{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JNKMZ5VX4IIP3OYBJAJNV7F5HR","short_pith_number":"pith:JNKMZ5VX","schema_version":"1.0","canonical_sha256":"4b54ccf6b7e210fdbb014812dafcbd3c7bfda059236ddff95199f29b63d6edca","source":{"kind":"arxiv","id":"2604.13583","version":3},"attestation_state":"computed","paper":{"title":"BenGER Platform: A Collaborative Web Platform for End-to-End Benchmarking of German Legal Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"BenGER integrates task design, annotation, LLM runs, and multi-metric evaluation into a single collaborative web platform for German legal benchmarks.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Matthias Grabmair, Sebastian Nagl","submitted_at":"2026-04-15T07:43:01Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2604.13583","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-15T07:43:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4e8169df2011655b12c1d2e7d5c1766740526698da81213548a3a322164e050","abstract_canon_sha256":"a593f9c7ad7a88631c7d65bbac90e5a57e6274d42a1bce6135f44a4fd6124ccb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:40.092947Z","signature_b64":"fQArn44vAH5l8saqEwbvCqtvbj+L8OTUIllsJ/o4vGuR0+uWDFObtVagV9w6SOKxgEkqe5wGrRvDeg66ZxBCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b54ccf6b7e210fdbb014812dafcbd3c7bfda059236ddff95199f29b63d6edca","last_reissued_at":"2026-05-28T01:04:40.092219Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:40.092219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BenGER Platform: A Collaborative Web Platform for End-to-End Benchmarking of German Legal Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"BenGER integrates task design, annotation, LLM runs, and multi-metric evaluation into a single collaborative web platform for German legal benchmarks.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Matthias Grabmair, Sebastian Nagl","submitted_at":"2026-04-15T07:43:01Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"BenGER integrates task design, annotation, LLM runs, and multi-metric evaluation into a single collaborative web platform for German legal benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8a1085bcd9e26c9a5be4b5c6e525e701894fa8b0830ff55ef7db2fa7235986f8"},"source":{"id":"2604.13583","kind":"arxiv","version":3},"verdict":{"id":"93fa6909-6939-45d0-ae55-516d5164ae3b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T13:45:09.899118Z","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.","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","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.","pith_extraction_headline":"BenGER integrates task design, annotation, LLM runs, and multi-metric evaluation into a single collaborative web platform for German legal benchmarks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.13583/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.13583","created_at":"2026-05-28T01:04:40.092306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.13583v3","created_at":"2026-05-28T01:04:40.092306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13583","created_at":"2026-05-28T01:04:40.092306+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNKMZ5VX4IIP","created_at":"2026-05-28T01:04:40.092306+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNKMZ5VX4IIP3OYB","created_at":"2026-05-28T01:04:40.092306+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNKMZ5VX","created_at":"2026-05-28T01:04:40.092306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR","json":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR.json","graph_json":"https://pith.science/api/pith-number/JNKMZ5VX4IIP3OYBJAJNV7F5HR/graph.json","events_json":"https://pith.science/api/pith-number/JNKMZ5VX4IIP3OYBJAJNV7F5HR/events.json","paper":"https://pith.science/paper/JNKMZ5VX"},"agent_actions":{"view_html":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR","download_json":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR.json","view_paper":"https://pith.science/paper/JNKMZ5VX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.13583&json=true","fetch_graph":"https://pith.science/api/pith-number/JNKMZ5VX4IIP3OYBJAJNV7F5HR/graph.json","fetch_events":"https://pith.science/api/pith-number/JNKMZ5VX4IIP3OYBJAJNV7F5HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/action/storage_attestation","attest_author":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/action/author_attestation","sign_citation":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/action/citation_signature","submit_replication":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/action/replication_record"}},"created_at":"2026-05-28T01:04:40.092306+00:00","updated_at":"2026-05-28T01:04:40.092306+00:00"}