{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OPRECC22UXJYILLJGG4YL6CH4Q","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":"afa3d774dd89a2c41700bff907927d7ef1e69eab243265fe01aa6842be04973e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T15:20:16Z","title_canon_sha256":"2b1fcfc65b441ded39558ce47e7d98358a069820b69eeef76ee61bf43a4de084"},"schema_version":"1.0","source":{"id":"2605.16052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16052","created_at":"2026-05-20T00:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16052v1","created_at":"2026-05-20T00:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16052","created_at":"2026-05-20T00:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"OPRECC22UXJY","created_at":"2026-05-20T00:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"OPRECC22UXJYILLJ","created_at":"2026-05-20T00:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"OPRECC22","created_at":"2026-05-20T00:01:50Z"}],"graph_snapshots":[{"event_id":"sha256:668c9404940b9fddcd099c32a9ab35c20c366a89a43282a7cdc13aa665d2e5c7","target":"graph","created_at":"2026-05-20T00:01:50Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:41.554517Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.527572Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.16052/integrity.json","findings":[],"snapshot_sha256":"4f1b015492cc68a8423a3cc5d9f916d29e76b05c9066e6d4f7bf795a05643f11","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have significantly enhanced automated legal reasoning. Yet, it remains unclear whether their performance reflects genuine legal reasoning ability or artifacts of data contamination. We present a comprehensive empirical study of tax law reasoning approaches and implement a contamination detection protocol to rigorously assess LLM reliability. We show that performance can be inflated by contamination. Building on this analysis, we conduct a systematic evaluation, comparing monolithic LLMs with hybrid systems that translate statutory text into forma","authors_text":"Enrico Santus, Leslie Barrett, Madhavan Seshadri, Parisa Kordjamshidi, Samer Aslan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T15:20:16Z","title":"Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax Law"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16052","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:a2110df7840bb9e29fce7c21f6b191f1c5dd522fdd213a56a901b1104e997d2d","target":"record","created_at":"2026-05-20T00:01:50Z","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":"afa3d774dd89a2c41700bff907927d7ef1e69eab243265fe01aa6842be04973e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T15:20:16Z","title_canon_sha256":"2b1fcfc65b441ded39558ce47e7d98358a069820b69eeef76ee61bf43a4de084"},"schema_version":"1.0","source":{"id":"2605.16052","kind":"arxiv","version":1}},"canonical_sha256":"73e2410b5aa5d3842d6931b985f847e428356c55054d3b21d8858ccdb8ad43e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73e2410b5aa5d3842d6931b985f847e428356c55054d3b21d8858ccdb8ad43e4","first_computed_at":"2026-05-20T00:01:50.765220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:50.765220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FMGaFvw4cTznaNUIylOs0zZWLipr8u40WL/uaHcQdB69ogf4wgpejBLhZrEdsIFzDrKSSxOVAoLCTmnBkAArDg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:50.765746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2110df7840bb9e29fce7c21f6b191f1c5dd522fdd213a56a901b1104e997d2d","sha256:668c9404940b9fddcd099c32a9ab35c20c366a89a43282a7cdc13aa665d2e5c7"],"state_sha256":"b7dea37b88f8034a68d17261c726f2ee14c616fd71330d28abd0c2fcb7edf304"}