{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5DU3PVUW45ACHHR2XSJZAKYRC3","short_pith_number":"pith:5DU3PVUW","canonical_record":{"source":{"id":"2311.04911","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T18:31:02Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"79a918c2568fb9a88504c17c0742c67141025b3ddae0b8423bede26d94f0a368","abstract_canon_sha256":"bae5d8a897e12772e56d2f1315241fe830c0d92266d276d8af050c46b3a399cb"},"schema_version":"1.0"},"canonical_sha256":"e8e9b7d696e740239e3abc93902b1116eca246e578b919734fb6f5f14aa26c7d","source":{"kind":"arxiv","id":"2311.04911","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04911","created_at":"2026-07-05T07:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04911v1","created_at":"2026-07-05T07:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04911","created_at":"2026-07-05T07:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"5DU3PVUW45AC","created_at":"2026-07-05T07:10:51Z"},{"alias_kind":"pith_short_16","alias_value":"5DU3PVUW45ACHHR2","created_at":"2026-07-05T07:10:51Z"},{"alias_kind":"pith_short_8","alias_value":"5DU3PVUW","created_at":"2026-07-05T07:10:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5DU3PVUW45ACHHR2XSJZAKYRC3","target":"record","payload":{"canonical_record":{"source":{"id":"2311.04911","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T18:31:02Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"79a918c2568fb9a88504c17c0742c67141025b3ddae0b8423bede26d94f0a368","abstract_canon_sha256":"bae5d8a897e12772e56d2f1315241fe830c0d92266d276d8af050c46b3a399cb"},"schema_version":"1.0"},"canonical_sha256":"e8e9b7d696e740239e3abc93902b1116eca246e578b919734fb6f5f14aa26c7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:51.718351Z","signature_b64":"RmN6enl+QDs2i0dUoUuV9gJz/oC1k5RVia0h23zH15jcRhDmAp0uAkCdZPqXkNyAzpZFGL0GWwJpj5ruKBl9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8e9b7d696e740239e3abc93902b1116eca246e578b919734fb6f5f14aa26c7d","last_reissued_at":"2026-07-05T07:10:51.717891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:51.717891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.04911","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":"2026-07-05T07:10:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MUj/t0VZFTyjadsOtOGjJ0XO4ShveRpH/cjb4MN2XBE5rYtEX0Vr6ks2MFf2nxiKruhBvjn/fvtgvXJfHkhJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:22:43.412109Z"},"content_sha256":"dee2c63d3abf9016ad36a8462aeedc67a7453b020737d0185745d0d7b97cba89","schema_version":"1.0","event_id":"sha256:dee2c63d3abf9016ad36a8462aeedc67a7453b020737d0185745d0d7b97cba89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5DU3PVUW45ACHHR2XSJZAKYRC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Hannes Westermann, Jaromir Savelka, Jinzhe Tan, Karim Benyekhlef, Samyar Janatian","submitted_at":"2023-11-01T18:31:02Z","abstract_excerpt":"Encoding legislative text in a formal representation is an important prerequisite to different tasks in the field of AI & Law. For example, rule-based expert systems focused on legislation can support laypeople in understanding how legislation applies to them and provide them with helpful context and information. However, the process of analyzing legislation and other sources to encode it in the desired formal representation can be time-consuming and represents a bottleneck in the development of such systems. Here, we investigate to what degree large language models (LLMs), such as GPT-4, are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04911","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/2311.04911/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":"2026-07-05T07:10:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S2P6fkfvflOO4Jdz6yS88QwwTN4ItftHwUtKIpkFn04a6Fu9xcO+O4a0YBXV7qN2zCig9IcyhNPPLlkSH0nTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:22:43.412625Z"},"content_sha256":"37c187e3b2ff779b0b436b527cd050fc86a8037fdd028461c66e61865840e459","schema_version":"1.0","event_id":"sha256:37c187e3b2ff779b0b436b527cd050fc86a8037fdd028461c66e61865840e459"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5DU3PVUW45ACHHR2XSJZAKYRC3/bundle.json","state_url":"https://pith.science/pith/5DU3PVUW45ACHHR2XSJZAKYRC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5DU3PVUW45ACHHR2XSJZAKYRC3/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":"2026-08-10T16:22:43Z","links":{"resolver":"https://pith.science/pith/5DU3PVUW45ACHHR2XSJZAKYRC3","bundle":"https://pith.science/pith/5DU3PVUW45ACHHR2XSJZAKYRC3/bundle.json","state":"https://pith.science/pith/5DU3PVUW45ACHHR2XSJZAKYRC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5DU3PVUW45ACHHR2XSJZAKYRC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5DU3PVUW45ACHHR2XSJZAKYRC3","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":"bae5d8a897e12772e56d2f1315241fe830c0d92266d276d8af050c46b3a399cb","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T18:31:02Z","title_canon_sha256":"79a918c2568fb9a88504c17c0742c67141025b3ddae0b8423bede26d94f0a368"},"schema_version":"1.0","source":{"id":"2311.04911","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04911","created_at":"2026-07-05T07:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04911v1","created_at":"2026-07-05T07:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04911","created_at":"2026-07-05T07:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"5DU3PVUW45AC","created_at":"2026-07-05T07:10:51Z"},{"alias_kind":"pith_short_16","alias_value":"5DU3PVUW45ACHHR2","created_at":"2026-07-05T07:10:51Z"},{"alias_kind":"pith_short_8","alias_value":"5DU3PVUW","created_at":"2026-07-05T07:10:51Z"}],"graph_snapshots":[{"event_id":"sha256:37c187e3b2ff779b0b436b527cd050fc86a8037fdd028461c66e61865840e459","target":"graph","created_at":"2026-07-05T07:10:51Z","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/2311.04911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Encoding legislative text in a formal representation is an important prerequisite to different tasks in the field of AI & Law. For example, rule-based expert systems focused on legislation can support laypeople in understanding how legislation applies to them and provide them with helpful context and information. However, the process of analyzing legislation and other sources to encode it in the desired formal representation can be time-consuming and represents a bottleneck in the development of such systems. Here, we investigate to what degree large language models (LLMs), such as GPT-4, are ","authors_text":"Hannes Westermann, Jaromir Savelka, Jinzhe Tan, Karim Benyekhlef, Samyar Janatian","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T18:31:02Z","title":"From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04911","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:dee2c63d3abf9016ad36a8462aeedc67a7453b020737d0185745d0d7b97cba89","target":"record","created_at":"2026-07-05T07:10:51Z","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":"bae5d8a897e12772e56d2f1315241fe830c0d92266d276d8af050c46b3a399cb","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T18:31:02Z","title_canon_sha256":"79a918c2568fb9a88504c17c0742c67141025b3ddae0b8423bede26d94f0a368"},"schema_version":"1.0","source":{"id":"2311.04911","kind":"arxiv","version":1}},"canonical_sha256":"e8e9b7d696e740239e3abc93902b1116eca246e578b919734fb6f5f14aa26c7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8e9b7d696e740239e3abc93902b1116eca246e578b919734fb6f5f14aa26c7d","first_computed_at":"2026-07-05T07:10:51.717891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:51.717891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RmN6enl+QDs2i0dUoUuV9gJz/oC1k5RVia0h23zH15jcRhDmAp0uAkCdZPqXkNyAzpZFGL0GWwJpj5ruKBl9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:51.718351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.04911","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dee2c63d3abf9016ad36a8462aeedc67a7453b020737d0185745d0d7b97cba89","sha256:37c187e3b2ff779b0b436b527cd050fc86a8037fdd028461c66e61865840e459"],"state_sha256":"e5ab6e23965413fb1b6818e46073120d9609259420b9ed879aaa68e805d5220e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MSfRCd90ildWKBFKCrGzT/CC3VJQuR4OrreAs1ythOTVmIWLAFGr31mr1yO+gbPv9K4h4JitAD6tL15an/ZnBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:22:43.418339Z","bundle_sha256":"1d19c9602956598f953b956d49799751aae0d899c9e55dc0fb6b87cb2e936157"}}