{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T4TVG6JBWNBCSV7ALQHNDNB67U","short_pith_number":"pith:T4TVG6JB","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"},"canonical_sha256":"9f27537921b3422957e05c0ed1b43efd1b81a236710b06828d33ebdaccbd3340","source":{"kind":"arxiv","id":"2408.10902","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10902","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10902v3","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10902","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"pith_short_12","alias_value":"T4TVG6JBWNBC","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"pith_short_16","alias_value":"T4TVG6JBWNBCSV7A","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"pith_short_8","alias_value":"T4TVG6JB","created_at":"2026-07-05T09:15:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T4TVG6JBWNBCSV7ALQHNDNB67U","target":"record","payload":{"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"},"canonical_sha256":"9f27537921b3422957e05c0ed1b43efd1b81a236710b06828d33ebdaccbd3340","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"},"source_kind":"arxiv","source_id":"2408.10902","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KRzuI3n5pUyYpjbTOdQSBct5M+DtgdCnAio98/IXwEb3vLex3eikQLFWVF73eJ44Hj6OUj/UGjyMocUKcEosDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:40:48.002069Z"},"content_sha256":"e1351e9425f146f656e84b206d7af47f4594a3c43df55cadd00bf18bd06b9197","schema_version":"1.0","event_id":"sha256:e1351e9425f146f656e84b206d7af47f4594a3c43df55cadd00bf18bd06b9197"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T4TVG6JBWNBCSV7ALQHNDNB67U","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ov6978kbqGMWY6d/vQ3IjhzqdH+Fb9henhulcQHRB4Wcxqkm8RhV1t1OkO5WHUG3wW+rtK7IIprPjrRhG3NACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:40:48.002515Z"},"content_sha256":"e92468f28000ad86bfe2607715bb465c9c8710dfbc4f1d94d949ae5093c23d38","schema_version":"1.0","event_id":"sha256:e92468f28000ad86bfe2607715bb465c9c8710dfbc4f1d94d949ae5093c23d38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/bundle.json","state_url":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T04:40:48Z","links":{"resolver":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U","bundle":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/bundle.json","state":"https://pith.science/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T4TVG6JBWNBCSV7ALQHNDNB67U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T4TVG6JBWNBCSV7ALQHNDNB67U","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":"f2e9fdf6fc575cda235a29b38b9642da1db5f4215888ad2917196cec9da8ce6c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T14:45:23Z","title_canon_sha256":"ba7f84c4d38e77d622ccdf052e2ff181751721f1d56fe2b655475c211a96c89b"},"schema_version":"1.0","source":{"id":"2408.10902","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10902","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10902v3","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10902","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"pith_short_12","alias_value":"T4TVG6JBWNBC","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"pith_short_16","alias_value":"T4TVG6JBWNBCSV7A","created_at":"2026-07-05T09:15:59Z"},{"alias_kind":"pith_short_8","alias_value":"T4TVG6JB","created_at":"2026-07-05T09:15:59Z"}],"graph_snapshots":[{"event_id":"sha256:e92468f28000ad86bfe2607715bb465c9c8710dfbc4f1d94d949ae5093c23d38","target":"graph","created_at":"2026-07-05T09:15:59Z","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/2408.10902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alon Lavie, Isabel Trancoso, John Mendon\\c{c}a","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T14:45:23Z","title":"Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10902","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:e1351e9425f146f656e84b206d7af47f4594a3c43df55cadd00bf18bd06b9197","target":"record","created_at":"2026-07-05T09:15:59Z","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":"f2e9fdf6fc575cda235a29b38b9642da1db5f4215888ad2917196cec9da8ce6c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T14:45:23Z","title_canon_sha256":"ba7f84c4d38e77d622ccdf052e2ff181751721f1d56fe2b655475c211a96c89b"},"schema_version":"1.0","source":{"id":"2408.10902","kind":"arxiv","version":3}},"canonical_sha256":"9f27537921b3422957e05c0ed1b43efd1b81a236710b06828d33ebdaccbd3340","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f27537921b3422957e05c0ed1b43efd1b81a236710b06828d33ebdaccbd3340","first_computed_at":"2026-07-05T09:15:59.128830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:59.128830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NapllqOOxMY1h4zaOcKWQKGqFIYoG/PMkAmrvb7nZl2l2mGYN79wRo4+lzgTe21fdJl87A4XEhltmr4h+RllDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:59.129350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10902","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1351e9425f146f656e84b206d7af47f4594a3c43df55cadd00bf18bd06b9197","sha256:e92468f28000ad86bfe2607715bb465c9c8710dfbc4f1d94d949ae5093c23d38"],"state_sha256":"be2b3b88b68b586a6503a1fa0e8d26aa0e9d747512358383ef78dc7ef9ca396f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mEJwM2+5GrNvTNl/qzeZ9EzUSV9Fi7JX4agocykkDba+DtO4IAZ9KryuuiziKJdn1ikPVlOfGiKbT18QWNUtCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:40:48.004774Z","bundle_sha256":"3360e4cd9c7d109140540445e0dd9ddb80a4f323a1eb810c08fd4efd1a0ddfdf"}}