{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IV5EJIFRUQAFNFFCUDOARYNYJJ","short_pith_number":"pith:IV5EJIFR","schema_version":"1.0","canonical_sha256":"457a44a0b1a4005694a2a0dc08e1b84a7e418b018de126951ec4ed94ac5975e6","source":{"kind":"arxiv","id":"2201.06653","version":1},"attestation_state":"computed","paper":{"title":"Data-Centric Machine Learning in the Legal Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hannes Westermann, Jaromir Savelka, Karim Benyekhlef, Kevin D. Ashley, Vern R. Walker","submitted_at":"2022-01-17T23:05:14Z","abstract_excerpt":"Machine learning research typically starts with a fixed data set created early in the process. The focus of the experiments is finding a model and training procedure that result in the best possible performance in terms of some selected evaluation metric. This paper explores how changes in a data set influence the measured performance of a model. Using three publicly available data sets from the legal domain, we investigate how changes to their size, the train/test splits, and the human labelling accuracy impact the performance of a trained deep learning classifier. We assess the overall perfo"},"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":"2201.06653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T23:05:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b1286616ab2043643d93258d3790d94eb904edff59919fed1515f68d5b5eb2b1","abstract_canon_sha256":"5faf4aa8ca66801b403fe36752656c8faf6263ea0315fb465eac88046d835f56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:49:00.374805Z","signature_b64":"9o/bqleAL3J07Rw8cyLKzmBknAE4UNFKUsgr56yxUK1L831GH25N1FrSYeL8DMK3DNBVcrDmz5OmWlLPzC7+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457a44a0b1a4005694a2a0dc08e1b84a7e418b018de126951ec4ed94ac5975e6","last_reissued_at":"2026-07-05T03:49:00.374394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:49:00.374394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Centric Machine Learning in the Legal Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hannes Westermann, Jaromir Savelka, Karim Benyekhlef, Kevin D. Ashley, Vern R. Walker","submitted_at":"2022-01-17T23:05:14Z","abstract_excerpt":"Machine learning research typically starts with a fixed data set created early in the process. The focus of the experiments is finding a model and training procedure that result in the best possible performance in terms of some selected evaluation metric. This paper explores how changes in a data set influence the measured performance of a model. Using three publicly available data sets from the legal domain, we investigate how changes to their size, the train/test splits, and the human labelling accuracy impact the performance of a trained deep learning classifier. We assess the overall perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06653","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/2201.06653/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":"2201.06653","created_at":"2026-07-05T03:49:00.374451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.06653v1","created_at":"2026-07-05T03:49:00.374451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06653","created_at":"2026-07-05T03:49:00.374451+00:00"},{"alias_kind":"pith_short_12","alias_value":"IV5EJIFRUQAF","created_at":"2026-07-05T03:49:00.374451+00:00"},{"alias_kind":"pith_short_16","alias_value":"IV5EJIFRUQAFNFFC","created_at":"2026-07-05T03:49:00.374451+00:00"},{"alias_kind":"pith_short_8","alias_value":"IV5EJIFR","created_at":"2026-07-05T03:49:00.374451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ","json":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ.json","graph_json":"https://pith.science/api/pith-number/IV5EJIFRUQAFNFFCUDOARYNYJJ/graph.json","events_json":"https://pith.science/api/pith-number/IV5EJIFRUQAFNFFCUDOARYNYJJ/events.json","paper":"https://pith.science/paper/IV5EJIFR"},"agent_actions":{"view_html":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ","download_json":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ.json","view_paper":"https://pith.science/paper/IV5EJIFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.06653&json=true","fetch_graph":"https://pith.science/api/pith-number/IV5EJIFRUQAFNFFCUDOARYNYJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IV5EJIFRUQAFNFFCUDOARYNYJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/action/storage_attestation","attest_author":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/action/author_attestation","sign_citation":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/action/citation_signature","submit_replication":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/action/replication_record"}},"created_at":"2026-07-05T03:49:00.374451+00:00","updated_at":"2026-07-05T03:49:00.374451+00:00"}