{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M7NFMJ2GHZPAZNMN6ZOXATNNFG","short_pith_number":"pith:M7NFMJ2G","schema_version":"1.0","canonical_sha256":"67da5627463e5e0cb58df65d704dad299eef6a7c99a8b4d626c7c84e14e58909","source":{"kind":"arxiv","id":"2310.17413","version":1},"attestation_state":"computed","paper":{"title":"Harnessing GPT-3.5-turbo for Rhetorical Role Prediction in Legal Cases","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anas Belfathi, Laura Monceaux, Nicolas Hernandez","submitted_at":"2023-10-26T14:19:48Z","abstract_excerpt":"We propose a comprehensive study of one-stage elicitation techniques for querying a large pre-trained generative transformer (GPT-3.5-turbo) in the rhetorical role prediction task of legal cases. This task is known as requiring textual context to be addressed. Our study explores strategies such as zero-few shots, task specification with definitions and clarification of annotation ambiguities, textual context and reasoning with general prompts and specific questions. We show that the number of examples, the definition of labels, the presentation of the (labelled) textual context and specific qu"},"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":"2310.17413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T14:19:48Z","cross_cats_sorted":[],"title_canon_sha256":"ab8b5c771a840405b3ce53665f7fd3e0b2115f5b3bbce73351145ae1b991f681","abstract_canon_sha256":"c590b5b8e0a6e29aab64f7bceca1cfeade674fbf845387c1c9a5dba83a0d5d17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:33.392293Z","signature_b64":"nPPQKyMN3NLcUAIoxkZWwq/hT8yIUlFv9D0jD8tWHcGRrOUGjeRyT+nj/3h3i6iJDDGQiA9KTn/jO9k31JXFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67da5627463e5e0cb58df65d704dad299eef6a7c99a8b4d626c7c84e14e58909","last_reissued_at":"2026-07-05T07:05:33.391837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:33.391837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing GPT-3.5-turbo for Rhetorical Role Prediction in Legal Cases","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anas Belfathi, Laura Monceaux, Nicolas Hernandez","submitted_at":"2023-10-26T14:19:48Z","abstract_excerpt":"We propose a comprehensive study of one-stage elicitation techniques for querying a large pre-trained generative transformer (GPT-3.5-turbo) in the rhetorical role prediction task of legal cases. This task is known as requiring textual context to be addressed. Our study explores strategies such as zero-few shots, task specification with definitions and clarification of annotation ambiguities, textual context and reasoning with general prompts and specific questions. We show that the number of examples, the definition of labels, the presentation of the (labelled) textual context and specific qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17413","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/2310.17413/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":"2310.17413","created_at":"2026-07-05T07:05:33.391896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17413v1","created_at":"2026-07-05T07:05:33.391896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17413","created_at":"2026-07-05T07:05:33.391896+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7NFMJ2GHZPA","created_at":"2026-07-05T07:05:33.391896+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7NFMJ2GHZPAZNMN","created_at":"2026-07-05T07:05:33.391896+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7NFMJ2G","created_at":"2026-07-05T07:05:33.391896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.03325","citing_title":"From Judgments to Issues: Structured Extraction of Legal Reasoning with Citation-Hallucination Control","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7NFMJ2GHZPAZNMN6ZOXATNNFG","json":"https://pith.science/pith/M7NFMJ2GHZPAZNMN6ZOXATNNFG.json","graph_json":"https://pith.science/api/pith-number/M7NFMJ2GHZPAZNMN6ZOXATNNFG/graph.json","events_json":"https://pith.science/api/pith-number/M7NFMJ2GHZPAZNMN6ZOXATNNFG/events.json","paper":"https://pith.science/paper/M7NFMJ2G"},"agent_actions":{"view_html":"https://pith.science/pith/M7NFMJ2GHZPAZNMN6ZOXATNNFG","download_json":"https://pith.science/pith/M7NFMJ2GHZPAZNMN6ZOXATNNFG.json","view_paper":"https://pith.science/paper/M7NFMJ2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17413&json=true","fetch_graph":"https://pith.science/api/pith-number/M7NFMJ2GHZPAZNMN6ZOXATNNFG/graph.json","fetch_events":"https://pith.science/api/pith-number/M7NFMJ2GHZPAZNMN6ZOXATNNFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7NFMJ2GHZPAZNMN6ZOXATNNFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7NFMJ2GHZPAZNMN6ZOXATNNFG/action/storage_attestation","attest_author":"https://pith.science/pith/M7NFMJ2GHZPAZNMN6ZOXATNNFG/action/author_attestation","sign_citation":"https://pith.science/pith/M7NFMJ2GHZPAZNMN6ZOXATNNFG/action/citation_signature","submit_replication":"https://pith.science/pith/M7NFMJ2GHZPAZNMN6ZOXATNNFG/action/replication_record"}},"created_at":"2026-07-05T07:05:33.391896+00:00","updated_at":"2026-07-05T07:05:33.391896+00:00"}