{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DUIN6GTUW2G26GPKETCSDT6HHX","short_pith_number":"pith:DUIN6GTU","schema_version":"1.0","canonical_sha256":"1d10df1a74b68daf19ea24c521cfc73dd4013c7d01a4b5ecf7c49b03d73e97a7","source":{"kind":"arxiv","id":"2605.19806","version":1},"attestation_state":"computed","paper":{"title":"Chunking German Legal Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andreas Schultz, Max Prior, Natalia Milanova","submitted_at":"2026-05-19T13:04:58Z","abstract_excerpt":"This paper investigates chunking strategies for retrieval-augmented generation on German statutory law, using the German Civil Code as a structured benchmark corpus. We implement and compare a range of segmentation approaches, including structural units (sections, subsections, sentences, propositions), fixed-size windows, contextual chunking, semantic clustering, Lumber-style chunking, and RAPTOR-based hierarchical retrieval. All methods are evaluated on a legal question-answering dataset with section-level gold labels, measuring recall, query latency, index build time, and storage requirement"},"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":"2605.19806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T13:04:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64584b10a87531f3f17e1a5cfb23b4687076e7e60cc5be16fc0b3fa99d7e9d09","abstract_canon_sha256":"c4bc9b65ebdf1cddfec9c960eed1882e27594080d85fc7dd34c4e3dbada5944c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:15.462012Z","signature_b64":"KhLhS5BQnE/HNwvHpKo3kMcEdyVxHc1bpIhSd7nuOv2CZu9ksXSADvCMDUxPzcWYaukFKgWHhTHwklghIXTTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d10df1a74b68daf19ea24c521cfc73dd4013c7d01a4b5ecf7c49b03d73e97a7","last_reissued_at":"2026-05-20T01:06:15.461451Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:15.461451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chunking German Legal Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andreas Schultz, Max Prior, Natalia Milanova","submitted_at":"2026-05-19T13:04:58Z","abstract_excerpt":"This paper investigates chunking strategies for retrieval-augmented generation on German statutory law, using the German Civil Code as a structured benchmark corpus. We implement and compare a range of segmentation approaches, including structural units (sections, subsections, sentences, propositions), fixed-size windows, contextual chunking, semantic clustering, Lumber-style chunking, and RAPTOR-based hierarchical retrieval. All methods are evaluated on a legal question-answering dataset with section-level gold labels, measuring recall, query latency, index build time, and storage requirement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19806","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/2605.19806/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":"2605.19806","created_at":"2026-05-20T01:06:15.461549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19806v1","created_at":"2026-05-20T01:06:15.461549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19806","created_at":"2026-05-20T01:06:15.461549+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUIN6GTUW2G2","created_at":"2026-05-20T01:06:15.461549+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUIN6GTUW2G26GPK","created_at":"2026-05-20T01:06:15.461549+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUIN6GTU","created_at":"2026-05-20T01:06:15.461549+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/DUIN6GTUW2G26GPKETCSDT6HHX","json":"https://pith.science/pith/DUIN6GTUW2G26GPKETCSDT6HHX.json","graph_json":"https://pith.science/api/pith-number/DUIN6GTUW2G26GPKETCSDT6HHX/graph.json","events_json":"https://pith.science/api/pith-number/DUIN6GTUW2G26GPKETCSDT6HHX/events.json","paper":"https://pith.science/paper/DUIN6GTU"},"agent_actions":{"view_html":"https://pith.science/pith/DUIN6GTUW2G26GPKETCSDT6HHX","download_json":"https://pith.science/pith/DUIN6GTUW2G26GPKETCSDT6HHX.json","view_paper":"https://pith.science/paper/DUIN6GTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19806&json=true","fetch_graph":"https://pith.science/api/pith-number/DUIN6GTUW2G26GPKETCSDT6HHX/graph.json","fetch_events":"https://pith.science/api/pith-number/DUIN6GTUW2G26GPKETCSDT6HHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUIN6GTUW2G26GPKETCSDT6HHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUIN6GTUW2G26GPKETCSDT6HHX/action/storage_attestation","attest_author":"https://pith.science/pith/DUIN6GTUW2G26GPKETCSDT6HHX/action/author_attestation","sign_citation":"https://pith.science/pith/DUIN6GTUW2G26GPKETCSDT6HHX/action/citation_signature","submit_replication":"https://pith.science/pith/DUIN6GTUW2G26GPKETCSDT6HHX/action/replication_record"}},"created_at":"2026-05-20T01:06:15.461549+00:00","updated_at":"2026-05-20T01:06:15.461549+00:00"}