{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AEKBW34OIU3O4CRCPT2YYAAI2Q","short_pith_number":"pith:AEKBW34O","schema_version":"1.0","canonical_sha256":"01141b6f8e4536ee0a227cf58c0008d409ee073c51f9ffa49c081b4ec432ea7b","source":{"kind":"arxiv","id":"2304.12202","version":1},"attestation_state":"computed","paper":{"title":"ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilias Chalkidis","submitted_at":"2023-03-09T16:42:29Z","abstract_excerpt":"Following the hype around OpenAI's ChatGPT conversational agent, the last straw in the recent development of Large Language Models (LLMs) that demonstrate emergent unprecedented zero-shot capabilities, we audit the latest OpenAI's GPT-3.5 model, `gpt-3.5-turbo', the first available ChatGPT model, in the LexGLUE benchmark in a zero-shot fashion providing examples in a templated instruction-following format. The results indicate that ChatGPT achieves an average micro-F1 score of 47.6% across LexGLUE tasks, surpassing the baseline guessing rates. Notably, the model performs exceptionally well in "},"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":"2304.12202","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-09T16:42:29Z","cross_cats_sorted":[],"title_canon_sha256":"67b7c39cc566e9ec1625a9ab130860082282467a9a70987b6c9f1a51cd395b5d","abstract_canon_sha256":"8973fe23fd674627f622e81ba72ccae66f8c98d394570dd599dd9820e904b194"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:49.154138Z","signature_b64":"inO380b+3UrjMVEU8M15GVc7Ef+SVpaqA0gu5sqIe8Hooq0VtzdAuI5ZR+btLo7TFIRDOmNUNpjdlAGCHHZEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01141b6f8e4536ee0a227cf58c0008d409ee073c51f9ffa49c081b4ec432ea7b","last_reissued_at":"2026-07-05T06:03:49.153604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:49.153604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilias Chalkidis","submitted_at":"2023-03-09T16:42:29Z","abstract_excerpt":"Following the hype around OpenAI's ChatGPT conversational agent, the last straw in the recent development of Large Language Models (LLMs) that demonstrate emergent unprecedented zero-shot capabilities, we audit the latest OpenAI's GPT-3.5 model, `gpt-3.5-turbo', the first available ChatGPT model, in the LexGLUE benchmark in a zero-shot fashion providing examples in a templated instruction-following format. The results indicate that ChatGPT achieves an average micro-F1 score of 47.6% across LexGLUE tasks, surpassing the baseline guessing rates. Notably, the model performs exceptionally well in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12202","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/2304.12202/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":"2304.12202","created_at":"2026-07-05T06:03:49.153662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.12202v1","created_at":"2026-07-05T06:03:49.153662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12202","created_at":"2026-07-05T06:03:49.153662+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEKBW34OIU3O","created_at":"2026-07-05T06:03:49.153662+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEKBW34OIU3O4CRC","created_at":"2026-07-05T06:03:49.153662+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEKBW34O","created_at":"2026-07-05T06:03:49.153662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08825","citing_title":"Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEKBW34OIU3O4CRCPT2YYAAI2Q","json":"https://pith.science/pith/AEKBW34OIU3O4CRCPT2YYAAI2Q.json","graph_json":"https://pith.science/api/pith-number/AEKBW34OIU3O4CRCPT2YYAAI2Q/graph.json","events_json":"https://pith.science/api/pith-number/AEKBW34OIU3O4CRCPT2YYAAI2Q/events.json","paper":"https://pith.science/paper/AEKBW34O"},"agent_actions":{"view_html":"https://pith.science/pith/AEKBW34OIU3O4CRCPT2YYAAI2Q","download_json":"https://pith.science/pith/AEKBW34OIU3O4CRCPT2YYAAI2Q.json","view_paper":"https://pith.science/paper/AEKBW34O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.12202&json=true","fetch_graph":"https://pith.science/api/pith-number/AEKBW34OIU3O4CRCPT2YYAAI2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/AEKBW34OIU3O4CRCPT2YYAAI2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEKBW34OIU3O4CRCPT2YYAAI2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEKBW34OIU3O4CRCPT2YYAAI2Q/action/storage_attestation","attest_author":"https://pith.science/pith/AEKBW34OIU3O4CRCPT2YYAAI2Q/action/author_attestation","sign_citation":"https://pith.science/pith/AEKBW34OIU3O4CRCPT2YYAAI2Q/action/citation_signature","submit_replication":"https://pith.science/pith/AEKBW34OIU3O4CRCPT2YYAAI2Q/action/replication_record"}},"created_at":"2026-07-05T06:03:49.153662+00:00","updated_at":"2026-07-05T06:03:49.153662+00:00"}