{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ICB6T36ZQETPCKJZPP3WC5SZCD","short_pith_number":"pith:ICB6T36Z","canonical_record":{"source":{"id":"2505.12837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T08:25:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd6aa180b7792c1004fa93f9693163a10e3dfd66a645f353277fc5b44dcdce84","abstract_canon_sha256":"253829219c75cbcba43f0d9e88ffd9ca87691a6f45c7f5d4e7888ddd86ec4323"},"schema_version":"1.0"},"canonical_sha256":"4083e9efd98126f129397bf761765910f4b7d67c18b24f2795b9bc75c43c93a2","source":{"kind":"arxiv","id":"2505.12837","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12837","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12837v1","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12837","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"ICB6T36ZQETP","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"ICB6T36ZQETPCKJZ","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"ICB6T36Z","created_at":"2026-07-05T11:05:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ICB6T36ZQETPCKJZPP3WC5SZCD","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T08:25:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd6aa180b7792c1004fa93f9693163a10e3dfd66a645f353277fc5b44dcdce84","abstract_canon_sha256":"253829219c75cbcba43f0d9e88ffd9ca87691a6f45c7f5d4e7888ddd86ec4323"},"schema_version":"1.0"},"canonical_sha256":"4083e9efd98126f129397bf761765910f4b7d67c18b24f2795b9bc75c43c93a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:10.441820Z","signature_b64":"JZiSudLgpy7JGTzcxZAv89gUDF9sWd+2C1eVPrCh6oTUea6/5uy29Nyuna8HPRlRpdYJy9dNmAKAQvh57gLHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4083e9efd98126f129397bf761765910f4b7d67c18b24f2795b9bc75c43c93a2","last_reissued_at":"2026-07-05T11:05:10.441422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:10.441422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12837","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":"2026-07-05T11:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9OiHkBsZ8Rmfaw38UiXnYv0g84dSWs/GSciUMQLTz8cEOw6tZ7NS4bjW0K8U3damkrD7vEAwJTFs0IucldNQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:36:25.243573Z"},"content_sha256":"b58120b930161e92e0c425fc158292ce0499b8878c71853ee783589d2aa4cbb8","schema_version":"1.0","event_id":"sha256:b58120b930161e92e0c425fc158292ce0499b8878c71853ee783589d2aa4cbb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ICB6T36ZQETPCKJZPP3WC5SZCD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Lilienbeck, Christian Braun, Daniel Mentjukov","submitted_at":"2025-05-19T08:25:21Z","abstract_excerpt":"Legal contracts possess an inherent, semantically vital structure (e.g., sections, clauses) that is crucial for human comprehension but whose impact on LLM processing remains under-explored. This paper investigates the effects of explicit input text structure and prompt engineering on the performance of GPT-4o and GPT-4.1 on a legal question-answering task using an excerpt of the CUAD. We compare model exact-match accuracy across various input formats: well-structured plain-text (human-generated from CUAD), plain-text cleaned of line breaks, extracted plain-text from Azure OCR, plain-text extr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12837","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/2505.12837/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":"2026-07-05T11:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"czOop1KnCg8WICdkgq4tYiRh2qn7qsDM5A9bZiAsCOBkQJT+E8+JnMK+VSsrQEEM0ztQNMeumlrZbviyzinjDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:36:25.244142Z"},"content_sha256":"de92c3cd9552b3d030f788deedef249ba44a4fdf2e2e8b01419d14a66c0939b2","schema_version":"1.0","event_id":"sha256:de92c3cd9552b3d030f788deedef249ba44a4fdf2e2e8b01419d14a66c0939b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICB6T36ZQETPCKJZPP3WC5SZCD/bundle.json","state_url":"https://pith.science/pith/ICB6T36ZQETPCKJZPP3WC5SZCD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICB6T36ZQETPCKJZPP3WC5SZCD/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":"2026-08-05T09:36:25Z","links":{"resolver":"https://pith.science/pith/ICB6T36ZQETPCKJZPP3WC5SZCD","bundle":"https://pith.science/pith/ICB6T36ZQETPCKJZPP3WC5SZCD/bundle.json","state":"https://pith.science/pith/ICB6T36ZQETPCKJZPP3WC5SZCD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICB6T36ZQETPCKJZPP3WC5SZCD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ICB6T36ZQETPCKJZPP3WC5SZCD","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":"253829219c75cbcba43f0d9e88ffd9ca87691a6f45c7f5d4e7888ddd86ec4323","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T08:25:21Z","title_canon_sha256":"cd6aa180b7792c1004fa93f9693163a10e3dfd66a645f353277fc5b44dcdce84"},"schema_version":"1.0","source":{"id":"2505.12837","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12837","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12837v1","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12837","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"ICB6T36ZQETP","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"ICB6T36ZQETPCKJZ","created_at":"2026-07-05T11:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"ICB6T36Z","created_at":"2026-07-05T11:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:de92c3cd9552b3d030f788deedef249ba44a4fdf2e2e8b01419d14a66c0939b2","target":"graph","created_at":"2026-07-05T11:05:10Z","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/2505.12837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Legal contracts possess an inherent, semantically vital structure (e.g., sections, clauses) that is crucial for human comprehension but whose impact on LLM processing remains under-explored. This paper investigates the effects of explicit input text structure and prompt engineering on the performance of GPT-4o and GPT-4.1 on a legal question-answering task using an excerpt of the CUAD. We compare model exact-match accuracy across various input formats: well-structured plain-text (human-generated from CUAD), plain-text cleaned of line breaks, extracted plain-text from Azure OCR, plain-text extr","authors_text":"Alexander Lilienbeck, Christian Braun, Daniel Mentjukov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T08:25:21Z","title":"The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12837","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:b58120b930161e92e0c425fc158292ce0499b8878c71853ee783589d2aa4cbb8","target":"record","created_at":"2026-07-05T11:05:10Z","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":"253829219c75cbcba43f0d9e88ffd9ca87691a6f45c7f5d4e7888ddd86ec4323","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T08:25:21Z","title_canon_sha256":"cd6aa180b7792c1004fa93f9693163a10e3dfd66a645f353277fc5b44dcdce84"},"schema_version":"1.0","source":{"id":"2505.12837","kind":"arxiv","version":1}},"canonical_sha256":"4083e9efd98126f129397bf761765910f4b7d67c18b24f2795b9bc75c43c93a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4083e9efd98126f129397bf761765910f4b7d67c18b24f2795b9bc75c43c93a2","first_computed_at":"2026-07-05T11:05:10.441422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:10.441422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JZiSudLgpy7JGTzcxZAv89gUDF9sWd+2C1eVPrCh6oTUea6/5uy29Nyuna8HPRlRpdYJy9dNmAKAQvh57gLHAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:10.441820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12837","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b58120b930161e92e0c425fc158292ce0499b8878c71853ee783589d2aa4cbb8","sha256:de92c3cd9552b3d030f788deedef249ba44a4fdf2e2e8b01419d14a66c0939b2"],"state_sha256":"32570f39f1d9eafcfacb40315a4690c5830ba9f7aed776ca0890fef6dffa5962"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wa8LdRsOi7Vvsfod7VcBHxGl++XodJYU2rLXEiFVV57Wbf71Ei2eCP9QCn9AweJmxGmmE6ZlOEzgIkcoclJxAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:36:25.254816Z","bundle_sha256":"6db75099d8d96d12f39c07d8279f7754f119d64e02190ac5779a06ddef8372d5"}}