{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZOEJI4PQUG65J6S45GHKIUXMRH","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":"8e6cd225d5ddd417d26bc43ce751a200b9f84a375e69b4bcde9a77159a130929","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T17:50:47Z","title_canon_sha256":"e29d49011949fe90d5e0036a243e43d53b4e4eb2d3f2f0211f6cc7f87cf30c1b"},"schema_version":"1.0","source":{"id":"2311.18751","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18751","created_at":"2026-07-05T09:55:32Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18751v3","created_at":"2026-07-05T09:55:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18751","created_at":"2026-07-05T09:55:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZOEJI4PQUG65","created_at":"2026-07-05T09:55:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZOEJI4PQUG65J6S4","created_at":"2026-07-05T09:55:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZOEJI4PQ","created_at":"2026-07-05T09:55:32Z"}],"graph_snapshots":[{"event_id":"sha256:6df2477ead3bfb44c5cfd02102dec5901e090a1a935ccef2ddc9818a66c64d78","target":"graph","created_at":"2026-07-05T09:55:32Z","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/2311.18751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model agents (LMA) recently emerged as a promising paradigm on muti-step decision making tasks, often outperforming humans and other reinforcement learning agents. Despite the promise, their performance on real-world applications that often involve combinations of tasks is still underexplored. In this work, we introduce a new benchmark, called CompWoB -- 50 new compositional web automation tasks reflecting more realistic assumptions. We show that while existing prompted LMAs (gpt-3.5-turbo or gpt-4) achieve 94.0% average success rate on base tasks, their performance degrades to 24.9% ","authors_text":"Aleksandra Faust, Hiroki Furuta, Izzeddin Gur, Yutaka Matsuo","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T17:50:47Z","title":"Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18751","kind":"arxiv","version":3},"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:be533ac768575b6a8ea322d764e5f1a1453b270d8b51956c5c091c63bc9c0af6","target":"record","created_at":"2026-07-05T09:55:32Z","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":"8e6cd225d5ddd417d26bc43ce751a200b9f84a375e69b4bcde9a77159a130929","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-30T17:50:47Z","title_canon_sha256":"e29d49011949fe90d5e0036a243e43d53b4e4eb2d3f2f0211f6cc7f87cf30c1b"},"schema_version":"1.0","source":{"id":"2311.18751","kind":"arxiv","version":3}},"canonical_sha256":"cb889471f0a1bdd4fa5ce98ea452ec89e186f163c9eae223f8cf565375b64c8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb889471f0a1bdd4fa5ce98ea452ec89e186f163c9eae223f8cf565375b64c8b","first_computed_at":"2026-07-05T09:55:32.127615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:32.127615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7JoRzwRFDxpRN4CDmsJ7U/A37PTymPiYnkLEB+XZ0Am1X6SAeFGFUxYNygy06Hj7MMLdw0+a9dwCsvLvYZYABA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:32.128108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.18751","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be533ac768575b6a8ea322d764e5f1a1453b270d8b51956c5c091c63bc9c0af6","sha256:6df2477ead3bfb44c5cfd02102dec5901e090a1a935ccef2ddc9818a66c64d78"],"state_sha256":"8f451caf4f79dc6ba244b82d9f1f8fb957f3b98dbc34ab6315e8cea1f94cff1e"}