{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CWIKAVR2HL3ASPMF4AVVYBIU5A","short_pith_number":"pith:CWIKAVR2","schema_version":"1.0","canonical_sha256":"1590a0563a3af6093d85e02b5c0514e819994c9811ff66d8fdae13c93337a37a","source":{"kind":"arxiv","id":"2607.02141","version":1},"attestation_state":"computed","paper":{"title":"A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bei Yu, Dongfang Wu, Haodong Lu, Libo Shen, Rongliang Fu, Shuo Ren, Tsung-Yi Ho, Yaohui Han, Yifan Shi","submitted_at":"2026-07-02T13:18:57Z","abstract_excerpt":"Most LP-from-text benchmarks are static datasets of word problems written and labeled by hand. Once such a dataset is released, its size is fixed, its difficulty is fixed, and every problem can leak into the training data of future LLMs. We present \\textbf{A$^{2}$utoLPBench}, a benchmark for testing LLM-driven agents on linear programming problems written in plain text. We first pick a feasible point and dual, then write down a problem for which that point is optimal and the objective value is known. The answer is known by construction, with no solver call and no human annotator. The evaluatio"},"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":"2607.02141","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T13:18:57Z","cross_cats_sorted":[],"title_canon_sha256":"d46b66a97ca3ee9755bce3e0c0f4172adfca651c653f214517ae2ffbddebcccd","abstract_canon_sha256":"bdea49e6ef1f068081e7694a060697363c82358bf3cd80fa65094bfe2b81b35c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:43.281226Z","signature_b64":"qY5HvT3w+ZfVfdOaVG71FA2NPCxuEaGE0kaxAtfzGEQ/Lyq79NldjsX9w4CUGHS5SMSSC6P/FJkrCIxG586CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1590a0563a3af6093d85e02b5c0514e819994c9811ff66d8fdae13c93337a37a","last_reissued_at":"2026-07-03T01:17:43.280800Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:43.280800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bei Yu, Dongfang Wu, Haodong Lu, Libo Shen, Rongliang Fu, Shuo Ren, Tsung-Yi Ho, Yaohui Han, Yifan Shi","submitted_at":"2026-07-02T13:18:57Z","abstract_excerpt":"Most LP-from-text benchmarks are static datasets of word problems written and labeled by hand. Once such a dataset is released, its size is fixed, its difficulty is fixed, and every problem can leak into the training data of future LLMs. We present \\textbf{A$^{2}$utoLPBench}, a benchmark for testing LLM-driven agents on linear programming problems written in plain text. We first pick a feasible point and dual, then write down a problem for which that point is optimal and the objective value is known. The answer is known by construction, with no solver call and no human annotator. The evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02141","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/2607.02141/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":"2607.02141","created_at":"2026-07-03T01:17:43.280868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02141v1","created_at":"2026-07-03T01:17:43.280868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02141","created_at":"2026-07-03T01:17:43.280868+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWIKAVR2HL3A","created_at":"2026-07-03T01:17:43.280868+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWIKAVR2HL3ASPMF","created_at":"2026-07-03T01:17:43.280868+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWIKAVR2","created_at":"2026-07-03T01:17:43.280868+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/CWIKAVR2HL3ASPMF4AVVYBIU5A","json":"https://pith.science/pith/CWIKAVR2HL3ASPMF4AVVYBIU5A.json","graph_json":"https://pith.science/api/pith-number/CWIKAVR2HL3ASPMF4AVVYBIU5A/graph.json","events_json":"https://pith.science/api/pith-number/CWIKAVR2HL3ASPMF4AVVYBIU5A/events.json","paper":"https://pith.science/paper/CWIKAVR2"},"agent_actions":{"view_html":"https://pith.science/pith/CWIKAVR2HL3ASPMF4AVVYBIU5A","download_json":"https://pith.science/pith/CWIKAVR2HL3ASPMF4AVVYBIU5A.json","view_paper":"https://pith.science/paper/CWIKAVR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02141&json=true","fetch_graph":"https://pith.science/api/pith-number/CWIKAVR2HL3ASPMF4AVVYBIU5A/graph.json","fetch_events":"https://pith.science/api/pith-number/CWIKAVR2HL3ASPMF4AVVYBIU5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWIKAVR2HL3ASPMF4AVVYBIU5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWIKAVR2HL3ASPMF4AVVYBIU5A/action/storage_attestation","attest_author":"https://pith.science/pith/CWIKAVR2HL3ASPMF4AVVYBIU5A/action/author_attestation","sign_citation":"https://pith.science/pith/CWIKAVR2HL3ASPMF4AVVYBIU5A/action/citation_signature","submit_replication":"https://pith.science/pith/CWIKAVR2HL3ASPMF4AVVYBIU5A/action/replication_record"}},"created_at":"2026-07-03T01:17:43.280868+00:00","updated_at":"2026-07-03T01:17:43.280868+00:00"}