{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:64ODKDPTHURMXJVPZH5MLMSIQG","short_pith_number":"pith:64ODKDPT","schema_version":"1.0","canonical_sha256":"f71c350df33d22cba6afc9fac5b2488196f88a83aee528202f962de3f8d1689c","source":{"kind":"arxiv","id":"2308.04138","version":1},"attestation_state":"computed","paper":{"title":"Large Language Model Prompt Chaining for Long Legal Document Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dietrich Trautmann","submitted_at":"2023-08-08T08:57:01Z","abstract_excerpt":"Prompting is used to guide or steer a language model in generating an appropriate response that is consistent with the desired outcome. Chaining is a strategy used to decompose complex tasks into smaller, manageable components. In this study, we utilize prompt chaining for extensive legal document classification tasks, which present difficulties due to their intricate domain-specific language and considerable length. Our approach begins with the creation of a concise summary of the original document, followed by a semantic search for related exemplar texts and their corresponding annotations f"},"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":"2308.04138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-08T08:57:01Z","cross_cats_sorted":[],"title_canon_sha256":"6dabd4a8c14171e0c383a4cbb7e2939d09e74cd538ea6baab3039722776eec4e","abstract_canon_sha256":"7584f35ac6fd07490202af5a97ff88a945318578e9fe4fc528c19f2c46ca9ba3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:22.951201Z","signature_b64":"1qPfFtTN+TgvPz16meuv6MItM95ZMy1iYZv+PNQCTpiBv+sGrpX7XXE+WE3FiLtbW7IM6cOUT40pfOEohsmJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f71c350df33d22cba6afc9fac5b2488196f88a83aee528202f962de3f8d1689c","last_reissued_at":"2026-07-05T06:39:22.950742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:22.950742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model Prompt Chaining for Long Legal Document Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dietrich Trautmann","submitted_at":"2023-08-08T08:57:01Z","abstract_excerpt":"Prompting is used to guide or steer a language model in generating an appropriate response that is consistent with the desired outcome. Chaining is a strategy used to decompose complex tasks into smaller, manageable components. In this study, we utilize prompt chaining for extensive legal document classification tasks, which present difficulties due to their intricate domain-specific language and considerable length. Our approach begins with the creation of a concise summary of the original document, followed by a semantic search for related exemplar texts and their corresponding annotations f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04138","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/2308.04138/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":"2308.04138","created_at":"2026-07-05T06:39:22.950803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.04138v1","created_at":"2026-07-05T06:39:22.950803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04138","created_at":"2026-07-05T06:39:22.950803+00:00"},{"alias_kind":"pith_short_12","alias_value":"64ODKDPTHURM","created_at":"2026-07-05T06:39:22.950803+00:00"},{"alias_kind":"pith_short_16","alias_value":"64ODKDPTHURMXJVP","created_at":"2026-07-05T06:39:22.950803+00:00"},{"alias_kind":"pith_short_8","alias_value":"64ODKDPT","created_at":"2026-07-05T06:39:22.950803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06016","citing_title":"Conditional Multi-Stage Failure Recovery for Embodied Agents","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/64ODKDPTHURMXJVPZH5MLMSIQG","json":"https://pith.science/pith/64ODKDPTHURMXJVPZH5MLMSIQG.json","graph_json":"https://pith.science/api/pith-number/64ODKDPTHURMXJVPZH5MLMSIQG/graph.json","events_json":"https://pith.science/api/pith-number/64ODKDPTHURMXJVPZH5MLMSIQG/events.json","paper":"https://pith.science/paper/64ODKDPT"},"agent_actions":{"view_html":"https://pith.science/pith/64ODKDPTHURMXJVPZH5MLMSIQG","download_json":"https://pith.science/pith/64ODKDPTHURMXJVPZH5MLMSIQG.json","view_paper":"https://pith.science/paper/64ODKDPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.04138&json=true","fetch_graph":"https://pith.science/api/pith-number/64ODKDPTHURMXJVPZH5MLMSIQG/graph.json","fetch_events":"https://pith.science/api/pith-number/64ODKDPTHURMXJVPZH5MLMSIQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64ODKDPTHURMXJVPZH5MLMSIQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64ODKDPTHURMXJVPZH5MLMSIQG/action/storage_attestation","attest_author":"https://pith.science/pith/64ODKDPTHURMXJVPZH5MLMSIQG/action/author_attestation","sign_citation":"https://pith.science/pith/64ODKDPTHURMXJVPZH5MLMSIQG/action/citation_signature","submit_replication":"https://pith.science/pith/64ODKDPTHURMXJVPZH5MLMSIQG/action/replication_record"}},"created_at":"2026-07-05T06:39:22.950803+00:00","updated_at":"2026-07-05T06:39:22.950803+00:00"}