstract_excerpt":"While Large Language Model (LLM) agents have made remarkable progress on complex reasoning, evaluating them in real-world environments remains an open problem. Existing benchmarks are largely confined to idealized simulations and fail to capture specialized domains such as advertising and marketing analytics, where tasks require multi-round interaction with professional tools and where ground-truth answers quickly become obsolete as data and platform rules evolve. To address this, we propose AD-Bench, a benchmark built from real user marketing-analysis requests on a production advertising plat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14257","kind":"arxiv","version":2},"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/2602.14257/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":"2602.14257","created_at":"2026-06-23T03:13:54.456012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.14257v2","created_at":"2026-06-23T03:13:54.456012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14257","created_at":"2026-06-23T03:13:54.456012+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JSAFHMER6MY","created_at":"2026-06-23T03:13:54.456012+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JSAFHMER6MYA2G6","created_at":"2026-06-23T03:13:54.456012+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JSAFHME","created_at":"2026-06-23T03:13:54.456012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.09918","citing_title":"NaiAD: Initiate Data-Driven Research for LLM Advertising","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17870","citing_title":"GraSP: Graph-Structured Skill Compositions for LLM Agents","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JSAFHMER6MYA2G6CLMQVGV2ZS","json":"https://pith.science/pith/2JSAFHMER6MYA2G6CLMQVGV2ZS.json","graph_json":"https://pith.science/api/pith-number/2JSAFHMER6MYA2G6CLMQVGV2ZS/graph.json","events_json":"https://pith.science/api/pith-number/2JSAFHMER6MYA2G6CLMQVGV2ZS/events.json","paper":"https://pith.science/paper/2JSAFHME"},"agent_actions":{"view_html":"https://pith.science/pith/2JSAFHMER6MYA2G6CLMQVGV2ZS","download_json":"https://pith.science/pith/2JSAFHMER6MYA2G6CLMQVGV2ZS.json","view_paper":"https://pith.science/paper/2JSAFHME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.14257&json=true","fetch_graph":"https://pith.science/api/pith-number/2JSAFHMER6MYA2G6CLMQVGV2ZS/graph.json","fetch_events":"https://pith.science/api/pith-number/2JSAFHMER6MYA2G6CLMQVGV2ZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JSAFHMER6MYA2G6CLMQVGV2ZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JSAFHMER6MYA2G6CLMQVGV2ZS/action/storage_attestation","attest_author":"https://pith.science/pith/2JSAFHMER6MYA2G6CLMQVGV2ZS/action/author_attestation","sign_citation":"https://pith.science/pith/2JSAFHMER6MYA2G6CLMQVGV2ZS/action/citation_signature","submit_replication":"https://pith.science/pith/2JSAFHMER6MYA2G6CLMQVGV2ZS/action/replication_record"}},"created_at":"2026-06-23T03:13:54.456012+00:00","updated_at":"2026-06-23T03:13:54.456012+00:00"}