{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JNKMZ5VX4IIP3OYBJAJNV7F5HR","short_pith_number":"pith:JNKMZ5VX","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"},"canonical_sha256":"4b54ccf6b7e210fdbb014812dafcbd3c7bfda059236ddff95199f29b63d6edca","source":{"kind":"arxiv","id":"2604.13583","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JNKMZ5VX4IIP3OYBJAJNV7F5HR","target":"record","payload":{"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"},"canonical_sha256":"4b54ccf6b7e210fdbb014812dafcbd3c7bfda059236ddff95199f29b63d6edca","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"},"source_kind":"arxiv","source_id":"2604.13583","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+QTRh674QoXVzIzPTpP/LQm2Q0rz0B7FmgDw1JoGipgpiD53T3YbUj7Gx/27Oi369YsrguWP2K/bXTE7yyADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T19:32:14.379076Z"},"content_sha256":"a779f8ace7b550505f2bc5a2e84a562b82cfba0a510945fad7e76701d041a244","schema_version":"1.0","event_id":"sha256:a779f8ace7b550505f2bc5a2e84a562b82cfba0a510945fad7e76701d041a244"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JNKMZ5VX4IIP3OYBJAJNV7F5HR","target":"graph","payload":{"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"},"verdict_id":"93fa6909-6939-45d0-ae55-516d5164ae3b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X42EmeMmUvU0z9ZqHbrxSIpfLl6sgRkXK8/0wPrjVP3S+BGxfAVcVwcsxW2UXpWu6dW+CIPUkLbbJsLnFQI9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T19:32:14.379564Z"},"content_sha256":"a80e3895584cdbc5483ff331b3c200ec3528308b23ad92cdf13120fd8f338620","schema_version":"1.0","event_id":"sha256:a80e3895584cdbc5483ff331b3c200ec3528308b23ad92cdf13120fd8f338620"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/bundle.json","state_url":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/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":"2026-06-04T19:32:14Z","links":{"resolver":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR","bundle":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/bundle.json","state":"https://pith.science/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JNKMZ5VX4IIP3OYBJAJNV7F5HR/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LWDHYUGkxtIQ0JtCQDnk/r32sYXDG/sHW8DejNocXuxvJ8ue92oTao4DyfS4zQbUGboZm+CXB+8NA70fYBvCDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T19:32:14.381939Z","bundle_sha256":"3623568b758c342acdf5afe459945608457ad38ac3e1e8790cd5787a08631034"}}