{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RS2JABHSRW3DOGIJLXXKSIZTNK","short_pith_number":"pith:RS2JABHS","schema_version":"1.0","canonical_sha256":"8cb49004f28db63719095deea923336ab187bc6f65fa48436945f23434ca78ab","source":{"kind":"arxiv","id":"2601.21008","version":3},"attestation_state":"computed","paper":{"title":"ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"David Simchi-Levi, Ruicheng Ao, Xinshang Wang","submitted_at":"2026-01-28T20:02:44Z","abstract_excerpt":"Operations Research practitioners debug infeasible models through an iterative process: inspecting Irreducible Infeasible Subsystems ( IIS), identifying constraint conflicts, and repairing formulations until feasibility is restored. Existing LLM benchmarks mostly treat OR as one-shot translation from problem descriptions to solver code, omitting this diagnostic loop. We formalize infeasible-model repair as a solver-in-the-loop Markov Decision Process in which each action triggers solver re-execution and IIS recomputation, yielding deterministic, verifiable feedback. We introduce ORLoopBench, a"},"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":"2601.21008","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T20:02:44Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"f4f1ebdbbb63651d0ae17278429b7a437a5cc01efe2a43c16441ae4d845a6d5d","abstract_canon_sha256":"513f2a218dbfbd8cea2eadbbfb99f2f19b063786e395066693bf3809c49a3d13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:55.404195Z","signature_b64":"09zWtxHlBdT85di7riis0tyN1bgVZAFxi6i1sERoSWlLz0UsVyNj1Y1fXiRvsebQ5m6A+Qoivc/6q3JO/U7tBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cb49004f28db63719095deea923336ab187bc6f65fa48436945f23434ca78ab","last_reissued_at":"2026-05-27T01:04:55.403451Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:55.403451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"David Simchi-Levi, Ruicheng Ao, Xinshang Wang","submitted_at":"2026-01-28T20:02:44Z","abstract_excerpt":"Operations Research practitioners debug infeasible models through an iterative process: inspecting Irreducible Infeasible Subsystems ( IIS), identifying constraint conflicts, and repairing formulations until feasibility is restored. Existing LLM benchmarks mostly treat OR as one-shot translation from problem descriptions to solver code, omitting this diagnostic loop. We formalize infeasible-model repair as a solver-in-the-loop Markov Decision Process in which each action triggers solver re-execution and IIS recomputation, yielding deterministic, verifiable feedback. We introduce ORLoopBench, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21008","kind":"arxiv","version":3},"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/2601.21008/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":"2601.21008","created_at":"2026-05-27T01:04:55.403558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21008v3","created_at":"2026-05-27T01:04:55.403558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21008","created_at":"2026-05-27T01:04:55.403558+00:00"},{"alias_kind":"pith_short_12","alias_value":"RS2JABHSRW3D","created_at":"2026-05-27T01:04:55.403558+00:00"},{"alias_kind":"pith_short_16","alias_value":"RS2JABHSRW3DOGIJ","created_at":"2026-05-27T01:04:55.403558+00:00"},{"alias_kind":"pith_short_8","alias_value":"RS2JABHS","created_at":"2026-05-27T01:04:55.403558+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/RS2JABHSRW3DOGIJLXXKSIZTNK","json":"https://pith.science/pith/RS2JABHSRW3DOGIJLXXKSIZTNK.json","graph_json":"https://pith.science/api/pith-number/RS2JABHSRW3DOGIJLXXKSIZTNK/graph.json","events_json":"https://pith.science/api/pith-number/RS2JABHSRW3DOGIJLXXKSIZTNK/events.json","paper":"https://pith.science/paper/RS2JABHS"},"agent_actions":{"view_html":"https://pith.science/pith/RS2JABHSRW3DOGIJLXXKSIZTNK","download_json":"https://pith.science/pith/RS2JABHSRW3DOGIJLXXKSIZTNK.json","view_paper":"https://pith.science/paper/RS2JABHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21008&json=true","fetch_graph":"https://pith.science/api/pith-number/RS2JABHSRW3DOGIJLXXKSIZTNK/graph.json","fetch_events":"https://pith.science/api/pith-number/RS2JABHSRW3DOGIJLXXKSIZTNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RS2JABHSRW3DOGIJLXXKSIZTNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RS2JABHSRW3DOGIJLXXKSIZTNK/action/storage_attestation","attest_author":"https://pith.science/pith/RS2JABHSRW3DOGIJLXXKSIZTNK/action/author_attestation","sign_citation":"https://pith.science/pith/RS2JABHSRW3DOGIJLXXKSIZTNK/action/citation_signature","submit_replication":"https://pith.science/pith/RS2JABHSRW3DOGIJLXXKSIZTNK/action/replication_record"}},"created_at":"2026-05-27T01:04:55.403558+00:00","updated_at":"2026-05-27T01:04:55.403558+00:00"}