{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P5AYO6MYFPATQRTUFMVTKPB5DD","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":"2c65c530feb59510a4f6937796862b75deef82ffd240260d7a253b7f0a0b172e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T09:10:48Z","title_canon_sha256":"fa8c9de2075e5fed45f95e4251aa9794861fe9677be388a5ad06214618ccddc1"},"schema_version":"1.0","source":{"id":"2606.17698","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17698","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17698v1","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17698","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"pith_short_12","alias_value":"P5AYO6MYFPAT","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"pith_short_16","alias_value":"P5AYO6MYFPATQRTU","created_at":"2026-06-19T16:10:19Z"},{"alias_kind":"pith_short_8","alias_value":"P5AYO6MY","created_at":"2026-06-19T16:10:19Z"}],"graph_snapshots":[{"event_id":"sha256:0238b5b6fc52b32e0420ef425ebbfef5fc627a8a7abaf285612735638b5083e4","target":"graph","created_at":"2026-06-19T16:10:19Z","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/2606.17698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As LLM-based shopping agents enter production, existing benchmarks fail to capture how a shopper's requirements arrive: stated implicitly in the query, recorded in a profile, or revealed only when the right question is asked. Benchmarks that expose full intent upfront and grade only the final choice can neither pose this long-horizon challenge nor explain which requirement an agent missed. To address this gap, we introduce EComAgentBench, a benchmark of 662 tasks grounded in real Amazon products and reviews. Each task scatters these requirements across a visible query, a tool-gated profile, an","authors_text":"Haibo Zhang, Tong Li, Zeyao Du","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T09:10:48Z","title":"EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17698","kind":"arxiv","version":1},"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":"sha256:4b3b2fa890a94b5c9011b9b81ab6e85529391d7e694e9baf395fac80806290bf","target":"record","created_at":"2026-06-19T16:10:19Z","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":"2c65c530feb59510a4f6937796862b75deef82ffd240260d7a253b7f0a0b172e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T09:10:48Z","title_canon_sha256":"fa8c9de2075e5fed45f95e4251aa9794861fe9677be388a5ad06214618ccddc1"},"schema_version":"1.0","source":{"id":"2606.17698","kind":"arxiv","version":1}},"canonical_sha256":"7f418779982bc13846742b2b353c3d18e0af7ca06b21d3a3d34e01f8032ce086","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f418779982bc13846742b2b353c3d18e0af7ca06b21d3a3d34e01f8032ce086","first_computed_at":"2026-06-19T16:10:19.585634Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:19.585634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RpIpv8N5gnqBDhOgi/p6sNSYLLAxP828aG6gYWSubi9Gb1nSFP4B8K1dM7/9s3QMY3NhJ/iSVPg3v8LJRmFmCg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:19.585990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17698","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b3b2fa890a94b5c9011b9b81ab6e85529391d7e694e9baf395fac80806290bf","sha256:0238b5b6fc52b32e0420ef425ebbfef5fc627a8a7abaf285612735638b5083e4"],"state_sha256":"fd0f0e9cb15eb4a0020ddaa9d930c225db597a218b819969f345aab5d1b13159"}