{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YVLPDS6RFGYO7GO7R2GRPBCROK","short_pith_number":"pith:YVLPDS6R","schema_version":"1.0","canonical_sha256":"c556f1cbd129b0ef99df8e8d17845172beeecf68b1c8b5e68d9c506ccd142cf2","source":{"kind":"arxiv","id":"2312.07182","version":1},"attestation_state":"computed","paper":{"title":"Classifying complex documents: comparing bespoke solutions to large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Glen Hopkins, Kristjan Kalm","submitted_at":"2023-12-12T11:38:09Z","abstract_excerpt":"Here we search for the best automated classification approach for a set of complex legal documents. Our classification task is not trivial: our aim is to classify ca 30,000 public courthouse records from 12 states and 267 counties at two different levels using nine sub-categories. Specifically, we investigated whether a fine-tuned large language model (LLM) can achieve the accuracy of a bespoke custom-trained model, and what is the amount of fine-tuning necessary."},"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":"2312.07182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T11:38:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ced4f0acc1855262da3dbe06d71f000a305e70ce889b267352845d211e91a14a","abstract_canon_sha256":"e5cf1d5e4e13d1dc74887cf91c20b229cfae592ec5856b28cecc298bd0562d6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:16.231291Z","signature_b64":"RaKCnlZSBh8yj7f9DWq21Q+enqXQEWXukWA1G11hi/XjoYUk9NhHuugzjOVYml92imjAwope3Ld5bK6afNpJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c556f1cbd129b0ef99df8e8d17845172beeecf68b1c8b5e68d9c506ccd142cf2","last_reissued_at":"2026-07-05T07:23:16.230788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:16.230788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classifying complex documents: comparing bespoke solutions to large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Glen Hopkins, Kristjan Kalm","submitted_at":"2023-12-12T11:38:09Z","abstract_excerpt":"Here we search for the best automated classification approach for a set of complex legal documents. Our classification task is not trivial: our aim is to classify ca 30,000 public courthouse records from 12 states and 267 counties at two different levels using nine sub-categories. Specifically, we investigated whether a fine-tuned large language model (LLM) can achieve the accuracy of a bespoke custom-trained model, and what is the amount of fine-tuning necessary."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07182","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/2312.07182/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":"2312.07182","created_at":"2026-07-05T07:23:16.230845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07182v1","created_at":"2026-07-05T07:23:16.230845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07182","created_at":"2026-07-05T07:23:16.230845+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVLPDS6RFGYO","created_at":"2026-07-05T07:23:16.230845+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVLPDS6RFGYO7GO7","created_at":"2026-07-05T07:23:16.230845+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVLPDS6R","created_at":"2026-07-05T07:23:16.230845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21069","citing_title":"CXXCrafter: An LLM-Based Agent for Automated C/C++ Open Source Software Building","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVLPDS6RFGYO7GO7R2GRPBCROK","json":"https://pith.science/pith/YVLPDS6RFGYO7GO7R2GRPBCROK.json","graph_json":"https://pith.science/api/pith-number/YVLPDS6RFGYO7GO7R2GRPBCROK/graph.json","events_json":"https://pith.science/api/pith-number/YVLPDS6RFGYO7GO7R2GRPBCROK/events.json","paper":"https://pith.science/paper/YVLPDS6R"},"agent_actions":{"view_html":"https://pith.science/pith/YVLPDS6RFGYO7GO7R2GRPBCROK","download_json":"https://pith.science/pith/YVLPDS6RFGYO7GO7R2GRPBCROK.json","view_paper":"https://pith.science/paper/YVLPDS6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07182&json=true","fetch_graph":"https://pith.science/api/pith-number/YVLPDS6RFGYO7GO7R2GRPBCROK/graph.json","fetch_events":"https://pith.science/api/pith-number/YVLPDS6RFGYO7GO7R2GRPBCROK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVLPDS6RFGYO7GO7R2GRPBCROK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVLPDS6RFGYO7GO7R2GRPBCROK/action/storage_attestation","attest_author":"https://pith.science/pith/YVLPDS6RFGYO7GO7R2GRPBCROK/action/author_attestation","sign_citation":"https://pith.science/pith/YVLPDS6RFGYO7GO7R2GRPBCROK/action/citation_signature","submit_replication":"https://pith.science/pith/YVLPDS6RFGYO7GO7R2GRPBCROK/action/replication_record"}},"created_at":"2026-07-05T07:23:16.230845+00:00","updated_at":"2026-07-05T07:23:16.230845+00:00"}