{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JHHPU2V4MX5AUSS66CC25EVWIW","short_pith_number":"pith:JHHPU2V4","schema_version":"1.0","canonical_sha256":"49cefa6abc65fa0a4a5ef085ae92b64599b9a9cacee22ea6b5f0ab4bf8aa07f6","source":{"kind":"arxiv","id":"2607.16777","version":1},"attestation_state":"computed","paper":{"title":"JOR-Bench: Japanese Operations Research Benchmarks for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yuu Jinnai","submitted_at":"2026-07-18T11:24:10Z","abstract_excerpt":"We present JOR-Bench, a collection of five Japanese-language benchmarks for evaluating the ability of large language models (LLMs) to formulate and solve operations research (OR) problems. Each benchmark is a Japanese translation of an existing English benchmark: IndustryOR, MAMO Complex LP, NL4OPT, OptiBench, and OptMATH, covering 1,319 problems spanning linear programming, mixed-integer programming, non-linear programming, and combinatorial optimization. JOR-Bench is a solver-independent benchmark that can be used with any solver or programming language, and consists of pairs of Japanese pro"},"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":"2607.16777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-18T11:24:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e6e09310adc48f970a5328ec52807ea6d91d640ed324f525e189953fdabf493","abstract_canon_sha256":"66b59a20ea19348bb065e6c936ea0dc1f0021a8ef590163ca40fe1fbc9b0db9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:58.603257Z","signature_b64":"dTnYczAyv73vFkJmib947V+OuBC1rnbAEcRSg942q2faXSzsBd7J34Bkcn8y3GVhlRjKHLE8iosxZCcbpX8UDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49cefa6abc65fa0a4a5ef085ae92b64599b9a9cacee22ea6b5f0ab4bf8aa07f6","last_reissued_at":"2026-07-21T01:20:58.602430Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:58.602430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JOR-Bench: Japanese Operations Research Benchmarks for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yuu Jinnai","submitted_at":"2026-07-18T11:24:10Z","abstract_excerpt":"We present JOR-Bench, a collection of five Japanese-language benchmarks for evaluating the ability of large language models (LLMs) to formulate and solve operations research (OR) problems. Each benchmark is a Japanese translation of an existing English benchmark: IndustryOR, MAMO Complex LP, NL4OPT, OptiBench, and OptMATH, covering 1,319 problems spanning linear programming, mixed-integer programming, non-linear programming, and combinatorial optimization. JOR-Bench is a solver-independent benchmark that can be used with any solver or programming language, and consists of pairs of Japanese pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16777","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.16777/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":"2607.16777","created_at":"2026-07-21T01:20:58.602863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16777v1","created_at":"2026-07-21T01:20:58.602863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16777","created_at":"2026-07-21T01:20:58.602863+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHHPU2V4MX5A","created_at":"2026-07-21T01:20:58.602863+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHHPU2V4MX5AUSS6","created_at":"2026-07-21T01:20:58.602863+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHHPU2V4","created_at":"2026-07-21T01:20:58.602863+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/JHHPU2V4MX5AUSS66CC25EVWIW","json":"https://pith.science/pith/JHHPU2V4MX5AUSS66CC25EVWIW.json","graph_json":"https://pith.science/api/pith-number/JHHPU2V4MX5AUSS66CC25EVWIW/graph.json","events_json":"https://pith.science/api/pith-number/JHHPU2V4MX5AUSS66CC25EVWIW/events.json","paper":"https://pith.science/paper/JHHPU2V4"},"agent_actions":{"view_html":"https://pith.science/pith/JHHPU2V4MX5AUSS66CC25EVWIW","download_json":"https://pith.science/pith/JHHPU2V4MX5AUSS66CC25EVWIW.json","view_paper":"https://pith.science/paper/JHHPU2V4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16777&json=true","fetch_graph":"https://pith.science/api/pith-number/JHHPU2V4MX5AUSS66CC25EVWIW/graph.json","fetch_events":"https://pith.science/api/pith-number/JHHPU2V4MX5AUSS66CC25EVWIW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHHPU2V4MX5AUSS66CC25EVWIW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHHPU2V4MX5AUSS66CC25EVWIW/action/storage_attestation","attest_author":"https://pith.science/pith/JHHPU2V4MX5AUSS66CC25EVWIW/action/author_attestation","sign_citation":"https://pith.science/pith/JHHPU2V4MX5AUSS66CC25EVWIW/action/citation_signature","submit_replication":"https://pith.science/pith/JHHPU2V4MX5AUSS66CC25EVWIW/action/replication_record"}},"created_at":"2026-07-21T01:20:58.602863+00:00","updated_at":"2026-07-21T01:20:58.602863+00:00"}