{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2JV6ZVQ4APM6BEMP6VOO3XUGW2","short_pith_number":"pith:2JV6ZVQ4","schema_version":"1.0","canonical_sha256":"d26becd61c03d9e0918ff55cedde86b6b84af198fa5a3c90520b74a188567dc1","source":{"kind":"arxiv","id":"2105.01992","version":1},"attestation_state":"computed","paper":{"title":"LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Feifan Yan, Josh Arnold, Weiyan Shi, Yu Li, Zhou Yu","submitted_at":"2021-05-05T11:38:14Z","abstract_excerpt":"We present LEGOEval, an open-source toolkit that enables researchers to easily evaluate dialogue systems in a few lines of code using the online crowdsource platform, Amazon Mechanical Turk. Compared to existing toolkits, LEGOEval features a flexible task design by providing a Python API that maps to commonly used React.js interface components. Researchers can personalize their evaluation procedures easily with our built-in pages as if playing with LEGO blocks. Thus, LEGOEval provides a fast, consistent method for reproducing human evaluation results. Besides the flexible task design, LEGOEval"},"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":"2105.01992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-05-05T11:38:14Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"ab04abc6dc684173fafbcc6a2fc08b5b569d2d09b1bb503672d382642aad0b96","abstract_canon_sha256":"b035f01bf5cc0e42f917578e62b2ce295046441d3764b7ad4a79f3621dee2ff6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:51.347921Z","signature_b64":"VqHfowuBa2W0kOn1VZJe03jcwyEZi1uqPC50ki7gjbIBeuw5suhUBo3ySTwhMe+Yex5UHx6oUshwOawN0cjGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d26becd61c03d9e0918ff55cedde86b6b84af198fa5a3c90520b74a188567dc1","last_reissued_at":"2026-07-05T02:37:51.347429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:51.347429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Feifan Yan, Josh Arnold, Weiyan Shi, Yu Li, Zhou Yu","submitted_at":"2021-05-05T11:38:14Z","abstract_excerpt":"We present LEGOEval, an open-source toolkit that enables researchers to easily evaluate dialogue systems in a few lines of code using the online crowdsource platform, Amazon Mechanical Turk. Compared to existing toolkits, LEGOEval features a flexible task design by providing a Python API that maps to commonly used React.js interface components. Researchers can personalize their evaluation procedures easily with our built-in pages as if playing with LEGO blocks. Thus, LEGOEval provides a fast, consistent method for reproducing human evaluation results. Besides the flexible task design, LEGOEval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01992","kind":"arxiv","version":1},"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/2105.01992/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":"2105.01992","created_at":"2026-07-05T02:37:51.347503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.01992v1","created_at":"2026-07-05T02:37:51.347503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01992","created_at":"2026-07-05T02:37:51.347503+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JV6ZVQ4APM6","created_at":"2026-07-05T02:37:51.347503+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JV6ZVQ4APM6BEMP","created_at":"2026-07-05T02:37:51.347503+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JV6ZVQ4","created_at":"2026-07-05T02:37:51.347503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JV6ZVQ4APM6BEMP6VOO3XUGW2","json":"https://pith.science/pith/2JV6ZVQ4APM6BEMP6VOO3XUGW2.json","graph_json":"https://pith.science/api/pith-number/2JV6ZVQ4APM6BEMP6VOO3XUGW2/graph.json","events_json":"https://pith.science/api/pith-number/2JV6ZVQ4APM6BEMP6VOO3XUGW2/events.json","paper":"https://pith.science/paper/2JV6ZVQ4"},"agent_actions":{"view_html":"https://pith.science/pith/2JV6ZVQ4APM6BEMP6VOO3XUGW2","download_json":"https://pith.science/pith/2JV6ZVQ4APM6BEMP6VOO3XUGW2.json","view_paper":"https://pith.science/paper/2JV6ZVQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.01992&json=true","fetch_graph":"https://pith.science/api/pith-number/2JV6ZVQ4APM6BEMP6VOO3XUGW2/graph.json","fetch_events":"https://pith.science/api/pith-number/2JV6ZVQ4APM6BEMP6VOO3XUGW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JV6ZVQ4APM6BEMP6VOO3XUGW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JV6ZVQ4APM6BEMP6VOO3XUGW2/action/storage_attestation","attest_author":"https://pith.science/pith/2JV6ZVQ4APM6BEMP6VOO3XUGW2/action/author_attestation","sign_citation":"https://pith.science/pith/2JV6ZVQ4APM6BEMP6VOO3XUGW2/action/citation_signature","submit_replication":"https://pith.science/pith/2JV6ZVQ4APM6BEMP6VOO3XUGW2/action/replication_record"}},"created_at":"2026-07-05T02:37:51.347503+00:00","updated_at":"2026-07-05T02:37:51.347503+00:00"}