{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IV5EJIFRUQAFNFFCUDOARYNYJJ","short_pith_number":"pith:IV5EJIFR","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"},"canonical_sha256":"457a44a0b1a4005694a2a0dc08e1b84a7e418b018de126951ec4ed94ac5975e6","source":{"kind":"arxiv","id":"2201.06653","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06653","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06653v1","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06653","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"IV5EJIFRUQAF","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"IV5EJIFRUQAFNFFC","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"IV5EJIFR","created_at":"2026-07-05T03:49:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IV5EJIFRUQAFNFFCUDOARYNYJJ","target":"record","payload":{"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"},"canonical_sha256":"457a44a0b1a4005694a2a0dc08e1b84a7e418b018de126951ec4ed94ac5975e6","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"},"source_kind":"arxiv","source_id":"2201.06653","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:49:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TAMnjJz1PuOGohkipZN3QVNZ1T+ox9I+U4BedQD0z3CxpubB9bYGzUjd2ORwXQey13Q21BBOswkgFVuOSfSlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T12:44:00.783773Z"},"content_sha256":"ed6b73bcbe34afb220cbc93579b6cc1f1ed7c6d004e569b4f8c5ef6f817da577","schema_version":"1.0","event_id":"sha256:ed6b73bcbe34afb220cbc93579b6cc1f1ed7c6d004e569b4f8c5ef6f817da577"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IV5EJIFRUQAFNFFCUDOARYNYJJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:49:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jI0Fd5hjctwykYJ6Khlh1WSp7fGnoqgEMOOuc5MtpjJUqLHesOPCKFgDZiFp1v2Zv5CYOwHFAn6HrQMb7tUWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T12:44:00.784135Z"},"content_sha256":"8b57632eed6749b0a0c96e140f73561924b79dc53f5099cbbdd49b8d281c410c","schema_version":"1.0","event_id":"sha256:8b57632eed6749b0a0c96e140f73561924b79dc53f5099cbbdd49b8d281c410c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/bundle.json","state_url":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-14T12:44:00Z","links":{"resolver":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ","bundle":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/bundle.json","state":"https://pith.science/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IV5EJIFRUQAFNFFCUDOARYNYJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IV5EJIFRUQAFNFFCUDOARYNYJJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5faf4aa8ca66801b403fe36752656c8faf6263ea0315fb465eac88046d835f56","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T23:05:14Z","title_canon_sha256":"b1286616ab2043643d93258d3790d94eb904edff59919fed1515f68d5b5eb2b1"},"schema_version":"1.0","source":{"id":"2201.06653","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06653","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06653v1","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06653","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"IV5EJIFRUQAF","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"IV5EJIFRUQAFNFFC","created_at":"2026-07-05T03:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"IV5EJIFR","created_at":"2026-07-05T03:49:00Z"}],"graph_snapshots":[{"event_id":"sha256:8b57632eed6749b0a0c96e140f73561924b79dc53f5099cbbdd49b8d281c410c","target":"graph","created_at":"2026-07-05T03:49:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.06653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hannes Westermann, Jaromir Savelka, Karim Benyekhlef, Kevin D. Ashley, Vern R. Walker","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T23:05:14Z","title":"Data-Centric Machine Learning in the Legal Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06653","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ed6b73bcbe34afb220cbc93579b6cc1f1ed7c6d004e569b4f8c5ef6f817da577","target":"record","created_at":"2026-07-05T03:49:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5faf4aa8ca66801b403fe36752656c8faf6263ea0315fb465eac88046d835f56","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T23:05:14Z","title_canon_sha256":"b1286616ab2043643d93258d3790d94eb904edff59919fed1515f68d5b5eb2b1"},"schema_version":"1.0","source":{"id":"2201.06653","kind":"arxiv","version":1}},"canonical_sha256":"457a44a0b1a4005694a2a0dc08e1b84a7e418b018de126951ec4ed94ac5975e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"457a44a0b1a4005694a2a0dc08e1b84a7e418b018de126951ec4ed94ac5975e6","first_computed_at":"2026-07-05T03:49:00.374394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:49:00.374394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9o/bqleAL3J07Rw8cyLKzmBknAE4UNFKUsgr56yxUK1L831GH25N1FrSYeL8DMK3DNBVcrDmz5OmWlLPzC7+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:49:00.374805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.06653","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed6b73bcbe34afb220cbc93579b6cc1f1ed7c6d004e569b4f8c5ef6f817da577","sha256:8b57632eed6749b0a0c96e140f73561924b79dc53f5099cbbdd49b8d281c410c"],"state_sha256":"21589e7e526e8a9369e75e281ca36db79784071120a4c96fa363b5a7a076fb2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y0qCgnvA/ae802DAYL3YLjtRJmpWFvZd/D897x2i/Rgpp0LBT3M/uprjroDeTNHzaf6KnRPvNsXKE/0OXbO5Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T12:44:00.786238Z","bundle_sha256":"4751bac605bafab032543e3335381eb37df8cdd9eb006adcf0a0d1da083ab2fa"}}