{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6L34WZPE7P6MMWX2ZVDAXJLJ7T","short_pith_number":"pith:6L34WZPE","schema_version":"1.0","canonical_sha256":"f2f7cb65e4fbfcc65afacd460ba569fcce95ee78adb2ff3b654968063c926de4","source":{"kind":"arxiv","id":"2401.11852","version":1},"attestation_state":"computed","paper":{"title":"The Right Model for the Job: An Evaluation of Legal Multi-Label Classification Baselines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Claudia Schulz, Jaykumar Kasundra, Martina Forster, Melicaalsadat Mirsafian, Prudhvi Nokku, Stavroula Skylaki","submitted_at":"2024-01-22T11:15:07Z","abstract_excerpt":"Multi-Label Classification (MLC) is a common task in the legal domain, where more than one label may be assigned to a legal document. A wide range of methods can be applied, ranging from traditional ML approaches to the latest Transformer-based architectures. In this work, we perform an evaluation of different MLC methods using two public legal datasets, POSTURE50K and EURLEX57K. By varying the amount of training data and the number of labels, we explore the comparative advantage offered by different approaches in relation to the dataset properties. Our findings highlight DistilRoBERTa and Leg"},"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":"2401.11852","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T11:15:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0f6a59cd9a6dafa332d84b4635f6a479874460a9242825139b421f9be66e6207","abstract_canon_sha256":"c72f733e6e63e2115547d8ae8d5f1c7122e70e17dfa46947d4fb939b4c509c02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:11.164726Z","signature_b64":"1nrbM1bi4iQmWOajNT24x44kYYQhvlNy2k1QfJr8C7AAX3iTrqkRuC5MNqkOCSod4z99y/h7C0v0e9XgY3kgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2f7cb65e4fbfcc65afacd460ba569fcce95ee78adb2ff3b654968063c926de4","last_reissued_at":"2026-07-05T07:36:11.164266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:11.164266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Right Model for the Job: An Evaluation of Legal Multi-Label Classification Baselines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Claudia Schulz, Jaykumar Kasundra, Martina Forster, Melicaalsadat Mirsafian, Prudhvi Nokku, Stavroula Skylaki","submitted_at":"2024-01-22T11:15:07Z","abstract_excerpt":"Multi-Label Classification (MLC) is a common task in the legal domain, where more than one label may be assigned to a legal document. A wide range of methods can be applied, ranging from traditional ML approaches to the latest Transformer-based architectures. In this work, we perform an evaluation of different MLC methods using two public legal datasets, POSTURE50K and EURLEX57K. By varying the amount of training data and the number of labels, we explore the comparative advantage offered by different approaches in relation to the dataset properties. Our findings highlight DistilRoBERTa and Leg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11852","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/2401.11852/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":"2401.11852","created_at":"2026-07-05T07:36:11.164324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11852v1","created_at":"2026-07-05T07:36:11.164324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11852","created_at":"2026-07-05T07:36:11.164324+00:00"},{"alias_kind":"pith_short_12","alias_value":"6L34WZPE7P6M","created_at":"2026-07-05T07:36:11.164324+00:00"},{"alias_kind":"pith_short_16","alias_value":"6L34WZPE7P6MMWX2","created_at":"2026-07-05T07:36:11.164324+00:00"},{"alias_kind":"pith_short_8","alias_value":"6L34WZPE","created_at":"2026-07-05T07:36:11.164324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16662","citing_title":"A Supervised Machine Learning Approach for Assessing Grant Peer Review Reports","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6L34WZPE7P6MMWX2ZVDAXJLJ7T","json":"https://pith.science/pith/6L34WZPE7P6MMWX2ZVDAXJLJ7T.json","graph_json":"https://pith.science/api/pith-number/6L34WZPE7P6MMWX2ZVDAXJLJ7T/graph.json","events_json":"https://pith.science/api/pith-number/6L34WZPE7P6MMWX2ZVDAXJLJ7T/events.json","paper":"https://pith.science/paper/6L34WZPE"},"agent_actions":{"view_html":"https://pith.science/pith/6L34WZPE7P6MMWX2ZVDAXJLJ7T","download_json":"https://pith.science/pith/6L34WZPE7P6MMWX2ZVDAXJLJ7T.json","view_paper":"https://pith.science/paper/6L34WZPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11852&json=true","fetch_graph":"https://pith.science/api/pith-number/6L34WZPE7P6MMWX2ZVDAXJLJ7T/graph.json","fetch_events":"https://pith.science/api/pith-number/6L34WZPE7P6MMWX2ZVDAXJLJ7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6L34WZPE7P6MMWX2ZVDAXJLJ7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6L34WZPE7P6MMWX2ZVDAXJLJ7T/action/storage_attestation","attest_author":"https://pith.science/pith/6L34WZPE7P6MMWX2ZVDAXJLJ7T/action/author_attestation","sign_citation":"https://pith.science/pith/6L34WZPE7P6MMWX2ZVDAXJLJ7T/action/citation_signature","submit_replication":"https://pith.science/pith/6L34WZPE7P6MMWX2ZVDAXJLJ7T/action/replication_record"}},"created_at":"2026-07-05T07:36:11.164324+00:00","updated_at":"2026-07-05T07:36:11.164324+00:00"}