{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N35EDPPTDY6TB2CL5XHGT7JX2R","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":"960b22b7e3c8053d46baa8a0fab01d5da7ebc02e92c1ea4422b5e745283ff434","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T12:31:43Z","title_canon_sha256":"db957254d6a35e62ec169c1a6ff63b9f3c801a58cb882087fe9ba615749bda71"},"schema_version":"1.0","source":{"id":"2505.02854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02854","created_at":"2026-07-05T10:58:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02854v1","created_at":"2026-07-05T10:58:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02854","created_at":"2026-07-05T10:58:48Z"},{"alias_kind":"pith_short_12","alias_value":"N35EDPPTDY6T","created_at":"2026-07-05T10:58:48Z"},{"alias_kind":"pith_short_16","alias_value":"N35EDPPTDY6TB2CL","created_at":"2026-07-05T10:58:48Z"},{"alias_kind":"pith_short_8","alias_value":"N35EDPPT","created_at":"2026-07-05T10:58:48Z"}],"graph_snapshots":[{"event_id":"sha256:ff8637279e1c73be83a46236bf98061d9a6dc5ad6f407052cf59544290447289","target":"graph","created_at":"2026-07-05T10:58:48Z","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/2505.02854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reproducibility and reliability remain pressing challenges for generative AI systems whose behavior can drift with each model update or prompt revision. We introduce GPR-bench, a lightweight, extensible benchmark that operationalizes regression testing for general purpose use cases. GPR-bench couples an open, bilingual (English and Japanese) dataset covering eight task categories (e.g., text generation, code generation, and information retrieval) and 10 scenarios in each task categories (80 total test cases for each language) with an automated evaluation pipeline that employs \"LLM-as-a-Judge\" ","authors_text":"Masumi Morishige, Ryo Koshihara","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T12:31:43Z","title":"Ensuring Reproducibility in Generative AI Systems for General Use Cases: A Framework for Regression Testing and Open Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02854","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":"sha256:3b2f4905ba0487e1f7c2e4479ad9b3ce45d60deccbb504cb0e5308432948eaab","target":"record","created_at":"2026-07-05T10:58:48Z","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":"960b22b7e3c8053d46baa8a0fab01d5da7ebc02e92c1ea4422b5e745283ff434","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T12:31:43Z","title_canon_sha256":"db957254d6a35e62ec169c1a6ff63b9f3c801a58cb882087fe9ba615749bda71"},"schema_version":"1.0","source":{"id":"2505.02854","kind":"arxiv","version":1}},"canonical_sha256":"6efa41bdf31e3d30e84bedce69fd37d4482581a532fb6516d0441e0920565e80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6efa41bdf31e3d30e84bedce69fd37d4482581a532fb6516d0441e0920565e80","first_computed_at":"2026-07-05T10:58:48.194582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:48.194582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"buElbL91//8TKjmshMwcOO9MVsIDXclFSwNoglFxs5/SKKAXZ5LWKb3OsSwb7Fr5ZYdI5sM/LQJ/x8/ywjeyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:48.195015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b2f4905ba0487e1f7c2e4479ad9b3ce45d60deccbb504cb0e5308432948eaab","sha256:ff8637279e1c73be83a46236bf98061d9a6dc5ad6f407052cf59544290447289"],"state_sha256":"2473538f6cfb7b6ea7b9d067d8f6d1fc47da19ac38c554b486d9523030ff6d0b"}