{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EMBJ4JYNGFNPKF6N3FFMBXXATS","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":"5bb74b5c53a2c171229b843175072213b3bf78e6fbf23517a81b9cbe42b2480e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T22:02:27Z","title_canon_sha256":"7df66264bbec951ee37a61e7f326e08e9272a4391e6b0d78b63697b7e3c66b55"},"schema_version":"1.0","source":{"id":"2301.12004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12004","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12004v1","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12004","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"pith_short_12","alias_value":"EMBJ4JYNGFNP","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"pith_short_16","alias_value":"EMBJ4JYNGFNPKF6N","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"pith_short_8","alias_value":"EMBJ4JYN","created_at":"2026-07-05T05:36:34Z"}],"graph_snapshots":[{"event_id":"sha256:514d51a3218f7446f766a7a08738e9d932e66925346a010ad9bd29e0e74ca7a3","target":"graph","created_at":"2026-07-05T05:36:34Z","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/2301.12004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models have steadily increased in size over the past few years. They achieve a high level of performance on various natural language processing (NLP) tasks such as question answering and summarization. Large language models (LLMs) have been used for generation and can now output human-like text. Due to this, there are other downstream tasks in the realm of dialog that can now harness the LLMs' language understanding capabilities. Dialog evaluation is one task that this paper will explore. It concentrates on prompting with LLMs: BLOOM, OPT, GPT-3, Flan-T5, InstructDial and TNLGv2. The ","authors_text":"Cathy Jiao, Jessica Huynh, Maxine Eskenazi, Payal Bajaj, Prakhar Gupta, Shikib Mehri, Vishrav Chaudhary","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T22:02:27Z","title":"Understanding the Effectiveness of Very Large Language Models on Dialog Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12004","kind":"arxiv","version":1},"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:ca70d8c9a31c6a4cbaa3b2938d73f9c06b3a6ed281b68f6ff87ac4d35da3ab04","target":"record","created_at":"2026-07-05T05:36:34Z","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":"5bb74b5c53a2c171229b843175072213b3bf78e6fbf23517a81b9cbe42b2480e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T22:02:27Z","title_canon_sha256":"7df66264bbec951ee37a61e7f326e08e9272a4391e6b0d78b63697b7e3c66b55"},"schema_version":"1.0","source":{"id":"2301.12004","kind":"arxiv","version":1}},"canonical_sha256":"23029e270d315af517cdd94ac0dee09c9fae5293ea64a958ac85a68d3032a9f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23029e270d315af517cdd94ac0dee09c9fae5293ea64a958ac85a68d3032a9f3","first_computed_at":"2026-07-05T05:36:34.137521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:34.137521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V8+Nnj/S9s9sl+m9bpk54kVXXbMuwRlmohuEv+iBKtOXYWBR3Rfh8K0YNGrWOSS6gUVAvBxPubaQdaiv/1O2CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:34.137956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca70d8c9a31c6a4cbaa3b2938d73f9c06b3a6ed281b68f6ff87ac4d35da3ab04","sha256:514d51a3218f7446f766a7a08738e9d932e66925346a010ad9bd29e0e74ca7a3"],"state_sha256":"66719028eef7b6934f5adb0494167060579c475638dd407bd1a7864c1aa05a74"}