{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DUIN6GTUW2G26GPKETCSDT6HHX","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":"c4bc9b65ebdf1cddfec9c960eed1882e27594080d85fc7dd34c4e3dbada5944c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T13:04:58Z","title_canon_sha256":"64584b10a87531f3f17e1a5cfb23b4687076e7e60cc5be16fc0b3fa99d7e9d09"},"schema_version":"1.0","source":{"id":"2605.19806","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19806","created_at":"2026-05-20T01:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19806v1","created_at":"2026-05-20T01:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19806","created_at":"2026-05-20T01:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"DUIN6GTUW2G2","created_at":"2026-05-20T01:06:15Z"},{"alias_kind":"pith_short_16","alias_value":"DUIN6GTUW2G26GPK","created_at":"2026-05-20T01:06:15Z"},{"alias_kind":"pith_short_8","alias_value":"DUIN6GTU","created_at":"2026-05-20T01:06:15Z"}],"graph_snapshots":[{"event_id":"sha256:b9a512f25d793100c0d561f03637d912018bab6530cc68bf83ee2c1f5d21f599","target":"graph","created_at":"2026-05-20T01:06:15Z","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/2605.19806/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andreas Schultz, Max Prior, Natalia Milanova","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T13:04:58Z","title":"Chunking German Legal Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19806","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":"sha256:1b24e3d5fa72515c3944c26c8c57d28ad04588220f7e756cdfa8a95b7bd7d025","target":"record","created_at":"2026-05-20T01:06:15Z","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":"c4bc9b65ebdf1cddfec9c960eed1882e27594080d85fc7dd34c4e3dbada5944c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T13:04:58Z","title_canon_sha256":"64584b10a87531f3f17e1a5cfb23b4687076e7e60cc5be16fc0b3fa99d7e9d09"},"schema_version":"1.0","source":{"id":"2605.19806","kind":"arxiv","version":1}},"canonical_sha256":"1d10df1a74b68daf19ea24c521cfc73dd4013c7d01a4b5ecf7c49b03d73e97a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d10df1a74b68daf19ea24c521cfc73dd4013c7d01a4b5ecf7c49b03d73e97a7","first_computed_at":"2026-05-20T01:06:15.461451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:06:15.461451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KhLhS5BQnE/HNwvHpKo3kMcEdyVxHc1bpIhSd7nuOv2CZu9ksXSADvCMDUxPzcWYaukFKgWHhTHwklghIXTTCw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:06:15.462012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19806","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b24e3d5fa72515c3944c26c8c57d28ad04588220f7e756cdfa8a95b7bd7d025","sha256:b9a512f25d793100c0d561f03637d912018bab6530cc68bf83ee2c1f5d21f599"],"state_sha256":"51b7273de7d682d7321bc4062343e84fc2e0b11f34c5c889f3f744d7661317d7"}