{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QKVGUKIKKKKOJPZKDRNZGUCD5W","short_pith_number":"pith:QKVGUKIK","schema_version":"1.0","canonical_sha256":"82aa6a290a5294e4bf2a1c5b935043eda9804c821a58668f8d118d831871d14d","source":{"kind":"arxiv","id":"2407.00132","version":3},"attestation_state":"computed","paper":{"title":"ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Desong Meng, Dongqi Cai, Haiyang Shen, Li Zhang, Mengwei Xu, Sheng Qi, Yue Li, Yun Ma","submitted_at":"2024-06-28T08:45:02Z","abstract_excerpt":"Recent advancements in integrating large language models (LLMs) with application programming interfaces (APIs) have gained significant interest in both academia and industry. Recent work demonstrates that these API-based agents exhibit relatively strong autonomy and planning capabilities. However, their ability to handle multi-dimensional difficulty levels, diverse task types, and real-world demands remains unknown. In this paper, we introduce \\textsc{ShortcutsBench}, a large-scale benchmark for the comprehensive evaluation of API-based agents in solving real-world complex tasks. \\textsc{Short"},"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":"2407.00132","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-28T08:45:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b4917f4cd27921bbf67499dd8c34b680f0a83149aafa45f1535b15556af7689","abstract_canon_sha256":"7029a77dc052811609ae5d2435d612b280181461e34ab221484e5401f58c7db3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:14.252843Z","signature_b64":"wzlkg/llLjHf7GHvvco8v4+o1Pl3n9kLOY4M+xM6EtWdZ3Esj2O3EDlLSLFX3jPbe6ylx57Z3WhwuTL2lIIEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82aa6a290a5294e4bf2a1c5b935043eda9804c821a58668f8d118d831871d14d","last_reissued_at":"2026-07-05T10:04:14.252430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:14.252430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Desong Meng, Dongqi Cai, Haiyang Shen, Li Zhang, Mengwei Xu, Sheng Qi, Yue Li, Yun Ma","submitted_at":"2024-06-28T08:45:02Z","abstract_excerpt":"Recent advancements in integrating large language models (LLMs) with application programming interfaces (APIs) have gained significant interest in both academia and industry. Recent work demonstrates that these API-based agents exhibit relatively strong autonomy and planning capabilities. However, their ability to handle multi-dimensional difficulty levels, diverse task types, and real-world demands remains unknown. In this paper, we introduce \\textsc{ShortcutsBench}, a large-scale benchmark for the comprehensive evaluation of API-based agents in solving real-world complex tasks. \\textsc{Short"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00132","kind":"arxiv","version":3},"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/2407.00132/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":"2407.00132","created_at":"2026-07-05T10:04:14.252485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00132v3","created_at":"2026-07-05T10:04:14.252485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00132","created_at":"2026-07-05T10:04:14.252485+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKVGUKIKKKKO","created_at":"2026-07-05T10:04:14.252485+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKVGUKIKKKKOJPZK","created_at":"2026-07-05T10:04:14.252485+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKVGUKIK","created_at":"2026-07-05T10:04:14.252485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19667","citing_title":"Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13934","citing_title":"Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20148","citing_title":"Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKVGUKIKKKKOJPZKDRNZGUCD5W","json":"https://pith.science/pith/QKVGUKIKKKKOJPZKDRNZGUCD5W.json","graph_json":"https://pith.science/api/pith-number/QKVGUKIKKKKOJPZKDRNZGUCD5W/graph.json","events_json":"https://pith.science/api/pith-number/QKVGUKIKKKKOJPZKDRNZGUCD5W/events.json","paper":"https://pith.science/paper/QKVGUKIK"},"agent_actions":{"view_html":"https://pith.science/pith/QKVGUKIKKKKOJPZKDRNZGUCD5W","download_json":"https://pith.science/pith/QKVGUKIKKKKOJPZKDRNZGUCD5W.json","view_paper":"https://pith.science/paper/QKVGUKIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00132&json=true","fetch_graph":"https://pith.science/api/pith-number/QKVGUKIKKKKOJPZKDRNZGUCD5W/graph.json","fetch_events":"https://pith.science/api/pith-number/QKVGUKIKKKKOJPZKDRNZGUCD5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKVGUKIKKKKOJPZKDRNZGUCD5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKVGUKIKKKKOJPZKDRNZGUCD5W/action/storage_attestation","attest_author":"https://pith.science/pith/QKVGUKIKKKKOJPZKDRNZGUCD5W/action/author_attestation","sign_citation":"https://pith.science/pith/QKVGUKIKKKKOJPZKDRNZGUCD5W/action/citation_signature","submit_replication":"https://pith.science/pith/QKVGUKIKKKKOJPZKDRNZGUCD5W/action/replication_record"}},"created_at":"2026-07-05T10:04:14.252485+00:00","updated_at":"2026-07-05T10:04:14.252485+00:00"}