{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JNKMZ5VX4IIP3OYBJAJNV7F5HR","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":"a593f9c7ad7a88631c7d65bbac90e5a57e6274d42a1bce6135f44a4fd6124ccb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-15T07:43:01Z","title_canon_sha256":"b4e8169df2011655b12c1d2e7d5c1766740526698da81213548a3a322164e050"},"schema_version":"1.0","source":{"id":"2604.13583","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.13583","created_at":"2026-05-28T01:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2604.13583v3","created_at":"2026-05-28T01:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13583","created_at":"2026-05-28T01:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"JNKMZ5VX4IIP","created_at":"2026-05-28T01:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"JNKMZ5VX4IIP3OYB","created_at":"2026-05-28T01:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"JNKMZ5VX","created_at":"2026-05-28T01:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:a80e3895584cdbc5483ff331b3c200ec3528308b23ad92cdf13120fd8f338620","target":"graph","created_at":"2026-05-28T01:04:40Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We present the BenGER (Benchmark for German Law) framework, an open-source web platform that integrates task creation, collaborative annotation, configurable LLM runs, and evaluation with lexical, semantic, factual, and judge-based metrics. BenGER supports multi-organization projects with tenant isolation and role-based access control, and can optionally provide formative, reference-grounded feedback to annotators."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That integrating task design, annotation, LLM execution, and multi-metric evaluation into a single web platform with tenant isolation and role-based access will meaningfully improve transparency, reproducibility, and participation by non-technical legal experts compared to existing split workflows."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"BenGER is a collaborative web platform that integrates end-to-end workflows for creating, annotating, running, and evaluating benchmarks on German legal tasks with large language models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"BenGER integrates task design, annotation, LLM runs, and multi-metric evaluation into a single collaborative web platform for German legal benchmarks."}],"snapshot_sha256":"8a1085bcd9e26c9a5be4b5c6e525e701894fa8b0830ff55ef7db2fa7235986f8"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.13583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language models (LLMs) for legal reasoning requires workflows that span task design, expert annotation, model execution, and metric-based evaluation. In practice, these steps are split across platforms and scripts, limiting transparency, reproducibility, and participation by non-technical legal experts. We present the BenGER (Benchmark for German Law) framework, an open-source web platform that integrates task creation, collaborative annotation, configurable LLM runs, and evaluation with lexical, semantic, factual, and judge-based metrics. BenGER supports multi-organization pr","authors_text":"Matthias Grabmair, Sebastian Nagl","cross_cats":["cs.AI"],"headline":"BenGER integrates task design, annotation, LLM runs, and multi-metric evaluation into a single collaborative web platform for German legal benchmarks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-15T07:43:01Z","title":"BenGER Platform: A Collaborative Web Platform for End-to-End Benchmarking of German Legal Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.13583","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T13:45:09.899118Z","id":"93fa6909-6939-45d0-ae55-516d5164ae3b","model_set":{"reader":"grok-4.3"},"one_line_summary":"BenGER is a collaborative web platform that integrates end-to-end workflows for creating, annotating, running, and evaluating benchmarks on German legal tasks with large language models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"BenGER integrates task design, annotation, LLM runs, and multi-metric evaluation into a single collaborative web platform for German legal benchmarks.","strongest_claim":"We present the BenGER (Benchmark for German Law) framework, an open-source web platform that integrates task creation, collaborative annotation, configurable LLM runs, and evaluation with lexical, semantic, factual, and judge-based metrics. BenGER supports multi-organization projects with tenant isolation and role-based access control, and can optionally provide formative, reference-grounded feedback to annotators.","weakest_assumption":"That integrating task design, annotation, LLM execution, and multi-metric evaluation into a single web platform with tenant isolation and role-based access will meaningfully improve transparency, reproducibility, and participation by non-technical legal experts compared to existing split workflows."}},"verdict_id":"93fa6909-6939-45d0-ae55-516d5164ae3b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a779f8ace7b550505f2bc5a2e84a562b82cfba0a510945fad7e76701d041a244","target":"record","created_at":"2026-05-28T01:04:40Z","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":"a593f9c7ad7a88631c7d65bbac90e5a57e6274d42a1bce6135f44a4fd6124ccb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-15T07:43:01Z","title_canon_sha256":"b4e8169df2011655b12c1d2e7d5c1766740526698da81213548a3a322164e050"},"schema_version":"1.0","source":{"id":"2604.13583","kind":"arxiv","version":3}},"canonical_sha256":"4b54ccf6b7e210fdbb014812dafcbd3c7bfda059236ddff95199f29b63d6edca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b54ccf6b7e210fdbb014812dafcbd3c7bfda059236ddff95199f29b63d6edca","first_computed_at":"2026-05-28T01:04:40.092219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:40.092219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fQArn44vAH5l8saqEwbvCqtvbj+L8OTUIllsJ/o4vGuR0+uWDFObtVagV9w6SOKxgEkqe5wGrRvDeg66ZxBCBQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:40.092947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.13583","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a779f8ace7b550505f2bc5a2e84a562b82cfba0a510945fad7e76701d041a244","sha256:a80e3895584cdbc5483ff331b3c200ec3528308b23ad92cdf13120fd8f338620"],"state_sha256":"51f14f9fb46346509455801ec9ee0f0cbae1884d6c5c26d89823a852bfd7c3c5"}