{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VZJNWUTBXDB2JR3GXQR5GQFFSO","short_pith_number":"pith:VZJNWUTB","schema_version":"1.0","canonical_sha256":"ae52db5261b8c3a4c766bc23d340a59397e3907e98d5ea39cee9a09d2d39d781","source":{"kind":"arxiv","id":"2409.09947","version":2},"attestation_state":"computed","paper":{"title":"Gaps or Hallucinations? Gazing into Machine-Generated Legal Analysis for Fine-grained Text Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Abe Bohan Hou, Andrew Blair-Stanek, Benjamin Van Durme, Nils Holzenberger, William Jurayj","submitted_at":"2024-09-16T02:38:38Z","abstract_excerpt":"Large Language Models (LLMs) show promise as a writing aid for professionals performing legal analyses. However, LLMs can often hallucinate in this setting, in ways difficult to recognize by non-professionals and existing text evaluation metrics. In this work, we pose the question: when can machine-generated legal analysis be evaluated as acceptable? We introduce the neutral notion of gaps, as opposed to hallucinations in a strict erroneous sense, to refer to the difference between human-written and machine-generated legal analysis. Gaps do not always equate to invalid generation. Working with"},"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":"2409.09947","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-16T02:38:38Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"5d55e45d46db9636aecbc02d40cfff2e7a1a44e5b40033d75cb22bb2c819f85c","abstract_canon_sha256":"29ddf9c18858939d9ed18735c7362a0dac192a8a7bf66f39cf713f6eca33e6c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:50.383281Z","signature_b64":"SIpoeVeZr7UPCh9xqmi7UpLi7h/5UMwlqqjG1+cZxHT0GzZ7U0vlIu1ZIbKK0dc2LZotF5Nq8MTQPBjeSTyfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae52db5261b8c3a4c766bc23d340a59397e3907e98d5ea39cee9a09d2d39d781","last_reissued_at":"2026-07-05T09:10:50.382811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:50.382811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaps or Hallucinations? Gazing into Machine-Generated Legal Analysis for Fine-grained Text Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Abe Bohan Hou, Andrew Blair-Stanek, Benjamin Van Durme, Nils Holzenberger, William Jurayj","submitted_at":"2024-09-16T02:38:38Z","abstract_excerpt":"Large Language Models (LLMs) show promise as a writing aid for professionals performing legal analyses. However, LLMs can often hallucinate in this setting, in ways difficult to recognize by non-professionals and existing text evaluation metrics. In this work, we pose the question: when can machine-generated legal analysis be evaluated as acceptable? We introduce the neutral notion of gaps, as opposed to hallucinations in a strict erroneous sense, to refer to the difference between human-written and machine-generated legal analysis. Gaps do not always equate to invalid generation. Working with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09947","kind":"arxiv","version":2},"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/2409.09947/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":"2409.09947","created_at":"2026-07-05T09:10:50.382864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09947v2","created_at":"2026-07-05T09:10:50.382864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09947","created_at":"2026-07-05T09:10:50.382864+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZJNWUTBXDB2","created_at":"2026-07-05T09:10:50.382864+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZJNWUTBXDB2JR3G","created_at":"2026-07-05T09:10:50.382864+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZJNWUTB","created_at":"2026-07-05T09:10:50.382864+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/VZJNWUTBXDB2JR3GXQR5GQFFSO","json":"https://pith.science/pith/VZJNWUTBXDB2JR3GXQR5GQFFSO.json","graph_json":"https://pith.science/api/pith-number/VZJNWUTBXDB2JR3GXQR5GQFFSO/graph.json","events_json":"https://pith.science/api/pith-number/VZJNWUTBXDB2JR3GXQR5GQFFSO/events.json","paper":"https://pith.science/paper/VZJNWUTB"},"agent_actions":{"view_html":"https://pith.science/pith/VZJNWUTBXDB2JR3GXQR5GQFFSO","download_json":"https://pith.science/pith/VZJNWUTBXDB2JR3GXQR5GQFFSO.json","view_paper":"https://pith.science/paper/VZJNWUTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09947&json=true","fetch_graph":"https://pith.science/api/pith-number/VZJNWUTBXDB2JR3GXQR5GQFFSO/graph.json","fetch_events":"https://pith.science/api/pith-number/VZJNWUTBXDB2JR3GXQR5GQFFSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZJNWUTBXDB2JR3GXQR5GQFFSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZJNWUTBXDB2JR3GXQR5GQFFSO/action/storage_attestation","attest_author":"https://pith.science/pith/VZJNWUTBXDB2JR3GXQR5GQFFSO/action/author_attestation","sign_citation":"https://pith.science/pith/VZJNWUTBXDB2JR3GXQR5GQFFSO/action/citation_signature","submit_replication":"https://pith.science/pith/VZJNWUTBXDB2JR3GXQR5GQFFSO/action/replication_record"}},"created_at":"2026-07-05T09:10:50.382864+00:00","updated_at":"2026-07-05T09:10:50.382864+00:00"}