{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T4TVG6JBWNBCSV7ALQHNDNB67U","short_pith_number":"pith:T4TVG6JB","schema_version":"1.0","canonical_sha256":"9f27537921b3422957e05c0ed1b43efd1b81a236710b06828d33ebdaccbd3340","source":{"kind":"arxiv","id":"2408.10902","version":3},"attestation_state":"computed","paper":{"title":"Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alon Lavie, Isabel Trancoso, John Mendon\\c{c}a","submitted_at":"2024-08-20T14:45:23Z","abstract_excerpt":"Although human evaluation remains the gold standard for open-domain dialogue evaluation, the growing popularity of automated evaluation using Large Language Models (LLMs) has also extended to dialogue. However, most frameworks leverage benchmarks that assess older chatbots on aspects such as fluency and relevance, which are not reflective of the challenges associated with contemporary models. In fact, a qualitative analysis on Soda, a GPT-3.5 generated dialogue dataset, suggests that current chatbots may exhibit several recurring issues related to coherence and commonsense knowledge, but gener"},"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":"2408.10902","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T14:45:23Z","cross_cats_sorted":[],"title_canon_sha256":"ba7f84c4d38e77d622ccdf052e2ff181751721f1d56fe2b655475c211a96c89b","abstract_canon_sha256":"f2e9fdf6fc575cda235a29b38b9642da1db5f4215888ad2917196cec9da8ce6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:59.129350Z","signature_b64":"NapllqOOxMY1h4zaOcKWQKGqFIYoG/PMkAmrvb7nZl2l2mGYN79wRo4+lzgTe21fdJl87A4XEhltmr4h+RllDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f27537921b3422957e05c0ed1b43efd1b81a236710b06828d33ebdaccbd3340","last_reissued_at":"2026-07-05T09:15:59.128830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:59.128830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alon Lavie, Isabel Trancoso, John Mendon\\c{c}a","submitted_at":"2024-08-20T14:45:23Z","abstract_excerpt":"Although human evaluation remains the gold standard for open-domain dialogue evaluation, the growing popularity of automated evaluation using Large Language Models (LLMs) has also extended to dialogue. However, most frameworks leverage benchmarks that assess older chatbots on aspects such as fluency and relevance, which are not reflective of the challenges associated with contemporary models. In fact, a qualitative analysis on Soda, a GPT-3.5 generated dialogue dataset, suggests that current chatbots may exhibit several recurring issues related to coherence and commonsense knowledge, but gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10902","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/2408.10902/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":"2408.10902","created_at":"2026-07-05T09:15:59.128891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10902v3","created_at":"2026-07-05T09:15:59.128891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10902","created_at":"2026-07-05T09:15:59.128891+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4TVG6JBWNBC","created_at":"2026-07-05T09:15:59.128891+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4TVG6JBWNBCSV7A","created_at":"2026-07-05T09:15:59.128891+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4TVG6JB","created_at":"2026-07-05T09:15:59.128891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":162,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U","json":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U.json","graph_json":"https://pith.science/api/pith-number/T4TVG6JBWNBCSV7ALQHNDNB67U/graph.json","events_json":"https://pith.science/api/pith-number/T4TVG6JBWNBCSV7ALQHNDNB67U/events.json","paper":"https://pith.science/paper/T4TVG6JB"},"agent_actions":{"view_html":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U","download_json":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U.json","view_paper":"https://pith.science/paper/T4TVG6JB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10902&json=true","fetch_graph":"https://pith.science/api/pith-number/T4TVG6JBWNBCSV7ALQHNDNB67U/graph.json","fetch_events":"https://pith.science/api/pith-number/T4TVG6JBWNBCSV7ALQHNDNB67U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/action/storage_attestation","attest_author":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/action/author_attestation","sign_citation":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/action/citation_signature","submit_replication":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/action/replication_record"}},"created_at":"2026-07-05T09:15:59.128891+00:00","updated_at":"2026-07-05T09:15:59.128891+00:00"}