{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JCM3USLE25W5MKJSRPVBWHHDX5","short_pith_number":"pith:JCM3USLE","schema_version":"1.0","canonical_sha256":"4899ba4964d76dd629328bea1b1ce3bf4408e7e4ba49b8fcd8619de8258dc615","source":{"kind":"arxiv","id":"2407.17770","version":1},"attestation_state":"computed","paper":{"title":"BotEval: Facilitating Interactive Human Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hyundong Cho, Jonathan May, Thamme Gowda, Tianli Tong, Yuyang Huang, Zixun Lu","submitted_at":"2024-07-25T04:57:31Z","abstract_excerpt":"Following the rapid progress in natural language processing (NLP) models, language models are applied to increasingly more complex interactive tasks such as negotiations and conversation moderations. Having human evaluators directly interact with these NLP models is essential for adequately evaluating the performance on such interactive tasks. We develop BotEval, an easily customizable, open-source, evaluation toolkit that focuses on enabling human-bot interactions as part of the evaluation process, as opposed to human evaluators making judgements for a static input. BotEval balances flexibili"},"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":"2407.17770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T04:57:31Z","cross_cats_sorted":[],"title_canon_sha256":"63250734574aa32aa1a9f4d86ea58c4f148bf43c36e14b0a1575b2c238fe3458","abstract_canon_sha256":"f277b45603862f7e784cea0ec4ba5f733aafdd18f72fc51ad4ac8766bbefea7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:21.232905Z","signature_b64":"TRe7g2Q5fubhIsdqeWMXZwdHRD728CV0RJNAEHwVKElZO3IqlUnbv62LLjgBjblOPGi3H1RA6sjRfEukpSr7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4899ba4964d76dd629328bea1b1ce3bf4408e7e4ba49b8fcd8619de8258dc615","last_reissued_at":"2026-07-05T08:48:21.232563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:21.232563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BotEval: Facilitating Interactive Human Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hyundong Cho, Jonathan May, Thamme Gowda, Tianli Tong, Yuyang Huang, Zixun Lu","submitted_at":"2024-07-25T04:57:31Z","abstract_excerpt":"Following the rapid progress in natural language processing (NLP) models, language models are applied to increasingly more complex interactive tasks such as negotiations and conversation moderations. Having human evaluators directly interact with these NLP models is essential for adequately evaluating the performance on such interactive tasks. We develop BotEval, an easily customizable, open-source, evaluation toolkit that focuses on enabling human-bot interactions as part of the evaluation process, as opposed to human evaluators making judgements for a static input. BotEval balances flexibili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17770","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/2407.17770/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":"2407.17770","created_at":"2026-07-05T08:48:21.232619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17770v1","created_at":"2026-07-05T08:48:21.232619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17770","created_at":"2026-07-05T08:48:21.232619+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCM3USLE25W5","created_at":"2026-07-05T08:48:21.232619+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCM3USLE25W5MKJS","created_at":"2026-07-05T08:48:21.232619+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCM3USLE","created_at":"2026-07-05T08:48:21.232619+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/JCM3USLE25W5MKJSRPVBWHHDX5","json":"https://pith.science/pith/JCM3USLE25W5MKJSRPVBWHHDX5.json","graph_json":"https://pith.science/api/pith-number/JCM3USLE25W5MKJSRPVBWHHDX5/graph.json","events_json":"https://pith.science/api/pith-number/JCM3USLE25W5MKJSRPVBWHHDX5/events.json","paper":"https://pith.science/paper/JCM3USLE"},"agent_actions":{"view_html":"https://pith.science/pith/JCM3USLE25W5MKJSRPVBWHHDX5","download_json":"https://pith.science/pith/JCM3USLE25W5MKJSRPVBWHHDX5.json","view_paper":"https://pith.science/paper/JCM3USLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17770&json=true","fetch_graph":"https://pith.science/api/pith-number/JCM3USLE25W5MKJSRPVBWHHDX5/graph.json","fetch_events":"https://pith.science/api/pith-number/JCM3USLE25W5MKJSRPVBWHHDX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCM3USLE25W5MKJSRPVBWHHDX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCM3USLE25W5MKJSRPVBWHHDX5/action/storage_attestation","attest_author":"https://pith.science/pith/JCM3USLE25W5MKJSRPVBWHHDX5/action/author_attestation","sign_citation":"https://pith.science/pith/JCM3USLE25W5MKJSRPVBWHHDX5/action/citation_signature","submit_replication":"https://pith.science/pith/JCM3USLE25W5MKJSRPVBWHHDX5/action/replication_record"}},"created_at":"2026-07-05T08:48:21.232619+00:00","updated_at":"2026-07-05T08:48:21.232619+00:00"}