{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2JSAFHMER6MYA2G6CLMQVGV2ZS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"76795125bff0e4fb789d0120ea0e3e04a82440efb3b953f7bf3f508a5278fc1e","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-15T17:59:47Z","title_canon_sha256":"e4b8bb84a4574cf07f92daf692af5cdd92defb88cadb61d9f93664fd752871e0"},"schema_version":"1.0","source":{"id":"2602.14257","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.14257","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"2602.14257v2","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14257","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"2JSAFHMER6MY","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_16","alias_value":"2JSAFHMER6MYA2G6","created_at":"2026-06-23T03:13:54Z"},{"alias_kind":"pith_short_8","alias_value":"2JSAFHME","created_at":"2026-06-23T03:13:54Z"}],"graph_snapshots":[{"event_id":"sha256:033c93ac6692d1bc1aa103b327e60626245583b2d306734edfc93d06dab05a1a","target":"graph","created_at":"2026-06-23T03:13:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.14257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jie Jiang, Lan Xu, Lingxiang Hu, Ming Xu, Siying Wang, Tianle Xia, Wei Xu, Wenwei Li, Yiding Sun","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-15T17:59:47Z","title":"AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14257","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dc52be143739102ea38df9673ba9bbf8c86f0214ed7abf49c4377f5d0b88352a","target":"record","created_at":"2026-06-23T03:13:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"76795125bff0e4fb789d0120ea0e3e04a82440efb3b953f7bf3f508a5278fc1e","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-15T17:59:47Z","title_canon_sha256":"e4b8bb84a4574cf07f92daf692af5cdd92defb88cadb61d9f93664fd752871e0"},"schema_version":"1.0","source":{"id":"2602.14257","kind":"arxiv","version":2}},"canonical_sha256":"d264029d848f998068de12d90a9abaccb437c9e4e1e53e278d8c3142f79d0390","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d264029d848f998068de12d90a9abaccb437c9e4e1e53e278d8c3142f79d0390","first_computed_at":"2026-06-23T03:13:54.455952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:54.455952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6avjNIX0QY27379vbs5V0Jq8/EYX1VDcgRkfgyDqgLg/YPUsMcnx54ntB40/ExBZdJVRUGS8IL8eZNJ3uESdAQ==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:54.456445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.14257","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc52be143739102ea38df9673ba9bbf8c86f0214ed7abf49c4377f5d0b88352a","sha256:033c93ac6692d1bc1aa103b327e60626245583b2d306734edfc93d06dab05a1a"],"state_sha256":"ede90e0f8b6bf1117c8cd3c4d7c6d371f28dc8041549e110cdc8531b84b98c02"}